Diplomado de Ciencia de los Datos en el ITLA

Módulo II

Introducción al Análisis de Series de Tiempo con $\textsf{R}$

Recursos

Librerías de $\textsf{R}$



In [3]:

    
# Librerías
suppressPackageStartupMessages(library(stringr))    # manejo de strings (caracteres)
suppressPackageStartupMessages(library(zoo))        # manejo de clases para series temporales
suppressPackageStartupMessages(library(lubridate))  # manejo de fechas
suppressPackageStartupMessages(library(xts))        # manejo de clases para series temporales, incluye series irreg
suppressPackageStartupMessages(library(quantmod))   # manejo del workflow de modelos cuantitativos financieros
suppressPackageStartupMessages(library(tseries))    # manejo de series irregulares
suppressPackageStartupMessages(library(forecast))   # varios metodos para pronóstico
suppressPackageStartupMessages(library(TSstudio))   # gráficos y análisis de series de tiempo usando plotly
suppressPackageStartupMessages(library(plyr))       # métodos para split-apply-combine usando dataframes  
suppressPackageStartupMessages(library(dplyr))      # manipulacion de datos - tidyverse
suppressPackageStartupMessages(library(tidyr))      # manipulación de datos - tidyverse (spread, gather)
suppressPackageStartupMessages(library(Hmisc))      # algunas funciones de interes para describir datos 
suppressPackageStartupMessages(library(data.table)) # manipulacion de datos mayor rapidez que dplyr
suppressPackageStartupMessages(library(readxl))     # lectura de archivos de excel
suppressPackageStartupMessages(library(IRdisplay))  # despliegue de resultados en jupyter para R
suppressPackageStartupMessages(library(xtable))     # manejo de formato de tablas en R
suppressPackageStartupMessages(library(ggplot2))    # manipulacion de graficos - tidyverse
suppressPackageStartupMessages(library(scales))     # manejo de escalas en ggplot2
suppressPackageStartupMessages(library(corrplot))   # grafico de correlacion

Caso de estudio y datos

Rossmann Store Sales

Pronóstico de ventas utilizando datos de la tienda, promoción y competencia

https://www.kaggle.com/c/rossmann-store-sales

Caso de estudio

Rossmann opera más de 3,000 tiendas [de farmacia y misceláneos] en 7 países europeos. Actualmente, los gerentes de las tiendas Rossmann tienen la tarea de predecir sus ventas diarias con hasta seis semanas de anticipación. Las ventas de las tiendas están influenciadas por muchos factores, que incluyen promociones, competencia, vacaciones escolares y estatales, estacionalidad y localidad. Con miles de gerentes individuales que predicen las ventas en función de sus circunstancias únicas, la precisión de los resultados puede ser muy variada.
Rossmann presenta un desafío de predecir 6 semanas de ventas diarias para 1,115 tiendas ubicadas en toda Alemania. Las previsiones de ventas fiables permiten a los gerentes de las tiendas crear cronogramas efectivos de personal que aumenten la productividad y la motivación. Al ayudar a Rossmann a crear un modelo de predicción robusto, los gerentes de las tiendas se mantendrán enfocados en lo que es más importante para ellos: ¡sus clientes y su personal!

Datos

Descripción de los datos

Ventas históricas para 1,115 tiendas de Rossmann. La tarea consiste en predecir la columna ventas (Sales) para el test data set. Nota: Algunas tiendas el conjunto de datos estuvieron temporalmente cerradas por remodelación.

Archivos

train.csv - datos históricos incluyendo las ventas (Sales)
test.csv - datos históricos excluyendo las ventas (Sales)
store.csv - información complementaria acerca de las tiendas
sample_submission.csv - una muestra del archivo para someter a la competencia en el formato correcto. La competancia ya está cerrada y nuestro propósito es pedagógico no competitivo, de manera que no vamos a realizar un sometimiento

Explicación de los campos que requieren explicación

Id - un identificador que representa una dupla de tienda y fecha (Store, Date) en los datos de test
Store - un identificador único para cada tienda
Sales - el monto de ventas para un día determinado (esto es lo que se pide predecir)
Customers - el número de clientes en un día determinado
Open - un indicador de si la tienda estuvo abierta: 0 = cerrada, 1 = abierta
StateHoliday - indica un día festivo a nivel estatal. Normalmente todas las tiendas, con pocas excepciones, están cerradas en los días festivos estatales. Nota: todas las escuelas están cerradas en los días festivos públicos y en los fines de semana. a = festivo público, b = festivo pascual, c = Navidad, 0 = ninguno
SchoolHoliday - indica si la dupla tienda y fecha (Store, Date) estuvo afectada por el cierre de las escuelas públicas
StoreType - diferencia entre 4 modelos de tienda: a, b, c, d
Assortment - describe un nivel de surtido: a = basico, b = extra, c = extendido
CompetitionDistance - distancia en metros de la tienda del competidor más cercano
CompetitionOpenSince[Month/Year] - proporciona un aproximado del mes y año a partir de los cuales el competidor más cercano abrió
Promo - indica si una tienda está ofreciendo una promoción en dicho día
Promo2 - Promo2 es una promoción continuada y consecutiva para algunas tiendas: 0 = la tienda no está participando, 1 = la tienda está participando
Promo2Since[Year/Week] - describe el año y la semana calendario en que la tienda empezó a participar en Promo2
PromoInterval - describe los intervalos consecutivos en los que Promo2 da inicio, nombrando los meses en que la promoción se reestablece. Por ejemplo: "Feb,May,Aug,Nov" significa que cada ronda inicia en Febrero, Mayo, Agosto, Noviembre de cada año para dicha tienda

Nota: Según el estándar ISO 8601, el lunes es el primer día de la semana. Seguido del martes, miércoles, jueves, viernes y sábado. Domingo es el 7mo y último día. Aunque algunos países, incluyendo USA, Canada y Australia, consideran el domingo como el inicio de la semana, para nuestro caso el Comité Europeo de Estandarización (CEN) adoptó ISO 8601. Sin embargo, debemos tener cuidado porque en R muchas funciones como .indexwday de xts siguen el criterio de 0 = Domingo.



In [4]:

    
# Datos ####
data.dir <- "./data/Rossmann\ Store\ Sales"

# data.table más rápido en la extracción y manipulación
train <- fread(paste0(data.dir, "/train.csv"), stringsAsFactors = T)
test  <- fread(paste0(data.dir, "/test.csv"), stringsAsFactors = T)
store <- fread(paste0(data.dir, "/store.csv"), stringsAsFactors = T)

# Train data set
train.store <- merge(train, store, by = "Store")

train.store[ , Date := as.Date(Date)]
train.store <- train.store[order(Store, Date)]

# Test data set
test.store <- merge(test, store, by = "Store")

test.store[ , Date := as.Date(Date)]
test.store <- test.store[order(Store, Date)]

print("Fin")

Breve introducción al análisis de series de tiempo

Tipos de datos en analítica

Para la investigación o análisis de una misma entidad podemos trabajar con varios tipos de datos:

Datos de corte transversal: observaciones registradas en un mismo momento de tiempo. Ejemplo: Censo de población.
Series de tiempo: observaciones registradas en diferentes momentos de tiempo.
Datos de panel (o longitudinales): observaciones multidimensionales que combinan datos de corte transversal de varios individuos y series de tiempo.
Datos espaciales: observaciones registradas en diferentes puntos del espacio físico o virtual

Series de tiempo

Una serie de tiempo consiste en una sucesión de observaciones (valores, mediciones) vinculadas a una misma variable ($X$) registradas en diferentes momentos en el tiempo ($t$).

Típicamente este registro se hace a intervalos regulares:

$$X_{t_{0}},X_{t_{0}+h},X_{t_{0}+2h},...,$$

Donde, $h$ es la cantidad de tiempo entre observaciones, también llamado intervalo de muestreo, y $1/h$ es la frecuencia o tasa de muestreo.

Ejemplos reales

Precios de las acciones en el mercadeo de valores
Variables económicas
Variables de clima
Demanda de energía
Pronóstico de ventas
Procesamiento de señales
Datos capturados por sensores (IoT)

¿En qué consiste el análisis de series de tiempo?

El análisis de series de tiempo consiste en el empleo de diferentes métodos (matemáticos, estadísticos y de machine learning) que permitan extraer información relevante de un conjunto de datos con dependencia temporal, para diferentes propósitos:

Predicción (pronóstico = forecasting)
Explicación descripción de los atributos más sobresalientes y/o entendimiento del mecanismo generador
Control del proceso que produce la serie

NOTA:

El análisis de series de tiempo (TSA) y el procesamiento estadístico de señales (SSP) tienen el mismo objeto de estudio, pero difieren en su origen, extracción y enfoque dominante.

	TSA	SSP
Origen	Economía	Ingenieria
Extracción	Registro	Procesamiento
Domina	Predicción	Explicación

https://stats.stackexchange.com/questions/52270/relations-and-differences-between-time-series-analysis-and-statistical-signal-pr

Supuestos estadísticos y series de tiempo

Supuestos que hemos mantenido hasta ahora en el aprendizaje estadístico:

Los datos que representan un mismo evento (variable) son generados aleatoriamiente de manera independiente e idéntica (independet and identically distributed = i.i.d. = iid = IID). Es decir, cada punto de observación es generado por la misma distribución de probabilidad que los otros y todos los puntos de datos son mutuamente independientes entre sí.
Por tanto, en el caso del aprendizaje supervisado los datos de entrenamiento (training data) tienen la misma distribución que los datos de prueba (test data).
Asimismo, las distribuciones de probabilidad se mantiene fijas en el tiempo (estacionariedad).

Sin embargo, estos supuestos raramente se mantienen para las series de tiempo reales, las cuales están afectadas por uno o varios componentes de dependencia temporal: autocorrelación serial, tendencia, estacionalidad, etc.

¿Qué hace particularmente difícil la predicción de series de tiempo (pronóstico = forecasting) ?

La posibilidad de múltiples dependencias (al menos temporal, pero también cruzada si la serie es multivariada)
La no-estacionariedad
El horizonte de predicción, que puede ser no sólo de un único periodo (one-step ahead) sino múltiple (multi-step)
La necesidad de detectar y lidiar con posible ruido y no-linealidad
La necesidad de resolver en conjunto varios temas de sesgo / varianza de diferente origen: múltiples dependencias, dimensionalidad, horizonte, ruido, no-linealidad, etc.
El carácter irreversible de algunas series temporales (series económicas y financieras)
Los aspectos de control, intervención y causalidad
La existencia de diferentes técnicas y métodos en diferentes disciplinas, con la dificultad de establecer a priori las ventajas y aspectos más relevantes

Métodos en el Análisis de Series de Tiempo

Según el número de variables involucradas
- Univariado: solo una misma serie y su historia
- Multivariado: varias series relacionadas y sus historias
Según su dominio
- Temporal
  - Autocorrelación
  - Correlación cruzada
- De Frecuencia
  - Análisis espectral (espectro de frecuencias)
  - Análisis de wavelets (ondículas = oscilaciones en torno a una amplitud cero)
Según sus parámetros sean fijos o no
- Paramétrico
  - Lineal univariado:
    - AR|MA, AR[I]MA, AR[FI]MA, AR[FI]MA[X]
  - Lineal multivariado: VAR, VECM, ...
  - No-Lineal: [C]GARCH, [E][G]ARCH, [FI][G]ARCH, [T]ARCH, ...
- No-paramétrico
  - Holt, ETS (Error, Trend, Seasonality), Theta,...
  - MARS
  - [Ver -> Machine Learning]
Según se considere o no el espacio de estados
- Estático
- Dinámico
  - State-Space Models (continuo)
  - Hidden Markov Models (discreto)
Según la condición de linealidad
- Lineal
- No-Lineal
  - Machine Learning
    - kNN
    - Trees (CART, Random Forest, XGBoost)
    - SVM
    - ANN (MLP, BNN) & Deep Learning (RNN, LSTM)
  - Topológico:
    Reconstrucción de un espacio de estados (fases) a partir las medidas invariantes obtenidas de la serie como órbita de un sistema dinámico

Estudio comparativo de pronósticos de una serie temporal mediante métodos estadísticos tradicionales vs machine learning

NOTA: El error de porcentaje absoluto medio simétrico (Symmetric Mean Absolute Percent Error = sMAPE) es una alternativa al error de porcentaje absoluto medio (Mean Absolute Percent Error = MAPE) ante la posibilidad de eventos de con valores de baja ocurrencia. sMAPE se autolimita con una tasa de error del 200%, que reduce la influencia de tales valores. De lo contrario se podrían tener tasas de error infinitamente altas que sesgan la tasa de error general.

Alcance

En nuestro caso nos estaremos circunscribiendo al análisis de series temporales de tipo lineal univariado y multivariado utilizando modelos de regresión que nos permitan tratar la no-estacionariedad.
Aunque el caso tiene un enfoque predominantemente predictivo, por fines pedagógicos extenderemos la fase de exploración de datos con fines de obtener un mayor entendimiento sobre el tema de negocio y también unos datos de mayor calidad.

Caso Rossmann: Exploración de los datos y manejo de valores perdidos



In [3]:

    
# Sumario Train
dim(train.store)
str(train.store)
summary(train.store)
describe(train.store)
head(train.store)









    





	1017209
	18








    



Classes ‘data.table’ and 'data.frame':	1017209 obs. of  18 variables:
 $ Store                    : int  1 1 1 1 1 1 1 1 1 1 ...
 $ DayOfWeek                : int  2 3 4 5 6 7 1 2 3 4 ...
 $ Date                     : Date, format: "2013-01-01" "2013-01-02" ...
 $ Sales                    : int  0 5530 4327 4486 4997 0 7176 5580 5471 4892 ...
 $ Customers                : int  0 668 578 619 635 0 785 654 626 615 ...
 $ Open                     : int  0 1 1 1 1 0 1 1 1 1 ...
 $ Promo                    : int  0 0 0 0 0 0 1 1 1 1 ...
 $ StateHoliday             : Factor w/ 4 levels "0","a","b","c": 2 1 1 1 1 1 1 1 1 1 ...
 $ SchoolHoliday            : Factor w/ 2 levels "0","1": 2 2 2 2 2 2 2 2 2 2 ...
 $ StoreType                : Factor w/ 4 levels "a","b","c","d": 3 3 3 3 3 3 3 3 3 3 ...
 $ Assortment               : Factor w/ 3 levels "a","b","c": 1 1 1 1 1 1 1 1 1 1 ...
 $ CompetitionDistance      : int  1270 1270 1270 1270 1270 1270 1270 1270 1270 1270 ...
 $ CompetitionOpenSinceMonth: int  9 9 9 9 9 9 9 9 9 9 ...
 $ CompetitionOpenSinceYear : int  2008 2008 2008 2008 2008 2008 2008 2008 2008 2008 ...
 $ Promo2                   : int  0 0 0 0 0 0 0 0 0 0 ...
 $ Promo2SinceWeek          : int  NA NA NA NA NA NA NA NA NA NA ...
 $ Promo2SinceYear          : int  NA NA NA NA NA NA NA NA NA NA ...
 $ PromoInterval            : Factor w/ 4 levels "","Feb,May,Aug,Nov",..: 1 1 1 1 1 1 1 1 1 1 ...
 - attr(*, ".internal.selfref")=<externalptr> 






    





     Store          DayOfWeek          Date                Sales      
 Min.   :   1.0   Min.   :1.000   Min.   :2013-01-01   Min.   :    0  
 1st Qu.: 280.0   1st Qu.:2.000   1st Qu.:2013-08-17   1st Qu.: 3727  
 Median : 558.0   Median :4.000   Median :2014-04-02   Median : 5744  
 Mean   : 558.4   Mean   :3.998   Mean   :2014-04-11   Mean   : 5774  
 3rd Qu.: 838.0   3rd Qu.:6.000   3rd Qu.:2014-12-12   3rd Qu.: 7856  
 Max.   :1115.0   Max.   :7.000   Max.   :2015-07-31   Max.   :41551  
                                                                      
   Customers           Open            Promo        StateHoliday SchoolHoliday
 Min.   :   0.0   Min.   :0.0000   Min.   :0.0000   0:986159     0:835488     
 1st Qu.: 405.0   1st Qu.:1.0000   1st Qu.:0.0000   a: 20260     1:181721     
 Median : 609.0   Median :1.0000   Median :0.0000   b:  6690                  
 Mean   : 633.1   Mean   :0.8301   Mean   :0.3815   c:  4100                  
 3rd Qu.: 837.0   3rd Qu.:1.0000   3rd Qu.:1.0000                             
 Max.   :7388.0   Max.   :1.0000   Max.   :1.0000                             
                                                                              
 StoreType  Assortment CompetitionDistance CompetitionOpenSinceMonth
 a:551627   a:537445   Min.   :   20       Min.   : 1.0             
 b: 15830   b:  8294   1st Qu.:  710       1st Qu.: 4.0             
 c:136840   c:471470   Median : 2330       Median : 8.0             
 d:312912              Mean   : 5430       Mean   : 7.2             
                       3rd Qu.: 6890       3rd Qu.:10.0             
                       Max.   :75860       Max.   :12.0             
                       NA's   :2642        NA's   :323348           
 CompetitionOpenSinceYear     Promo2       Promo2SinceWeek  Promo2SinceYear 
 Min.   :1900             Min.   :0.0000   Min.   : 1.0     Min.   :2009    
 1st Qu.:2006             1st Qu.:0.0000   1st Qu.:13.0     1st Qu.:2011    
 Median :2010             Median :1.0000   Median :22.0     Median :2012    
 Mean   :2009             Mean   :0.5006   Mean   :23.3     Mean   :2012    
 3rd Qu.:2013             3rd Qu.:1.0000   3rd Qu.:37.0     3rd Qu.:2013    
 Max.   :2015             Max.   :1.0000   Max.   :50.0     Max.   :2015    
 NA's   :323348                            NA's   :508031   NA's   :508031  
          PromoInterval   
                 :508031  
 Feb,May,Aug,Nov :118596  
 Jan,Apr,Jul,Oct :293122  
 Mar,Jun,Sept,Dec: 97460  
                          
                          
                          






    





train.store 

 18  Variables      1017209  Observations
--------------------------------------------------------------------------------
Store 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
 1017209        0     1115        1    558.4    371.7       56      112 
     .25      .50      .75      .90      .95 
     280      558      838     1004     1060 

lowest :    1    2    3    4    5, highest: 1111 1112 1113 1114 1115
--------------------------------------------------------------------------------
DayOfWeek 
       n  missing distinct     Info     Mean      Gmd 
 1017209        0        7     0.98    3.998    2.283 
                                                           
Value           1      2      3      4      5      6      7
Frequency  144730 145664 145665 145845 145845 144730 144730
Proportion  0.142  0.143  0.143  0.143  0.143  0.142  0.142
--------------------------------------------------------------------------------
Date 
       n  missing distinct 
 1017209        0      942 

lowest : 2013-01-01 2013-01-02 2013-01-03 2013-01-04 2013-01-05
highest: 2015-07-27 2015-07-28 2015-07-29 2015-07-30 2015-07-31
--------------------------------------------------------------------------------
Sales 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
 1017209        0    21734    0.995     5774     4198        0        0 
     .25      .50      .75      .90      .95 
    3727     5744     7856    10288    12137 

lowest :     0    46   124   133   286, highest: 38037 38367 38484 38722 41551
--------------------------------------------------------------------------------
Customers 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
 1017209        0     4086    0.995    633.1    478.1        0        0 
     .25      .50      .75      .90      .95 
     405      609      837     1116     1362 

lowest :    0    3    5    8   13, highest: 5297 5387 5458 5494 7388
--------------------------------------------------------------------------------
Open 
       n  missing distinct     Info      Sum     Mean      Gmd 
 1017209        0        2    0.423   844392   0.8301   0.2821 

--------------------------------------------------------------------------------
Promo 
       n  missing distinct     Info      Sum     Mean      Gmd 
 1017209        0        2    0.708   388080   0.3815   0.4719 

--------------------------------------------------------------------------------
StateHoliday 
       n  missing distinct 
 1017209        0        4 
                                      
Value           0      a      b      c
Frequency  986159  20260   6690   4100
Proportion  0.969  0.020  0.007  0.004
--------------------------------------------------------------------------------
SchoolHoliday 
       n  missing distinct 
 1017209        0        2 
                        
Value           0      1
Frequency  835488 181721
Proportion  0.821  0.179
--------------------------------------------------------------------------------
StoreType 
       n  missing distinct 
 1017209        0        4 
                                      
Value           a      b      c      d
Frequency  551627  15830 136840 312912
Proportion  0.542  0.016  0.135  0.308
--------------------------------------------------------------------------------
Assortment 
       n  missing distinct 
 1017209        0        3 
                               
Value           a      b      c
Frequency  537445   8294 471470
Proportion  0.528  0.008  0.463
--------------------------------------------------------------------------------
CompetitionDistance 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
 1014567     2642      654        1     5430     6845      130      240 
     .25      .50      .75      .90      .95 
     710     2330     6890    15710    20390 

lowest :    20    30    40    50    60, highest: 45740 46590 48330 58260 75860
--------------------------------------------------------------------------------
CompetitionOpenSinceMonth 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
  693861   323348       12    0.988    7.223    3.675        2        3 
     .25      .50      .75      .90      .95 
       4        8       10       11       12 
                                                                         
Value           1      2      3      4      5      6      7      8      9
Frequency   12452  37886  63548  87076  39608  45444  59434  36186 114254
Proportion  0.018  0.055  0.092  0.125  0.057  0.065  0.086  0.052  0.165
                               
Value          10     11     12
Frequency   55622  84455  57896
Proportion  0.080  0.122  0.083
--------------------------------------------------------------------------------
CompetitionOpenSinceYear 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
  693861   323348       23    0.994     2009    5.254     2001     2003 
     .25      .50      .75      .90      .95 
    2006     2010     2013     2014     2015 

lowest : 1900 1961 1990 1994 1995, highest: 2011 2012 2013 2014 2015
--------------------------------------------------------------------------------
Promo2 
       n  missing distinct     Info      Sum     Mean      Gmd 
 1017209        0        2     0.75   509178   0.5006      0.5 

--------------------------------------------------------------------------------
Promo2SinceWeek 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
  509178   508031       24    0.993    23.27    16.06        1        5 
     .25      .50      .75      .90      .95 
      13       22       37       40       45 

lowest :  1  5  6  9 10, highest: 44 45 48 49 50
--------------------------------------------------------------------------------
Promo2SinceYear 
       n  missing distinct     Info     Mean      Gmd 
  509178   508031        7    0.968     2012    1.884 
                                                           
Value        2009   2010   2011   2012   2013   2014   2015
Frequency   65270  56240 115056  73174 110464  79922   9052
Proportion  0.128  0.110  0.226  0.144  0.217  0.157  0.018
--------------------------------------------------------------------------------
PromoInterval 
       n  missing distinct 
 1017209        0        4 
                                                                              
Value                        Feb,May,Aug,Nov  Jan,Apr,Jul,Oct Mar,Jun,Sept,Dec
Frequency            508031           118596           293122            97460
Proportion            0.499            0.117            0.288            0.096
--------------------------------------------------------------------------------






    





Store DayOfWeek Date Sales Customers Open Promo StateHoliday SchoolHoliday StoreType Assortment CompetitionDistance CompetitionOpenSinceMonth CompetitionOpenSinceYear Promo2 Promo2SinceWeek Promo2SinceYear PromoInterval

	1         2         2013-01-01    0        0       0         0         a         1         c         a         1270      9         2008      0         NA        NA                  
	1         3         2013-01-02 5530      668       1         0         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         4         2013-01-03 4327      578       1         0         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         5         2013-01-04 4486      619       1         0         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         6         2013-01-05 4997      635       1         0         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         7         2013-01-06    0        0       0         0         0         1         c         a         1270      9         2008      0         NA        NA



In [4]:

    
# Sumario Test
dim(test.store)
str(test.store)
summary(test.store)
describe(test.store)
head(test.store)









    





	41088
	17








    



Classes ‘data.table’ and 'data.frame':	41088 obs. of  17 variables:
 $ Store                    : int  1 1 1 1 1 1 1 1 1 1 ...
 $ Id                       : int  40233 39377 38521 37665 36809 35953 35097 34241 33385 32529 ...
 $ DayOfWeek                : int  6 7 1 2 3 4 5 6 7 1 ...
 $ Date                     : Date, format: "2015-08-01" "2015-08-02" ...
 $ Open                     : int  1 0 1 1 1 1 1 1 0 1 ...
 $ Promo                    : int  0 0 1 1 1 1 1 0 0 0 ...
 $ StateHoliday             : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
 $ SchoolHoliday            : Factor w/ 2 levels "0","1": 2 2 2 2 2 2 2 2 2 2 ...
 $ StoreType                : Factor w/ 4 levels "a","b","c","d": 3 3 3 3 3 3 3 3 3 3 ...
 $ Assortment               : Factor w/ 3 levels "a","b","c": 1 1 1 1 1 1 1 1 1 1 ...
 $ CompetitionDistance      : int  1270 1270 1270 1270 1270 1270 1270 1270 1270 1270 ...
 $ CompetitionOpenSinceMonth: int  9 9 9 9 9 9 9 9 9 9 ...
 $ CompetitionOpenSinceYear : int  2008 2008 2008 2008 2008 2008 2008 2008 2008 2008 ...
 $ Promo2                   : int  0 0 0 0 0 0 0 0 0 0 ...
 $ Promo2SinceWeek          : int  NA NA NA NA NA NA NA NA NA NA ...
 $ Promo2SinceYear          : int  NA NA NA NA NA NA NA NA NA NA ...
 $ PromoInterval            : Factor w/ 4 levels "","Feb,May,Aug,Nov",..: 1 1 1 1 1 1 1 1 1 1 ...
 - attr(*, ".internal.selfref")=<externalptr> 






    





     Store              Id          DayOfWeek          Date           
 Min.   :   1.0   Min.   :    1   Min.   :1.000   Min.   :2015-08-01  
 1st Qu.: 279.8   1st Qu.:10273   1st Qu.:2.000   1st Qu.:2015-08-12  
 Median : 553.5   Median :20544   Median :4.000   Median :2015-08-24  
 Mean   : 555.9   Mean   :20544   Mean   :3.979   Mean   :2015-08-24  
 3rd Qu.: 832.2   3rd Qu.:30816   3rd Qu.:6.000   3rd Qu.:2015-09-05  
 Max.   :1115.0   Max.   :41088   Max.   :7.000   Max.   :2015-09-17  
                                                                      
      Open            Promo        StateHoliday SchoolHoliday StoreType
 Min.   :0.0000   Min.   :0.0000   0:40908      0:22866       a:22128  
 1st Qu.:1.0000   1st Qu.:0.0000   a:  180      1:18222       b:  576  
 Median :1.0000   Median :0.0000                              c: 4272  
 Mean   :0.8543   Mean   :0.3958                              d:14112  
 3rd Qu.:1.0000   3rd Qu.:1.0000                                       
 Max.   :1.0000   Max.   :1.0000                                       
 NA's   :11                                                            
 Assortment CompetitionDistance CompetitionOpenSinceMonth
 a:20304    Min.   :   20       Min.   : 1.000           
 b:  432    1st Qu.:  720       1st Qu.: 4.000           
 c:20352    Median : 2425       Median : 7.000           
            Mean   : 5089       Mean   : 7.035           
            3rd Qu.: 6480       3rd Qu.: 9.000           
            Max.   :75860       Max.   :12.000           
            NA's   :96          NA's   :15216            
 CompetitionOpenSinceYear     Promo2       Promo2SinceWeek Promo2SinceYear
 Min.   :1900             Min.   :0.0000   Min.   : 1.00   Min.   :2009   
 1st Qu.:2006             1st Qu.:0.0000   1st Qu.:13.00   1st Qu.:2011   
 Median :2010             Median :1.0000   Median :22.00   Median :2012   
 Mean   :2009             Mean   :0.5806   Mean   :24.43   Mean   :2012   
 3rd Qu.:2012             3rd Qu.:1.0000   3rd Qu.:37.00   3rd Qu.:2013   
 Max.   :2015             Max.   :1.0000   Max.   :49.00   Max.   :2015   
 NA's   :15216                             NA's   :17232   NA's   :17232  
          PromoInterval  
                 :17232  
 Feb,May,Aug,Nov : 5712  
 Jan,Apr,Jul,Oct :13776  
 Mar,Jun,Sept,Dec: 4368  
                         
                         
                         






    





test.store 

 17  Variables      41088  Observations
--------------------------------------------------------------------------------
Store 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
   41088        0      856        1    555.9    369.8     56.0    113.0 
     .25      .50      .75      .90      .95 
   279.8    553.5    832.2   1004.0   1061.0 

lowest :    1    3    7    8    9, highest: 1111 1112 1113 1114 1115
--------------------------------------------------------------------------------
Id 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
   41088        0    41088        1    20544    13696     2055     4110 
     .25      .50      .75      .90      .95 
   10273    20544    30816    36979    39034 

lowest :     1     2     3     4     5, highest: 41084 41085 41086 41087 41088
--------------------------------------------------------------------------------
DayOfWeek 
       n  missing distinct     Info     Mean      Gmd 
   41088        0        7    0.979    3.979    2.303 
                                                    
Value          1     2     3     4     5     6     7
Frequency   5992  5992  5992  5992  5136  5992  5992
Proportion 0.146 0.146 0.146 0.146 0.125 0.146 0.146
--------------------------------------------------------------------------------
Date 
       n  missing distinct 
   41088        0       48 

lowest : 2015-08-01 2015-08-02 2015-08-03 2015-08-04 2015-08-05
highest: 2015-09-13 2015-09-14 2015-09-15 2015-09-16 2015-09-17
--------------------------------------------------------------------------------
Open 
       n  missing distinct     Info      Sum     Mean      Gmd 
   41077       11        2    0.373    35093   0.8543   0.2489 

--------------------------------------------------------------------------------
Promo 
       n  missing distinct     Info      Sum     Mean      Gmd 
   41088        0        2    0.717    16264   0.3958   0.4783 

--------------------------------------------------------------------------------
StateHoliday 
       n  missing distinct 
   41088        0        2 
                      
Value          0     a
Frequency  40908   180
Proportion 0.996 0.004
--------------------------------------------------------------------------------
SchoolHoliday 
       n  missing distinct 
   41088        0        2 
                      
Value          0     1
Frequency  22866 18222
Proportion 0.557 0.443
--------------------------------------------------------------------------------
StoreType 
       n  missing distinct 
   41088        0        4 
                                  
Value          a     b     c     d
Frequency  22128   576  4272 14112
Proportion 0.539 0.014 0.104 0.343
--------------------------------------------------------------------------------
Assortment 
       n  missing distinct 
   41088        0        3 
                            
Value          a     b     c
Frequency  20304   432 20352
Proportion 0.494 0.011 0.495
--------------------------------------------------------------------------------
CompetitionDistance 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
   40992       96      554        1     5089     6282      120      220 
     .25      .50      .75      .90      .95 
     720     2425     6480    13990    18610 

lowest :    20    30    40    50    60, highest: 40860 46590 48330 58260 75860
--------------------------------------------------------------------------------
CompetitionOpenSinceMonth 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
   25872    15216       12    0.989    7.035    3.602        2        3 
     .25      .50      .75      .90      .95 
       4        7        9       11       12 
                                                                            
Value          1     2     3     4     5     6     7     8     9    10    11
Frequency    480  1440  2688  3024  1536  1632  2976  1392  4320  1968  2496
Proportion 0.019 0.056 0.104 0.117 0.059 0.063 0.115 0.054 0.167 0.076 0.096
                
Value         12
Frequency   1920
Proportion 0.074
--------------------------------------------------------------------------------
CompetitionOpenSinceYear 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
   25872    15216       23    0.993     2009    5.502     2000     2003 
     .25      .50      .75      .90      .95 
    2006     2010     2012     2014     2014 

lowest : 1900 1961 1990 1994 1995, highest: 2011 2012 2013 2014 2015
--------------------------------------------------------------------------------
Promo2 
       n  missing distinct     Info      Sum     Mean      Gmd 
   41088        0        2    0.731    23856   0.5806    0.487 

--------------------------------------------------------------------------------
Promo2SinceWeek 
       n  missing distinct     Info     Mean      Gmd      .05      .10 
   23856    17232       21    0.992    24.43    16.17        1        5 
     .25      .50      .75      .90      .95 
      13       22       37       40       45 

lowest :  1  5  9 10 13, highest: 40 44 45 48 49
--------------------------------------------------------------------------------
Promo2SinceYear 
       n  missing distinct     Info     Mean      Gmd 
   23856    17232        7    0.969     2012    1.917 
                                                    
Value       2009  2010  2011  2012  2013  2014  2015
Frequency   3120  2592  4704  3552  5184  4320   384
Proportion 0.131 0.109 0.197 0.149 0.217 0.181 0.016
--------------------------------------------------------------------------------
PromoInterval 
       n  missing distinct 
   41088        0        4 
                                                                              
Value                        Feb,May,Aug,Nov  Jan,Apr,Jul,Oct Mar,Jun,Sept,Dec
Frequency             17232             5712            13776             4368
Proportion            0.419            0.139            0.335            0.106
--------------------------------------------------------------------------------






    





Store Id DayOfWeek Date Open Promo StateHoliday SchoolHoliday StoreType Assortment CompetitionDistance CompetitionOpenSinceMonth CompetitionOpenSinceYear Promo2 Promo2SinceWeek Promo2SinceYear PromoInterval

	1         40233     6         2015-08-01 1         0         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         39377     7         2015-08-02 0         0         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         38521     1         2015-08-03 1         1         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         37665     2         2015-08-04 1         1         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         36809     3         2015-08-05 1         1         0         1         c         a         1270      9         2008      0         NA        NA                  
	1         35953     4         2015-08-06 1         1         0         1         c         a         1270      9         2008      0         NA        NA



In [5]:

    
# Comparativo de variables: train vs test 
names(test.store)
setdiff(names(train.store), names(test.store))
setdiff(names(test.store), names(train.store))









    





	'Store'
	'Id'
	'DayOfWeek'
	'Date'
	'Open'
	'Promo'
	'StateHoliday'
	'SchoolHoliday'
	'StoreType'
	'Assortment'
	'CompetitionDistance'
	'CompetitionOpenSinceMonth'
	'CompetitionOpenSinceYear'
	'Promo2'
	'Promo2SinceWeek'
	'Promo2SinceYear'
	'PromoInterval'








    





	'Sales'
	'Customers'








    




'Id'

¿Cómo se comportan las ventas de manera global para todas las tiendas?



In [6]:

    
# Ventas Totales
train.all.sum <- as.data.frame(train.store) %>%
  group_by(Date) %>% 
  summarise(Sales = sum(as.numeric(Sales), na.rm = TRUE)) %>% 
  ungroup()

head(train.all.sum)









    





Date Sales

	2013-01-01   97235   
	2013-01-02 6949829   
	2013-01-03 6347820   
	2013-01-04 6638954   
	2013-01-05 5951593   
	2013-01-06  143904



In [30]:

    
# Gráfico de Ventas Totales ####
Date <- train.all.sum$Date

# xts
xts.all.sales <- xts(train.all.sum$Sales, order.by = Date)

# TSstudio
ts_plot(xts.all.sales, 
        title = "Rossmann Stores - Ventas Totales",
        Xtitle = "Fuente: Rossmann Store Sales (Kaggle)", 
        Ytitle = "Sales",
        slider = TRUE
        )

¿Cómo se comportan las ventas totales en fines de semana vs días de semana?



In [31]:

    
# Gráfico de Ventas Totales: Fines de Semana vs Días de Semana

train.dweek.sum <- as.data.frame(train.store) %>%
  mutate(wkend_sales = ifelse(DayOfWeek %in% c(6,7), Sales, 0), 
         wkday_sales = ifelse(!DayOfWeek %in% c(6,7), Sales, 0)) %>%
  group_by(Date) %>% 
  summarise(wkend_sales = sum(wkend_sales, na.rm = T), 
            wkday_sales = sum(wkday_sales, na.rm = T)) %>% 
  ungroup()

xts.dweek.sales <- xts(cbind(train.dweek.sum$wkend_sales, 
                             train.dweek.sum$wkday_sales), 
                       order.by = Date)

#index.wkday <- which(   .indexwday(xts.all.sales) != 6 
#                      & .indexwday(xts.all.sales) != 0)

#index.wkend <- which(   .indexwday(xts.all.sales) == 6 
#                      | .indexwday(xts.all.sales) == 0)

ts_plot(xts.dweek.sales, 
        title = "Rossmann Stores - Ventas Totales (Fines de Semana vs Resto)",
        Xtitle = "Fuente: Rossmann Store Sales (Kaggle)", 
        Ytitle = "Sales",
        type = "single",
        slider = TRUE
        )

¿Cómo se comportan las ventas de manera global en los domingos y festivos no-laborables?



In [32]:

    
# Gráfico de Ventas Totales: Domingos y Feriados

#holidays <- as.data.frame(train.store) %>%
#   dplyr::select(Date, StateHoliday) %>%
#   filter(as.character(StateHoliday) != '0') %>%
#   dplyr::select(Date) %>%
#   distinct()

# str(holidays)

# holidays.dt <- as.Date(holidays[[1]])

# str(holidays.dt)

# Aunque la variable StateHoliday marca los días festivos, parece que no excluye los festivos laborables
# Por eso usamos el siguiente listado:
holidays <- c(
              "2013-01-01", "2013-01-06", "2013-03-29", "2013-04-01", 
              "2013-05-01", "2013-05-09", "2013-05-12", "2013-05-20", 
              "2013-10-03", "2013-12-25", "2013-12-26", "2014-01-01", 
              "2014-04-18", "2014-04-21", "2014-05-01", "2014-05-11", 
              "2014-05-29", "2014-06-09", "2014-10-03", "2014-12-25", 
              "2014-12-26", "2015-01-01", "2015-04-03", "2015-04-06", 
              "2015-05-01", "2015-05-10", "2015-05-14", "2015-05-25"
              )

holidays.dt <- sapply(holidays, function(x) {as.Date(x)})

index.holiday <- which( .indexwday(xts.all.sales) == 0 
                      | index(xts.all.sales) %in% holidays.dt)

ts_plot(xts.all.sales[index.holiday], 
        title = "Rossmann Stores - Ventas Totales (Domingos y Feriados)",
        Xtitle = "Fuente: Rossmann Store Sales (Kaggle)", 
        Ytitle = "Sales",
        slider = TRUE
       )

¿Cómo se comportan las ventas de manera global excluyendo los domingos y feriados?



In [33]:

    
# Gráfico de Ventas Totales: Excluyendo Domingos y Feriados

index.noholiday <- which( .indexwday(xts.all.sales) != 0 
                       & !(index(xts.all.sales) %in% holidays.dt))

ts_plot(xts.all.sales[index.noholiday], 
        title = "Rossmann Stores - Ventas Totales (Sin Domingos ni Feriados)",
        Xtitle = "Fuente: Rossmann Store Sales (Kaggle)", 
        Ytitle = "Sales",
        slider = TRUE
        )

Valores perdidos: registros (Store, Date) con tiendas cerradas y/o con cero ventas



In [34]:

    
train.store.null <- train.store %>%
  dplyr::select(Store, Sales, Open) %>%
  filter(Open == 0 | Sales == 0) %>%
  mutate(store_close = as.numeric(Open == 0)) %>%
  mutate(store_nsale = as.numeric(Open == 1 & Sales == 0)) %>%
  summarise(closed_store_events = sum(store_close),
            null_sales_events = sum(store_nsale),
            store_nd = n_distinct(Store)
           )

train.store.null

print(paste("% de registros (tienda, día) con tienda cerrada y/o cero ventas:", 
            (train.store.null$closed_store_events 
             + train.store.null$null_sales_events) 
            / nrow(train.store) * 100)
     )









    





closed_store_events null_sales_events store_nd

	172817 54    1105  









    



[1] "% de registros (tienda, día) con tienda cerrada y/o cero ventas: 16.9946392530935"

Estos registos con tienda cerrada y/o cero ventas no los tomaremos en cuenta para el ejercicio de predicción, a fin de evitar cualquier sesgo.

Otros valores perdidos



In [35]:

    
train.store %>% 
 summarise_all(funs(sum(is.na(.)))) %>%
 select_if(. > 0)









    





CompetitionDistance CompetitionOpenSinceMonth CompetitionOpenSinceYear Promo2SinceWeek Promo2SinceYear

	2642  323348 323348 508031 508031



In [36]:

    
store %>% 
 summarise_all(funs(sum(is.na(.)))) %>%
 select_if(. > 0)









    





CompetitionDistance CompetitionOpenSinceMonth CompetitionOpenSinceYear Promo2SinceWeek Promo2SinceYear

	3  354 354 544 544

Aparentemente este información consiste simplemente en registros faltantes en los datos, sin ningún patrón particular.
En este caso, hace sentido reemplazar los valores NA con la mediana de los valores para el caso de la variable de distancia y con cero para el resto.



In [6]:

    
### Versión de train.store con tratamiento de valores perdidos
train.store.clean <- train.store %>%
  filter(Open != 0 & Sales != 0) %>%
  mutate(CompetitionDistance = ifelse(is.na(CompetitionDistance)==TRUE, 
                                      median(CompetitionDistance, na.rm = T),
                                     CompetitionDistance)) %>%
  mutate(CompetitionOpenSinceMonth = ifelse(is.na(CompetitionOpenSinceMonth)==TRUE, 0,
                                     CompetitionOpenSinceMonth)) %>%
  mutate(CompetitionOpenSinceYear = ifelse(is.na(CompetitionOpenSinceYear)==TRUE, 0,
                                     CompetitionOpenSinceYear)) %>%
  mutate(Promo2SinceWeek = ifelse(is.na(Promo2SinceWeek)==TRUE, 0,
                                    Promo2SinceWeek)) %>%
  mutate(Promo2SinceYear = ifelse(is.na(Promo2SinceYear)==TRUE, 0,
                                     Promo2SinceYear))
  
  
train.store.clean %>% 
 summarise_all(funs(sum(is.na(.)))) %>%
 dplyr::select(CompetitionDistance, CompetitionOpenSinceMonth, CompetitionOpenSinceYear, 
               Promo2SinceWeek, Promo2SinceYear)









    





CompetitionDistance CompetitionOpenSinceMonth CompetitionOpenSinceYear Promo2SinceWeek Promo2SinceYear

	0 0 0 0 0

Transformaciones y nuevas variables



In [7]:

    
train.store.new <- train.store.clean %>%
  mutate(Year = year(Date),
         Month = month(Date),
         Day = day(Date),
         WeekOfYear = week(Date)) %>%
  mutate(SalesPerCustomer = Sales / Customers) %>%
  mutate(SchoolHoliday = as.numeric(as.character(SchoolHoliday))) %>%
  # Dias abiertos a la competencia y a promociones:
  mutate(CompetitionOpen = 12 * (Year - CompetitionOpenSinceYear) + (Month - CompetitionOpenSinceMonth), 
         PromoOpen = 12 * (Year - Promo2SinceYear) + (WeekOfYear - Promo2SinceWeek) / 4.0)

¿Cómo se comportan las ventas por tipo de tienda?



In [39]:

    
train.store.type.mean <- train.store.new %>%
  dplyr::select(StoreType, Sales, Customers, SalesPerCustomer, CompetitionDistance, CompetitionOpen, PromoOpen) %>%
  # mutate(store_id  = paste0("s-", str_pad(as.character(Store), 4, "left", pad = "0"))) %>%
  group_by(StoreType) %>%
  summarise_all(funs(mean(.)))
  # unite(type_assort, StoreType, Assortment, sep = "_") %>%
  # spread(type_assort, avg_sales, fill = 0)

train.store.type.sum <- train.store.new %>%
  dplyr::select(StoreType, Sales, Customers) %>%
  group_by(StoreType) %>%
  summarise_all(funs(sum(as.numeric(.))))

xtable(train.store.type.sum, auto = TRUE)
xtable(train.store.type.mean, auto = TRUE)









    





StoreType Sales Customers

	a         3165334859 363541431 
	b          159231395  31465616 
	c          783221426  92129705 
	d         1765392943 156904995 









    





StoreType Sales Customers SalesPerCustomer CompetitionDistance CompetitionOpen PromoOpen

	a         6925.698  795.4224  8.846296 5222.894  7115.514 12918.54 
	b        10233.380 2022.2118  5.133427 1072.573 11364.495 17199.37 
	c         6933.126  815.5381  8.626227 3514.147  6745.419 12158.68 
	d         6822.300  606.3539 11.277862 6959.561  9028.527 10421.96

Las tiendas tipo a son las de mayor volumen de ventas totales y las más concurridas, pero también en promedio no parecen de las más expuestas a la competencia.
Las tiendas tipo b son las que tienen el mayor promedio de ventas por tienda, pero las tiendas tipo d son las que tienen el mayor promedio de venta ($) por cliente.
Las tiendas tipo b, a diferencia de las tipo a tienen en promedio la mayor exposición a la competencia y la mayor cantidad de tiempo corriendo promociones.



In [15]:

    
# By week
train.store.type.week <- train.store.new %>%
  dplyr::select(StoreType, Store, Year, WeekOfYear, Sales) %>%
  group_by(StoreType, Store, Year, WeekOfYear) %>%
  summarise_all(funs(sum(.)))

head(train.store.type.week)









    





StoreType Store Year WeekOfYear Sales

	a    2    2013 1    15407
	a    2    2013 2    32914
	a    2    2013 3    21081
	a    2    2013 4    29973
	a    2    2013 5    23297
	a    2    2013 6    31996



In [16]:

    
# Empirical Cumulative Distribution Function (ECDF) por Tienda en cada Tipo de Tienda

# Función para generar ECDF de cada tienda y asociar su tipo 
ts_ecdf <- function(store){
    Store <- unique(store$Store)
    StoreType <- unique(store$StoreType)
    Fn <- ecdf(store$Sales)
  
    y.list <- list()
    y.list <- list(StoreType = StoreType, Store = Store, Fn = Fn)
    
    return(y.list)
}

# Función para colocar en un mismo gráfico las ECDFs de las tiendas de un mismo tipo como argumento
plot_ts_ecdf <- function(type, xmax = 240000){
    ecdf.ls <- dlply(train.store.type.week %>% filter(StoreType == type), .(Store), ts_ecdf)
    # str(ecdf.a.ls)
    # str(sapply(ecdf.a.ls, function(x) x[3]))
    ll <- Map(f  = stat_function, 
          colour = rainbow(length(sapply(ecdf.ls, function(x) x[3]))),
          fun = sapply(ecdf.ls, function(x) x[3]), geom = 'step')
    g <- ggplot(data = data.frame(x = c(0, xmax)), aes(x = x)) + ll + labs(title=paste("ECDFs StoreType =", type), x ="Sales")
    
    return(g)
                       }



In [17]:

    
plot_ts_ecdf("a")



In [18]:

    
plot_ts_ecdf("b")



In [19]:

    
plot_ts_ecdf("c")



In [20]:

    
plot_ts_ecdf("d")

¿Cómo se comportan las ventas por tipo de surtido?



In [40]:

    
# Por tipo de surtido
train.store.assort.mean <- train.store.new %>%
  dplyr::select(Assortment, Sales, Customers, SalesPerCustomer, 
                CompetitionDistance, CompetitionOpen, PromoOpen) %>%
  group_by(Assortment) %>%
  summarise_all(funs(mean(.)))

train.store.assort.sum <- train.store.new %>%
  dplyr::select(Assortment, Sales, Customers) %>%
  group_by(Assortment) %>%
  summarise_all(funs(sum(as.numeric(.))))

xtable(train.store.assort.sum, auto = TRUE)
xtable(train.store.assort.mean, auto = TRUE)









    





Assortment Sales Customers

	a         2945750070 332766935 
	b           70946312  16972520 
	c         2856484241 294302292 









    





Assortment Sales Customers SalesPerCustomer CompetitionDistance CompetitionOpen PromoOpen

	a        6621.523  748.0010  9.130807 4385.694  6359.424 12212.71 
	b        8642.504 2067.5502  4.163726 1189.447 15965.434 13727.96 
	c        7300.844  752.2026 10.018030 6749.628  9116.896 12003.78

El tipo de surtido básico (a) se vincula al mayor volumen de ventas totales y mayor concurrencia, pero en promedio no es el de mayor ventas por cliente, e incluso el menor en promedio de ventas por tienda y promedio de clientes por tienda. ¡Capilaridad de commodities!
El tipo de surtido extra (b) tiene el menor volumen de ventas y la menor concurrencia, pero la mayor venta promedio por tienda aunque la menor por cliente, quizá por la menor distancia respecto de la competencia en las tiendas que lo reciben.
El tipo de surtido extendido (c) es de mayor promedio de venta por cliente, quizá porque se da en tiendas con una competencia más alejada.

¿Cómo se comportan las ventas ante las promociones?



In [42]:

    
train.store.promo.dweek <- train.store.new %>%
  dplyr::select(Promo, Promo2, DayOfWeek, Sales) %>%
  mutate(group = as.factor(paste("Promo =", as.character(Promo), "|", "Promo2 =", as.character(Promo2)))) %>%
  group_by(DayOfWeek, group) %>%
  summarise(avg_sales = mean(Sales))

ggplot(train.store.promo.dweek, aes(group)) + 
geom_line(aes(x = DayOfWeek, y = avg_sales)) +
facet_wrap(~ group)

En promedio, los clientes tienden a comprar más los lunes cuando hay promoción (Promo), pero también en domingos cuando no hay ninguna promoción (Promo y Promo2 son iguales a 0).
No hay Promo en fines de semana (sábados y domingos).
Promo2 por sí sola no parece estar correlacionada con ningún tipo de cambio significativo en el monto de ventas.

Análisis de correlación



In [43]:

    
train.store.corr <- train.store.new %>%
  dplyr::select(-Open) %>%
  select_if(is.numeric)

train.corr.mat <- cor(train.store.corr)

corrplot(train.corr.mat, method = "color", type = "upper")

En general y de manera global, solo Promo tiene correlación positiva significativa con el monto total de ventas (Sales) y con el monto de ventas por cliente (SalesPerCustomer).

Análisis de estacionariedad y autocorrelación

¿Qué hace que una serie de tiempo sea diferente de un problema de regresión regular?

Depende del tiempo. La suposición básica de una regresión lineal de que las observaciones son independientes no se cumple en este caso.
La mayoría de las series de tiempo tienen una tendencia creciente o decreciente con alguna forma de estacionalidad, es decir, variaciones específicas de un marco de tiempo particular. Por ejemplo, para las vacaciones de Navidad, como veremos en este conjunto de datos.

¿Qué se entiende por estacionariedad?

En términos intuitivos, una serie temporal estacionaria es aquella cuyas propiedades no dependen del momento en el que se observa la serie. Entonces, las series de tiempo con tendencias, o con la estacionalidad, en principio no son estacionarias: la tendencia y la estacionalidad afectarán el valor de las series de tiempo en diferentes veces. Por otro lado, una serie de ruido blanco (gaussiana con media cero y desviación estándar 1) es estacionaria, ya que no importa cuando la observe, debería verse de manera similar en cualquier período de tiempo.
Algunos casos pueden ser confusos: una serie temporal con comportamiento cíclico (pero no con tendencia o estacionalidad) es estacionaria. Esto se debe a que los ciclos no son de longitud fija, por lo que antes de observar la serie no podemos estar seguros de dónde estarán los picos y valles de los ciclos.
En general, una serie temporal estacionaria no tendrá patrones predecibles a largo plazo. Los diagramas de tiempo mostrarán que la serie es más o menos horizontal (aunque es posible algún comportamiento cíclico) con varianza constante.

¿Cuáles de estas series son estacionarias?

(a) Indice Dow Jones en 292 días consecutivos
(b) Cambio diario en el índice Dow Jones en 292 días consecutivos
(c) Número anual de huelgas en los Estados Unidos
(d) Ventas mensuales de casas unifamiliares nuevas vendidas en los Estados Unidos
(e) Precio de una docena de huevos en los Estados Unidos (a dólares constantes)
(f) Total mensual de cerdos sacrificados en Victoria (Australia)
(g) Total anual de lince atrapado en el distrito del río McKenzie en el noroeste de Canadá
(h) Producción mensual de cerveza australiana
(i) Producción de electricidad australiana mensual

¿Cuáles de estas series son estacionarias?

La estacionalidad obvia descarta las series (d), (h) y (i).
La tendencia excluye las series (a), (c), (e), (f) y (i).
El aumento de la varianza también descarta (i).
Eso deja solo (b) y (g) como series estacionarias.
A primera vista, los fuertes ciclos de la serie (g) pueden parecer no estacionarios. Pero estos ciclos son aperiódicos: se producen cuando la población de linces se vuelve demasiado grande para el alimento disponible, por lo que dejan de reproducirse y la población cae a números muy bajos, luego la regeneración de sus fuentes de alimentos permite que la población vuelva a crecer, y así en. A largo plazo, el tiempo de estos ciclos no es predecible. Por lo tanto, la serie es estacionaria.

Detección y tratamiento de la estacionariedad

En el panel (a) se observa cómo los datos del índice Dow Jones no eran estacionarios, pero los cambios diarios fueron estacionarios en el panel (b). Esto muestra una forma de hacer una serie temporal estacionaria: calcular las diferencias entre observaciones consecutivas [por ejemplo: $x(t) - x(t-1)$]. Esto se conoce como diferenciación.
Las transformaciones, como los logaritmos, pueden ayudar a estabilizar la varianza de una serie temporal. La diferenciación puede ayudar a estabilizar la media de una serie de tiempo, al eliminar los cambios en el nivel de una serie temporal, y así eliminar la tendencia y la estacionalidad.
Además de ver el gráfico de tiempo, también es útil el gráfico ACF para identificar series temporales no estacionarias. Para una serie temporal estacionaria, el ACF caerá a cero con relativa rapidez, mientras que el ACF de datos no estacionarios disminuirá lentamente. Además, para datos no estacionarios, el valor del coeficiente de autocorrelación menudo es grande y positivo.

¿Cómo podemos proceder con estos datos que tienen 1115 series de tiempo (una por cada tienda) y un máximo de 941 días de observación para cada serie?

Construiremos un análisis preliminar de series de tiempo para cada tipo de tienda. La principal ventaja de este enfoque es su simplicidad de presentación y el hecho que toma en cuenta al menos de manera representativa las diferentes tendencias y estacionalidades en el conjunto de datos.
Para ello consideraremos las siguientes tiendas en representación de cada tipo:
- Store 2: StoreType a
- Store 85: StoreType b
- Store 1: StoreType c
- Store 13: StoreType d
Nota: Además del ejercicio de EDA con ECDF, pudiéramos realizar un análisis no-supervisado de clusters que confirme la homogeneidad prevalente de estas tipologías.
Pregunta: ¿Por qué no hacer un análisis con los valores agregados de todos los tipos en lugar de ejemplos?

Estacionalidad



In [123]:

    
# Función para generar gráficos de estacionalidad por tienda, remuestreando a frecuencia semanal
# Hace sentido reducir la frecuencia de días a semanas para presentar los patrones de estacionalidad más claramente

ts_season <- function(store){
    y <- as.data.frame(train.store.new) %>%
         filter(Store == store) %>%
         group_by(Store, StoreType, Date) %>% 
         summarise(Sales = sum(as.numeric(Sales))) %>% 
         ungroup()
    
    Date <- y$Date
    
    y.xts.w <- apply.weekly(xts(y$Sales, order.by = Date), drop.time = FALSE, sum)
    
    tsplot <- ts_plot(y.xts.w,
        title = paste("Rossmann Stores - Ventas Semanales de la Tienda", y$Store, "Tipo =", y$StoreType),
        Ytitle = "Sales",
        type = "single"
       )
    
    return(tsplot)
}



In [124]:

    
ts_season(2)  # a
ts_season(85) # b
ts_season(1)  # c
ts_season(13) # d

Las ventas minoristas para los casos de StoreType "a" y "c" tienden a llegar a su punto máximo durante la temporada navideña y luego disminuyen después de las vacaciones.
Podríamos haber visto la misma tendencia para el caso de StoreType "d" (en la parte inferior), pero no hay información de julio de 2014 a enero de 2015 sobre estas tiendas, ya que estaban cerradas.

Tendencia



In [121]:

    
# Función para generar gráficos de tendencia por tienda

ts_trend <- function(store){
    y <- as.data.frame(train.store.new) %>%
         filter(Store == store) %>%
         group_by(Store, StoreType, Date) %>% 
         summarise(Sales = sum(as.numeric(Sales))) %>% 
         ungroup()
    
    Date <- y$Date
    
    y.xts <- xts(y$Sales, order.by = Date)
    
    attr(y.xts, 'frequency') <- 365

    y.xts.decomp <- decompose(as.ts(y.xts), type = "additive")

    tsplot <- ts_plot(xts(y.xts.decomp$trend, order.by = Date),
        title = paste("Rossmann Stores - Tendencia Ventas de la Tienda", y$Store, "Tipo =", y$StoreType),
        Ytitle = "Sales",
        type = "single"
       )
    
    return(tsplot)
}



In [122]:

    
ts_trend(2)  # a
ts_trend(85) # b
ts_trend(1)  # c
ts_trend(13) # d









    



































    



































    



































    



Error in decompose(as.ts(y.xts), type = "additive"): time series has no or less than 2 periods
Traceback:

1. ts_trend(13)
2. decompose(as.ts(y.xts), type = "additive")   # at line 16 of file <text>
3. stop("time series has no or less than 2 periods")

En general, las ventas parecen aumentar, sin embargo, no para StoreType "c" (un tercio desde la parte superior).
A pesar de que el StoreType "a" es el tipo de tienda con mayor volumen de ventas en el conjunto de datos, parece que tiene un patrón de decrecimiento similar en gran parte al caso de StoreType "c".

Autocorrelación

El siguiente paso en nuestro análisis es revisar las funciones de autocorrelación ($ACF$) y de autocorrelación parcial ($PACF$).
$ACF$ es una medida de la correlación entre las series temporales con una versión rezagada de sí misma. Por ejemplo, en el desfase o rezago $k$, $ACF$ compararía series en el instante de tiempo $t(1) ... t(n)$ con series en el instante $t(1-k) ... t(n-k)$, donde $t(1-k)$ y $t(n)$ son puntos finales.
$PACF$, por otro lado, mide la correlación entre las series temporales con una versión rezagada de sí misma, pero después de eliminar los rezagos intermedios menores que $k$. Por ejemplo, si $k = 5$, $PACF$ verificará la correlación pero eliminará los efectos ya explicados por los rezagos $1$ a $4$.



In [171]:

    
# Función para generar gráficos de autocorrelación (ACF, PACF) por tienda

ts_autocorr <- function(store, lag = 50){
    y <- as.data.frame(train.store.new) %>%
         filter(Store == store) %>%
         group_by(Store, StoreType, Date) %>% 
         summarise(Sales = sum(as.numeric(Sales))) %>% 
         ungroup()
    
    Date <- y$Date
    
    y.xts <- na.omit(xts(y$Sales, order.by = Date))
    
    yacf  <- acf(y.xts, lag.max = lag)
    ypacf <- pacf(y.xts, lag.max = lag)
     
    return(list(yacf, ypacf))
}



In [172]:

    
# Tienda 2  (Tipo "a")
ts_autocorr(2)









    












    





[[1]]

Autocorrelations of series ‘y.xts’, by lag

     0      1      2      3      4      5      6      7      8      9     10 
 1.000  0.289  0.170 -0.181 -0.085 -0.172  0.077 -0.240 -0.178 -0.215  0.069 
    11     12     13     14     15     16     17     18     19     20     21 
 0.192  0.538  0.130  0.059 -0.104 -0.046 -0.075  0.090 -0.183 -0.143 -0.141 
    22     23     24     25     26     27     28     29     30     31     32 
 0.068  0.133  0.354  0.067  0.021 -0.044  0.000 -0.077  0.012 -0.213 -0.152 
    33     34     35     36     37     38     39     40     41     42     43 
-0.091  0.069  0.119  0.274  0.058  0.047  0.038 -0.016 -0.086 -0.052 -0.209 
    44     45     46     47     48     49     50 
-0.160 -0.073  0.023  0.095  0.157  0.059  0.035 

[[2]]

Partial autocorrelations of series ‘y.xts’, by lag

     1      2      3      4      5      6      7      8      9     10     11 
 0.289  0.094 -0.278  0.023 -0.091  0.131 -0.333 -0.141  0.001  0.108  0.172 
    12     13     14     15     16     17     18     19     20     21     22 
 0.367 -0.152 -0.084  0.068 -0.059  0.003  0.079 -0.019  0.006  0.027  0.030 
    23     24     25     26     27     28     29     30     31     32     33 
-0.024  0.079  0.011 -0.034  0.059  0.007 -0.104 -0.041 -0.029 -0.010  0.033 
    34     35     36     37     38     39     40     41     42     43     44 
 0.017  0.027  0.050 -0.008 -0.003  0.043 -0.102 -0.015  0.002 -0.020 -0.021 
    45     46     47     48     49     50 
-0.022 -0.010  0.028 -0.067  0.030 -0.029



In [173]:

    
# Tienda 85 (Tipo "b")
ts_autocorr(85)









    












    





[[1]]

Autocorrelations of series ‘y.xts’, by lag

     0      1      2      3      4      5      6      7      8      9     10 
 1.000  0.054 -0.009 -0.032 -0.072 -0.135 -0.155  0.510 -0.156 -0.134 -0.095 
    11     12     13     14     15     16     17     18     19     20     21 
-0.065 -0.048 -0.020  0.681 -0.042 -0.061 -0.075 -0.088 -0.127 -0.130  0.519 
    22     23     24     25     26     27     28     29     30     31     32 
-0.137 -0.126 -0.097 -0.098 -0.077 -0.038  0.662 -0.037 -0.050 -0.056 -0.064 
    33     34     35     36     37     38     39     40     41     42     43 
-0.087 -0.105  0.523 -0.123 -0.135 -0.092 -0.118 -0.095 -0.056  0.604 -0.073 
    44     45     46     47     48     49     50 
-0.069 -0.059 -0.086 -0.101 -0.103  0.542 -0.110 

[[2]]

Partial autocorrelations of series ‘y.xts’, by lag

     1      2      3      4      5      6      7      8      9     10     11 
 0.054 -0.012 -0.030 -0.069 -0.129 -0.148  0.538 -0.354 -0.140 -0.067 -0.001 
    12     13     14     15     16     17     18     19     20     21     22 
 0.077  0.114  0.455 -0.165 -0.072 -0.061 -0.020 -0.017  0.005  0.154 -0.079 
    23     24     25     26     27     28     29     30     31     32     33 
-0.058 -0.022 -0.073  0.016  0.058  0.275 -0.043 -0.025 -0.021  0.026  0.043 
    34     35     36     37     38     39     40     41     42     43     44 
-0.004  0.057 -0.016 -0.060  0.039 -0.075 -0.015  0.024  0.090 -0.064 -0.010 
    45     46     47     48     49     50 
-0.017 -0.019 -0.011 -0.006  0.108 -0.014



In [174]:

    
# Tienda 1 (Tipo "c")
ts_autocorr(1)









    












    





[[1]]

Autocorrelations of series ‘y.xts’, by lag

     0      1      2      3      4      5      6      7      8      9     10 
 1.000  0.682  0.481  0.270  0.198  0.015 -0.030 -0.057 -0.009  0.055  0.171 
    11     12     13     14     15     16     17     18     19     20     21 
 0.276  0.333  0.282  0.182  0.094  0.037 -0.019 -0.061 -0.072 -0.023  0.062 
    22     23     24     25     26     27     28     29     30     31     32 
 0.166  0.247  0.297  0.255  0.181  0.111  0.048 -0.059 -0.130 -0.164 -0.123 
    33     34     35     36     37     38     39     40     41     42     43 
-0.071  0.019  0.100  0.139  0.116  0.096  0.054 -0.016 -0.085 -0.140 -0.150 
    44     45     46     47     48     49     50 
-0.130 -0.085  0.011  0.085  0.156  0.143  0.138 

[[2]]

Partial autocorrelations of series ‘y.xts’, by lag

     1      2      3      4      5      6      7      8      9     10     11 
 0.682  0.029 -0.129  0.099 -0.234  0.061  0.040  0.033  0.146  0.120  0.137 
    12     13     14     15     16     17     18     19     20     21     22 
 0.057 -0.096 -0.094 -0.019  0.025  0.018  0.002 -0.005  0.053  0.072  0.072 
    23     24     25     26     27     28     29     30     31     32     33 
 0.057  0.049 -0.056 -0.033  0.015 -0.025 -0.085 -0.026 -0.038  0.025 -0.008 
    34     35     36     37     38     39     40     41     42     43     44 
 0.010  0.040 -0.039 -0.039  0.022 -0.025 -0.042  0.013 -0.029  0.014 -0.009 
    45     46     47     48     49     50 
-0.042  0.091  0.004  0.065 -0.035  0.003



In [175]:

    
# Tienda 3 (Tipo "d")
ts_autocorr(13)









    












    





[[1]]

Autocorrelations of series ‘y.xts’, by lag

     0      1      2      3      4      5      6      7      8      9     10 
 1.000  0.537  0.301  0.045 -0.179 -0.417 -0.482 -0.410 -0.177 -0.029  0.192 
    11     12     13     14     15     16     17     18     19     20     21 
 0.340  0.485  0.300  0.174 -0.022 -0.150 -0.325 -0.357 -0.310 -0.113  0.009 
    22     23     24     25     26     27     28     29     30     31     32 
 0.153  0.276  0.387  0.285  0.195  0.051 -0.076 -0.240 -0.286 -0.305 -0.155 
    33     34     35     36     37     38     39     40     41     42     43 
-0.065  0.088  0.201  0.266  0.179  0.147  0.004 -0.110 -0.241 -0.253 -0.277 
    44     45     46     47     48     49     50 
-0.142 -0.055  0.107  0.223  0.271  0.197  0.154 

[[2]]

Partial autocorrelations of series ‘y.xts’, by lag

     1      2      3      4      5      6      7      8      9     10     11 
 0.537  0.018 -0.173 -0.207 -0.310 -0.166 -0.045  0.141 -0.010  0.086  0.070 
    12     13     14     15     16     17     18     19     20     21     22 
 0.207 -0.142 -0.003 -0.049  0.034 -0.052 -0.030 -0.036  0.062  0.018 -0.029 
    23     24     25     26     27     28     29     30     31     32     33 
 0.048  0.099  0.035  0.043  0.044 -0.007 -0.021  0.001 -0.073  0.036 -0.008 
    34     35     36     37     38     39     40     41     42     43     44 
 0.033 -0.002 -0.046 -0.094  0.041 -0.038 -0.045 -0.048 -0.001 -0.073  0.010 
    45     46     47     48     49     50 
-0.018  0.020  0.058 -0.016 -0.043 -0.009

Modelado

Modelado univariado mediante ARIMA

Un modelo de promedio móvil integrado autorregresivo ($ARIMA$ = Autoregressive Integrated Moving Average) es una generalización de un modelo de promedio móvil autorregresivo ($ARMA$).
Ambos modelos se ajustan a datos de series de tiempo para comprender mejor los datos o para predecir puntos futuros en la serie (pronóstico).
Los modelos ARIMA se aplican en casos de evidencia de no-estacionariedad, donde un paso de diferenciación inicial (correspondiente a la parte "integrada" del modelo) puede aplicarse una o más veces para eliminar la no-estacionariedad.
- $AR(p)$: indica que la variable de interés en evolución experimenta una regresión en sus propios valores rezagados (es decir, anteriores). Siendo $p$ el orden (número de rezagos) del modelo autorregresivo.
- $MA(q)$: indica que el error de regresión es en realidad una combinación lineal de términos de error cuyos valores ocurrieron contemporáneamente y en varias ocasiones en el pasado. Siendo $q$ el orden de promedio móvil en el modelo.
- $I(d)$ ("integrado"): indica que los valores de los datos han sido reemplazados por la diferencia entre sus valores y los valores previos (y este proceso de diferenciación puede haberse realizado más de una vez). Siendo $d$ el grado de diferenciación (la cantidad de veces que se han restado valores pasados a los datos)

El propósito de cada una de estas características es hacer que el modelo se ajuste a los datos lo mejor posible, eliminando o al menos mitigando la no-estacionariedad.



In [8]:

    
# Funcion para generar los modelos ARIMA por tienda

ts_arima <- function(store){
    Date <- store$Date
    y.xts <- xts(store$Sales, order.by = Date)
    y.fit <- auto.arima(y.xts, lambda = BoxCox.lambda(y.xts))
    return(y.fit)
}



In [9]:

    
system.time(
    out.arima <- dlply(train.store.new, .(Store), ts_arima)
)









    





   user  system elapsed 
592.134  26.013 619.261



In [14]:

    
str(out.arima)









    



List of 1115
 $ 1   :List of 19
  ..$ coef     : Named num [1:4] -0.657 -0.142 -0.219 0.486
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ sigma2   : num 7.2e-08
  ..$ var.coef : num [1:4, 1:4] 0.00835 0.002027 -0.000895 -0.007578 0.002027 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 5322
  ..$ aic      : num -10633
  ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:781] from 1 to 781: 1.31e-03 -3.60e-04 -1.36e-05 1.74e-04 4.32e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.31007390199431,  1.30969538468098, 1.309755| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 780
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] -0.657 -0.142 -0.219
  .. ..$ theta: num [1:2] 0.486 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 7.01e-05 2.62e-06 -1.64e-05 1.31
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 -5.71e-18 2.61e-17 0.00 ...
  .. ..$ T    : num [1:4, 1:4] -0.657 -0.142 -0.219 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 0.486 0 0 0.486 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 4.86e-01 0.00 1.47e-18 4.86e-01 ...
  ..$ bic      : num -10610
  ..$ aicc     : num -10633
  ..$ x        : Time-Series [1:781] from 1 to 781: 5530 4327 4486 4997 7176 5580 5471 4892 4881 4952 ...
  ..$ lambda   : atomic [1:1] -0.762
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 2732 5457 4523 4477 5157 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 2   :List of 19
  ..$ coef     : Named num [1:10] -0.574 -0.14 -0.934 -0.42 0.817 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.0061
  ..$ var.coef : num [1:10, 1:10] 0.02634 0.00319 0.00254 0.02367 -0.02549 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 891
  ..$ aic      : num -1759
  ..$ arma     : int [1:7] 4 5 0 0 1 0 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: -0.01165 -0.02426 -0.00351 -0.17983 0.12001 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.69853618066949,  4.68173538869948, 4.702328| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 784
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] -0.574 -0.14 -0.934 -0.42
  .. ..$ theta: num [1:5] 0.817 0.4015 0.9429 0.5065 -0.0242
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. ..$ a    : num [1:6] 0.07039 -0.01197 -0.00227 0.05821 0.0262 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] -0.574 -0.14 -0.934 -0.42 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 0.817 0.402 0.943 0.507 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 0.817 0.402 0.943 0.507 ...
  ..$ bic      : num -1708
  ..$ aicc     : num -1759
  ..$ x        : Time-Series [1:784] from 1 to 784: 4422 4159 4484 2342 6775 6318 6763 5618 4810 2630 ...
  ..$ lambda   : atomic [1:1] -0.155
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 4616 4545 4542 4385 4303 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 3   :List of 19
  ..$ coef     : Named num [1:10] -0.628 0.113 0.504 0.17 -0.51 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.000113
  ..$ var.coef : num [1:10, 1:10] 0.003502 0.004292 0.002342 -0.000502 -0.001395 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 2438
  ..$ aic      : num -4855
  ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00167 -0.00374 -0.00176 -0.01228 0.02374 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.61977813667363,  2.61393053048493, 2.615080| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.628 0.113 0.504 0.17 -0.51
  .. ..$ theta: num [1:4] 0.981 0.351 -0.344 -0.475
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 0.009503 0.00035 0.000667 -0.003296 -0.007137
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -0.628 0.113 0.504 0.17 -0.51 ...
  .. ..$ V    : num [1:5, 1:5] 1 0.981 0.351 -0.344 -0.475 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 0.981 0.351 -0.344 -0.475 ...
  ..$ bic      : num -4803
  ..$ aicc     : num -4854
  ..$ x        : Time-Series [1:779] from 1 to 779: 6823 5902 6069 4523 12247 9800 8001 7772 9292 4455 ...
  ..$ lambda   : atomic [1:1] -0.367
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6540 6470 6338 6003 6318 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 4   :List of 19
  ..$ coef     : Named num [1:2] -0.126 -0.196
  .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  ..$ sigma2   : num 1.54e-09
  ..$ var.coef : num [1:2, 1:2] 0.00292 0.00241 0.00241 0.0039
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 7528
  ..$ aic      : num -15049
  ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -2.00e-05 -1.12e-06 1.99e-05 1.64e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999975086284638,  0.999954409310638, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num [1:2] -0.126 -0.196
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 2.48e-05 -2.89e-06 -5.06e-06 1.00
  .. ..$ P    : num [1:4, 1:4] 0.0 0.0 0.0 3.1e-21 0.0 ...
  .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.126 -0.196 0 -0.126 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.26e-01 -1.96e-01 -2.34e-22 -1.26e-01 ...
  ..$ bic      : num -15036
  ..$ aicc     : num -15049
  ..$ x        : Time-Series [1:784] from 1 to 784: 9941 8247 8290 10338 12112 10031 8857 9472 10512 9719 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 909 9879 8368 8573 10106 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 5   :List of 19
  ..$ coef     : Named num [1:11] -1.092 -1.166 -1.096 -0.969 -0.88 ...
  .. ..- attr(*, "names")= chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.0876
  ..$ var.coef : num [1:11, 1:11] 6.55e-04 6.17e-04 5.40e-04 2.07e-04 3.67e-05 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:11] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -153
  ..$ aic      : num 331
  ..$ arma     : int [1:7] 5 5 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.00851 -0.1516 0.01486 -0.70328 0.25794 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(7.75108283524211,  7.57475007087681, 7.791114| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.092 -1.166 -1.096 -0.969 -0.88
  .. ..$ theta: num [1:5] 1.106 1.364 1.217 0.914 0.667
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. ..$ a    : num [1:6] 0.0972 -0.3229 -0.1058 -0.0523 0.0296 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] -1.092 -1.166 -1.096 -0.969 -0.88 ...
  .. ..$ V    : num [1:6, 1:6] 1 1.106 1.364 1.217 0.914 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 1.106 1.364 1.217 0.914 ...
  ..$ bic      : num 387
  ..$ aicc     : num 331
  ..$ x        : Time-Series [1:779] from 1 to 779: 4253 3465 4456 1590 6978 5718 5974 4999 5159 1760 ...
  ..$ lambda   : atomic [1:1] -0.0182
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4295 4132 4380 3575 5158 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 6   :List of 19
  ..$ coef     : Named num [1:9] -1.2963 -0.8581 -0.0716 0.2229 -0.1645 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.0693
  ..$ var.coef : num [1:9, 1:9] 0.0078 0.00853 0.00366 -0.0042 -0.00417 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -63.2
  ..$ aic      : num 146
  ..$ arma     : int [1:7] 5 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00922 -0.08688 0.04731 -0.35671 0.44581 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(9.21983942367567,  9.08524518233759, 9.220390| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.2963 -0.8581 -0.0716 0.2229 -0.1645
  .. ..$ theta: num [1:4] 0.5598 -0.0702 -0.7563 -0.5835
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.184 -0.219 -0.03 -0.115 -0.066 ...
  .. ..$ P    : num [1:6, 1:6] 0.00 0.00 1.39e-17 0.00 0.00 ...
  .. ..$ T    : num [1:6, 1:6] -1.2963 -0.8581 -0.0716 0.2229 -0.1645 ...
  .. ..$ V    : num [1:6, 1:6] 1 0.5598 -0.0702 -0.7563 -0.5835 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 0.5598 -0.0702 -0.7563 -0.5835 ...
  ..$ bic      : num 193
  ..$ aicc     : num 147
  ..$ x        : Time-Series [1:780] from 1 to 780: 6089 5398 6092 3872 8591 7099 6749 6282 6829 3829 ...
  ..$ lambda   : atomic [1:1] 0.0128
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 6039 5835 5840 5333 5771 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 7   :List of 19
  ..$ coef     : Named num [1:6] -0.0706 -0.3689 -0.7873 0.4757 -0.3799 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 0.0622
  ..$ var.coef : num [1:6, 1:6] 0.02138 -0.00344 -0.01952 0.02141 -0.00668 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num -22
  ..$ aic      : num 58
  ..$ arma     : int [1:7] 2 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:786] from 1 to 786: 0.008931 -0.093886 0.000225 -0.343216 0.563337 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(8.93056724262743,  8.80195315333357, 8.870966| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 785
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.0706 -0.3689
  .. ..$ theta: num [1:4] -0.787 0.476 -0.38 -0.244
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.277 -0.454 0.165 -0.153 -0.101 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] -0.0706 -0.3689 0 0 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.787 0.476 -0.38 -0.244 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -0.787 0.476 -0.38 -0.244 ...
  ..$ bic      : num 90.7
  ..$ aicc     : num 58.2
  ..$ x        : Time-Series [1:786] from 1 to 786: 8244 7231 7758 5218 12718 10073 7049 8234 7115 4236 ...
  ..$ lambda   : atomic [1:1] -0.00215
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:786] from 1 to 786: 8169 7957 7756 7403 7160 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 8   :List of 19
  ..$ coef     : Named num [1:3] -0.343 -0.469 -0.506
  .. ..- attr(*, "names")= chr [1:3] "ar1" "ma1" "ma2"
  ..$ sigma2   : num 12.6
  ..$ var.coef : num [1:3, 1:3] 0.00894 -0.0073 0.00712 -0.0073 0.00683 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  ..$ mask     : logi [1:3] TRUE TRUE TRUE
  ..$ loglik   : num -2102
  ..$ aic      : num 4213
  ..$ arma     : int [1:7] 1 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.0346 -0.8833 -1.7953 -5.5158 6.5815 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(34.605247508431,  33.4475430468026, 31.703713| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num -0.343
  .. ..$ theta: num [1:2] -0.469 -0.506
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 0.1 -3.1 -1.65 39.5
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 5.17e-23 0.00 ...
  .. ..$ T    : num [1:4, 1:4] -0.343 0 0 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.469 -0.506 0 -0.469 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -4.69e-01 -5.06e-01 1.32e-23 -4.69e-01 ...
  ..$ bic      : num 4232
  ..$ aicc     : num 4213
  ..$ x        : Time-Series [1:784] from 1 to 784: 5419 4842 4059 2337 7416 6333 5038 6084 4997 2660 ...
  ..$ lambda   : atomic [1:1] 0.273
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5401 5278 4867 4304 3951 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 9   :List of 19
  ..$ coef     : Named num [1:4] -0.4255 0.5073 -0.0811 -0.8846
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "ma2"
  ..$ sigma2   : num 4.48e-09
  ..$ var.coef : num [1:4, 1:4] 0.002381 0.000641 -0.001718 0.001603 0.000641 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 6536
  ..$ aic      : num -13063
  ..$ arma     : int [1:7] 2 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.09e-03 -2.19e-05 8.29e-06 -4.40e-05 1.69e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.08515719213164,  1.0851311890386, 1.0851484| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.425 0.507
  .. ..$ theta: num [1:2] -0.0811 -0.8846
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 3.23e-05 -1.61e-05 -2.57e-05 1.09
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -1.28e-16 0.00 ...
  .. ..$ T    : num [1:4, 1:4] -0.425 0.507 0 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.0811 -0.8846 0 -0.0811 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.11e-02 -8.85e-01 -6.09e-17 -8.11e-02 ...
  ..$ bic      : num -13040
  ..$ aicc     : num -13063
  ..$ x        : Time-Series [1:779] from 1 to 779: 4903 4602 4798 4254 7574 6206 4699 5340 5855 4657 ...
  ..$ lambda   : atomic [1:1] -0.921
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 1255 4853 4702 4708 4599 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 10  :List of 20
  ..$ coef     : Named num [1:2] -6.4e-01 5.9e-08
  .. ..- attr(*, "names")= chr [1:2] "ma1" "drift"
  ..$ sigma2   : num 2.29e-09
  ..$ var.coef : num [1:2, 1:2] 4.84e-03 1.34e-06 1.34e-06 1.65e-09
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "drift"
  .. .. ..$ : chr [1:2] "ma1" "drift"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 6999
  ..$ aic      : num -13991
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -4.64e-06 1.49e-05 -2.98e-05 8.74e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99986779450382,  0.999861700653274, 0.99988| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.64
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 2.24e-05 -1.80e-05 1.00
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 2.49e-23 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.64 0 -0.64 0.409 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -6.40e-01 9.73e-24 -6.40e-01 4.09e-01 ...
  ..$ xreg     : int [1:784, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num -13977
  ..$ aicc     : num -13991
  ..$ x        : Time-Series [1:784] from 1 to 784: 4812 4675 5114 4256 7804 5394 5696 5419 5556 4402 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 828 4779 4751 4874 4641 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 11  :List of 19
  ..$ coef     : Named num [1:5] -0.322 0.64 0.757 -0.122 1.409
  .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 1.21e-07
  ..$ var.coef : num [1:5, 1:5] 2.37e-03 2.16e-03 -2.52e-03 -2.26e-03 7.68e-09 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 5134
  ..$ aic      : num -10255
  ..$ arma     : int [1:7] 2 2 0 0 1 0 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 2.19e-04 -1.62e-04 -1.65e-05 -5.00e-04 5.75e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.40880169584566,  1.40847994352751, 1.408572| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 784
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.322 0.64
  .. ..$ theta: num [1:2] 0.757 -0.122
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:3] 1 0 0
  .. ..$ a    : num [1:3] 5.04e-04 1.85e-04 -3.79e-05
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 0.00 0.00 7.77e-16 ...
  .. ..$ T    : num [1:3, 1:3] -0.322 0.64 0 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 0.757 -0.122 0.757 0.573 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1 0.757 -0.122 0.757 0.573 ...
  ..$ bic      : num -10227
  ..$ aicc     : num -10255
  ..$ x        : Time-Series [1:784] from 1 to 784: 8913 7375 7768 5734 9939 9422 8458 8525 8745 5752 ...
  ..$ lambda   : atomic [1:1] -0.709
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 7815 8086 7842 7373 7037 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 12  :List of 19
  ..$ coef     : Named num [1:8] 0.71 0.689 -0.919 -1.257 -0.418 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 1.93e-09
  ..$ var.coef : num [1:8, 1:8] 5.90e-04 -2.84e-04 -9.11e-05 -5.96e-04 4.35e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7181
  ..$ aic      : num -14344
  ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -4.91e-06 -9.71e-06 4.68e-05 6.63e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999876767389667,  0.999870144433433, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.71 0.689 -0.919
  .. ..$ theta: num [1:5] -1.257 -0.418 1.216 -0.35 -0.159
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 1.35e-05 -3.52e-05 6.69e-06 1.06e-05 -1.51e-06 ...
  .. ..$ P    : num [1:7, 1:7] 0 0 0 0 0 ...
  .. ..$ T    : num [1:7, 1:7] 0.71 0.689 -0.919 0 0 ...
  .. ..$ V    : num [1:7, 1:7] 1 -1.257 -0.418 1.216 -0.35 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -1.257 -0.418 1.216 -0.35 ...
  ..$ bic      : num -14302
  ..$ aicc     : num -14344
  ..$ x        : Time-Series [1:784] from 1 to 784: 5029 4867 4642 6392 11010 9114 8311 7591 7999 6342 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 835 4986 4861 4921 6365 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 13  :List of 19
  ..$ coef     : Named num [1:6] 1.682 -0.948 -1.235 0.476 0.106 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 1.48e-08
  ..$ var.coef : num [1:6, 1:6] 3.26e-04 -2.72e-04 -3.87e-04 -3.91e-05 2.17e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 4720
  ..$ aic      : num -9425
  ..$ arma     : int [1:7] 2 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:621] from 1 to 621: -8.90e-05 -5.27e-05 -2.08e-05 1.14e-05 2.44e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.132335676811,  1.1323236269455, 1.132356002| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] 1.682 -0.948
  .. ..$ theta: num [1:3] -1.235 0.476 0.106
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:4] 1 0 0 0
  .. ..$ a    : num [1:4] 2.91e-04 -4.13e-04 9.37e-05 1.89e-05
  .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. ..$ T    : num [1:4, 1:4] 1.682 -0.948 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -1.235 0.476 0.106 -1.235 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1 -1.235 0.476 0.106 -1.235 ...
  ..$ bic      : num -9394
  ..$ aicc     : num -9425
  ..$ x        : Time-Series [1:621] from 1 to 621: 3737 3674 3848 4285 8246 6700 5296 5432 6075 4592 ...
  ..$ lambda   : atomic [1:1] -0.883
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:621] from 1 to 621: 4273 3965 3968 4208 4785 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 14  :List of 19
  ..$ coef     : Named num [1:2] -0.73 -0.338
  .. ..- attr(*, "names")= chr [1:2] "ar1" "ar2"
  ..$ sigma2   : num 0.000151
  ..$ var.coef : num [1:2, 1:2] 0.00114 0.00062 0.00062 0.00114
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "ar2"
  .. .. ..$ : chr [1:2] "ar1" "ar2"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 2320
  ..$ aic      : num -4634
  ..$ arma     : int [1:7] 2 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.002551 -0.007577 0.000136 -0.028782 0.028562 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.55133744009416,  2.54172845777618, 2.547115| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.73 -0.338
  .. ..$ theta: num 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 0.005383 -0.000618 2.554348
  .. ..$ P    : num [1:3, 1:3] 0.00 2.11e-17 -6.25e-17 2.11e-17 -1.95e-34 ...
  .. ..$ T    : num [1:3, 1:3] -0.73 -0.338 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 0 0 0 0 0 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 7.13e-18 -4.56e-17 7.13e-18 0.00 ...
  ..$ bic      : num -4620
  ..$ aicc     : num -4634
  ..$ x        : Time-Series [1:779] from 1 to 779: 5253 4169 4734 2519 7788 6920 5391 6046 6159 3020 ...
  ..$ lambda   : atomic [1:1] -0.376
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4931 4994 4718 4656 3775 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 15  :List of 19
  ..$ coef     : Named num [1:3] -0.977 0.623 -0.286
  .. ..- attr(*, "names")= chr [1:3] "ar1" "ma1" "ma2"
  ..$ sigma2   : num 2.3e-09
  ..$ var.coef : num [1:3, 1:3] 1.29e-04 -1.33e-04 5.75e-05 -1.33e-04 1.52e-03 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  ..$ mask     : logi [1:3] TRUE TRUE TRUE
  ..$ loglik   : num 6995
  ..$ aic      : num -13982
  ..$ arma     : int [1:7] 1 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 1.70e-05 7.99e-06 1.33e-05 7.58e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999862884456626,  0.999881064326566, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num -0.977
  .. ..$ theta: num [1:2] 0.623 -0.286
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 3.67e-06 -4.88e-06 -1.27e-06 1.00
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 3.18e-21 0.00 ...
  .. ..$ T    : num [1:4, 1:4] -0.977 0 0 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 0.623 -0.286 0 0.623 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 6.23e-01 -2.86e-01 2.38e-21 6.23e-01 ...
  ..$ bic      : num -13963
  ..$ aicc     : num -13982
  ..$ x        : Time-Series [1:784] from 1 to 784: 4701 5140 5174 5538 9049 7439 6777 6818 7621 5429 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 825 4728 4969 5158 5369 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 16  :List of 19
  ..$ coef     : Named num [1:3] 0.116 0.137 -0.986
  .. ..- attr(*, "names")= chr [1:3] "ar1" "ar2" "ma1"
  ..$ sigma2   : num 1.74e-06
  ..$ var.coef : num [1:3, 1:3] 1.32e-03 -1.16e-04 -4.81e-05 -1.16e-04 1.31e-03 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:3] "ar1" "ar2" "ma1"
  .. .. ..$ : chr [1:3] "ar1" "ar2" "ma1"
  ..$ mask     : logi [1:3] TRUE TRUE TRUE
  ..$ loglik   : num 4045
  ..$ aic      : num -8083
  ..$ arma     : int [1:7] 2 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.001698 -0.00091 -0.000314 -0.001979 0.003066 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.69809373366723,  1.69688016681599, 1.697139| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] 0.116 0.137
  .. ..$ theta: num -0.986
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 2.19e-06 -9.50e-04 1.70
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -8.25e-22 0.00 9.92e-12 ...
  .. ..$ T    : num [1:3, 1:3] 0.116 0.137 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -0.986 0 -0.986 0.972 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.86e-01 -1.88e-21 -9.86e-01 9.72e-01 ...
  ..$ bic      : num -8064
  ..$ aicc     : num -8083
  ..$ x        : Time-Series [1:777] from 1 to 777: 6919 5650 5888 4346 10013 8370 7898 7017 7498 4559 ...
  ..$ lambda   : atomic [1:1] -0.586
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 5244 6562 6199 5812 5670 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 17  :List of 19
  ..$ coef     : Named num [1:9] -1.195 -0.826 -0.224 -0.021 -0.334 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.01
  ..$ var.coef : num [1:9, 1:9] 0.00417 0.00468 0.00209 -0.00183 -0.00201 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -1109
  ..$ aic      : num 2237
  ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:782] from 1 to 782: -0.1213 -0.3271 0.0186 -1.8547 1.7794 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(15.2056929036692,  14.9463586261433, 15.33500| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 782
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.195 -0.826 -0.224 -0.021 -0.334
  .. ..$ theta: num [1:4] 1.47 1.304 0.577 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 1.047 0.349 0.459 0.257 -0.241
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -1.195 -0.826 -0.224 -0.021 -0.334 ...
  .. ..$ V    : num [1:5, 1:5] 1 1.47 1.304 0.577 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 1.47 1.304 0.577 0 ...
  ..$ bic      : num 2284
  ..$ aicc     : num 2238
  ..$ x        : Time-Series [1:782] from 1 to 782: 5593 5102 5853 2576 11279 9034 7450 7259 7711 3031 ...
  ..$ lambda   : atomic [1:1] 0.121
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 5837 5728 5815 5127 6208 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 18  :List of 19
  ..$ coef     : Named num [1:4] -0.718 0.254 -0.105 -0.865
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "ma2"
  ..$ sigma2   : num 5.27e-06
  ..$ var.coef : num [1:4, 1:4] 0.001633 0.001417 -0.000497 0.000392 0.001417 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 3638
  ..$ aic      : num -7267
  ..$ arma     : int [1:7] 2 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:782] from 1 to 782: 1.87e-03 -8.37e-05 1.59e-03 -3.77e-03 4.17e-03 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.86527612263994,  1.86514947263116, 1.867119| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 781
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.718 0.254
  .. ..$ theta: num [1:2] -0.105 -0.865
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 0.00257 -0.00177 -0.00187 1.86879
  .. ..$ P    : num [1:4, 1:4] 0.00 -1.39e-17 0.00 -1.11e-16 -1.39e-17 ...
  .. ..$ T    : num [1:4, 1:4] -0.718 0.254 0 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.105 -0.865 0 -0.105 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.05e-01 -8.65e-01 -8.48e-17 -1.05e-01 ...
  ..$ bic      : num -7243
  ..$ aicc     : num -7266
  ..$ x        : Time-Series [1:782] from 1 to 782: 5143 5083 6155 3688 7843 6653 6553 6903 6797 3768 ...
  ..$ lambda   : atomic [1:1] -0.53
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 4357 5123 5268 5076 5095 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 19  :List of 19
  ..$ coef     : Named num [1:6] -0.586 -0.59 0.33 -0.237 0.106 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 1.19e-06
  ..$ var.coef : num [1:6, 1:6] 0.00292 0.00254 0.00151 -0.00222 0.0012 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 4204
  ..$ aic      : num -8395
  ..$ arma     : int [1:7] 3 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.001583 -0.001183 0.000332 -0.001291 0.002756 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.5827700877602,  1.58105283402581, 1.5823028| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] -0.586 -0.59 0.33
  .. ..$ theta: num [1:3] -0.237 0.106 -0.842
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] -6.83e-05 -1.26e-03 2.67e-04 -6.99e-04 1.58
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -2.41e-25 ...
  .. ..$ T    : num [1:5, 1:5] -0.586 -0.59 0.33 0 1 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.237 0.106 -0.842 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -2.37e-01 1.06e-01 -8.42e-01 6.11e-22 ...
  ..$ bic      : num -8362
  ..$ aicc     : num -8394
  ..$ x        : Time-Series [1:779] from 1 to 779: 5763 4038 5189 3769 8978 7369 6149 6753 6725 3950 ...
  ..$ lambda   : atomic [1:1] -0.629
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4141 5114 4835 4829 4557 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 20  :List of 19
  ..$ coef     : Named num [1:8] -1.904 -1.79 -0.865 1.146 0.188 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 839659
  ..$ var.coef : num [1:8, 1:8] 0.001769 0.002625 0.001312 -0.001436 -0.000217 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -5090
  ..$ aic      : num 10198
  ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:619] from 1 to 619: 4.69 101.95 -768.76 -1596.71 2079.53 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4691.01127378294,  4844.60915510654, 3740.950| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 618
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] -1.904 -1.79 -0.865
  .. ..$ theta: num [1:5] 1.146 0.188 -0.709 -1.079 -0.411
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] -1702 -4402 -4014 -2226 -780 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 0.00 -1.11e-16 -3.33e-16 -2.22e-16 ...
  .. ..$ T    : num [1:7, 1:7] -1.904 -1.79 -0.865 0 0 ...
  .. ..$ V    : num [1:7, 1:7] 1 1.146 0.188 -0.709 -1.079 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 1.146 0.188 -0.709 -1.079 ...
  ..$ bic      : num 10238
  ..$ aicc     : num 10198
  ..$ x        : Time-Series [1:619] from 1 to 619: 7110 7356 5599 3642 9662 9065 7764 8175 6745 4527 ...
  ..$ lambda   : atomic [1:1] 0.947
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:619] from 1 to 619: 7102 7193 6820 6145 6315 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 21  :List of 19
  ..$ coef     : Named num [1:5] 1.356 -0.438 -0.189 -1.707 0.721
  .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 3.11e-09
  ..$ var.coef : num [1:5, 1:5] 0.0024 -0.00303 0.00143 -0.00127 0.0013 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 6709
  ..$ aic      : num -13406
  ..$ arma     : int [1:7] 3 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 1.69e-05 2.35e-05 2.05e-05 8.06e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99980382877924,  0.999824008187924, 0.99985| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 1.356 -0.438 -0.189
  .. ..$ theta: num [1:2] -1.707 0.721
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 3.81e-05 -1.02e-04 5.23e-05 1.00
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -2.51e-24 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 1.356 -0.438 -0.189 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -1.707 0.721 0 -1.707 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.71 7.21e-01 -6.04e-25 -1.71 ...
  ..$ bic      : num -13378
  ..$ aicc     : num -13406
  ..$ x        : Time-Series [1:777] from 1 to 777: 3680 3975 4471 5034 9580 7288 6618 5569 5869 5329 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 787 3725 4046 4563 5407 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 22  :List of 19
  ..$ coef     : Named num [1:2] -0.864 -0.123
  .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  ..$ sigma2   : num 7.25e-09
  ..$ var.coef : num [1:2, 1:2] 0.00119 -0.00114 -0.00114 0.00117
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 4998
  ..$ aic      : num -9991
  ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:619] from 1 to 619: 1.04e-03 2.85e-05 2.49e-05 -1.36e-04 1.84e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.03597223920683,  1.03600928797097, 1.036022| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 618
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num [1:2] -0.864 -0.123
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 3.20e-05 -8.36e-05 -1.08e-05 1.04
  .. ..$ P    : num [1:4, 1:4] 0.0 0.0 0.0 -5.1e-22 0.0 ...
  .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.864 -0.123 0 -0.864 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.64e-01 -1.23e-01 -4.80e-21 -8.64e-01 ...
  ..$ bic      : num -9978
  ..$ aicc     : num -9991
  ..$ x        : Time-Series [1:619] from 1 to 619: 3514 3894 4053 2645 6507 5779 5254 4742 4750 2665 ...
  ..$ lambda   : atomic [1:1] -0.965
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:619] from 1 to 619: 922 3595 3768 3631 3441 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 23  :List of 19
  ..$ coef     : Named num [1:6] 1.6168 -0.8955 -1.3398 0.8052 -0.0758 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 2.03e-09
  ..$ var.coef : num [1:6, 1:6] 7.43e-04 -4.82e-04 -7.47e-04 6.46e-05 -2.03e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 6694
  ..$ aic      : num -13373
  ..$ arma     : int [1:7] 2 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -2.29e-05 -4.63e-06 -9.86e-07 -4.12e-05 1.08e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.01701226326749,  1.01702192395747, 1.017027| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] 1.617 -0.896
  .. ..$ theta: num [1:3] -1.3398 0.8052 -0.0758
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:4] 1 0 0 0
  .. ..$ a    : num [1:4] 6.67e-05 -9.59e-05 3.78e-05 -3.45e-06
  .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. ..$ T    : num [1:4, 1:4] 1.617 -0.896 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -1.3398 0.8052 -0.0758 -1.3398 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1 -1.3398 0.8052 -0.0758 -1.3398 ...
  ..$ bic      : num -13340
  ..$ aicc     : num -13373
  ..$ x        : Time-Series [1:779] from 1 to 779: 4523 4701 4816 4174 9075 6998 5800 6023 6377 4314 ...
  ..$ lambda   : atomic [1:1] -0.983
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4968 4791 4836 4904 4924 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 24  :List of 19
  ..$ coef     : Named num [1:8] -0.04213 0.66475 0.00245 -0.17382 -0.37146 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.77e-09
  ..$ var.coef : num [1:8, 1:8] 0.004391 0.000518 -0.002629 0.000669 0.000458 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7254
  ..$ aic      : num -14490
  ..$ arma     : int [1:7] 5 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.72e-06 2.29e-05 -8.26e-06 4.81e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999930868955441,  0.999927565070031, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.04213 0.66475 0.00245 -0.17382 -0.37146
  .. ..$ theta: num [1:4] -0.629 -0.681 0.366 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 1.70e-05 -3.73e-05 -3.64e-07 4.68e-06 -3.38e-06 ...
  .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 0.00 -4.37e-18 ...
  .. ..$ T    : num [1:6, 1:6] -0.04213 0.66475 0.00245 -0.17382 -0.37146 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.629 -0.681 0.366 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -0.629 -0.681 0.366 0 ...
  ..$ bic      : num -14448
  ..$ aicc     : num -14490
  ..$ x        : Time-Series [1:779] from 1 to 779: 6907 6753 8419 6975 13453 10349 9474 9823 10333 7297 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 874 6832 7057 7401 8169 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 25  :List of 19
  ..$ coef     : Named num [1:7] -0.355 0.406 0.249 -0.106 -0.343 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 32.4
  ..$ var.coef : num [1:7, 1:7] 0.00522 -0.000978 -0.000911 -0.000316 0.000048 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -2366
  ..$ aic      : num 4748
  ..$ arma     : int [1:7] 5 1 0 0 1 0 0
  ..$ residuals: Time-Series [1:750] from 1 to 750: 2 -2.13 -2.75 -3.71 10.58 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(74.9757777635979,  71.2892705408686, 69.54317| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 750
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.355 0.406 0.249 -0.106 -0.343
  .. ..$ theta: num [1:4] 0.707 0 0 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 7.205 3.818 0.374 0.276 -0.265
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -0.355 0.406 0.249 -0.106 -0.343 ...
  .. ..$ V    : num [1:5, 1:5] 1 0.707 0 0 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 0.707 0 0 0 ...
  ..$ bic      : num 4785
  ..$ aicc     : num 4748
  ..$ x        : Time-Series [1:750] from 1 to 750: 11944 10409 9729 8987 14513 14243 11539 11835 11194 9227 ...
  ..$ lambda   : atomic [1:1] 0.353
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:750] from 1 to 750: 11095 11278 10812 10394 9880 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 26  :List of 19
  ..$ coef     : Named num [1:7] 0.664 0.705 -0.889 -1.337 -0.229 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 4.27e-06
  ..$ var.coef : num [1:7, 1:7] 0.000784 -0.000129 -0.000308 -0.000861 0.000575 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 3721
  ..$ aic      : num -7426
  ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:782] from 1 to 782: 0.001853 -0.000384 0.000126 -0.00099 0.004526 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.8529654279375,  1.85246849479052, 1.8528002| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 781
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.664 0.705 -0.889
  .. ..$ theta: num [1:4] -1.337 -0.229 1.204 -0.629
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] -0.000078 -0.00171 0.000909 0.000547 -0.00046 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] 0.664 0.705 -0.889 0 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 -1.337 -0.229 1.204 -0.629 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -1.337 -0.229 1.204 -0.629 ...
  ..$ bic      : num -7389
  ..$ aicc     : num -7426
  ..$ x        : Time-Series [1:782] from 1 to 782: 5950 5654 5849 5129 10108 7450 7124 6818 7223 5310 ...
  ..$ lambda   : atomic [1:1] -0.534
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 4952 5881 5774 5656 5893 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 27  :List of 19
  ..$ coef     : Named num -0.349
  .. ..- attr(*, "names")= chr "ma1"
  ..$ sigma2   : num 2.14e-09
  ..$ var.coef : num [1, 1] 0.00137
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr "ma1"
  .. .. ..$ : chr "ma1"
  ..$ mask     : logi TRUE
  ..$ loglik   : num 7021
  ..$ aic      : num -14038
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.04e-05 3.63e-06 -4.62e-06 5.98e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999960382550472,  0.999948967278473, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.349
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 2.17e-05 -7.65e-06 1.00
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -3.84e-21 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.349 0 -0.349 0.122 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.49e-01 -9.93e-22 -3.49e-01 1.22e-01 ...
  ..$ bic      : num -14029
  ..$ aicc     : num -14038
  ..$ x        : Time-Series [1:779] from 1 to 779: 8674 7893 8361 7969 15594 11608 9803 10434 11571 8046 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 897 8602 8115 8274 8073 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 28  :List of 19
  ..$ coef     : Named num [1:3] -0.9534 0.0405 -0.0724
  .. ..- attr(*, "names")= chr [1:3] "ma1" "ma2" "ma3"
  ..$ sigma2   : num 0.0488
  ..$ var.coef : num [1:3, 1:3] 0.00158 -0.002443 0.000898 -0.002443 0.00595 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:3] "ma1" "ma2" "ma3"
  .. .. ..$ : chr [1:3] "ma1" "ma2" "ma3"
  ..$ mask     : logi [1:3] TRUE TRUE TRUE
  ..$ loglik   : num 69.3
  ..$ aic      : num -131
  ..$ arma     : int [1:7] 0 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:768] from 1 to 768: 0.00634 0.0249 0.03142 -0.4557 0.43434 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(6.33984707647235,  6.37431248336113, 6.393573| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 767
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num [1:3] -0.9534 0.0405 -0.0724
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] 0.08511 -0.24766 -0.00195 -0.01877 6.45993
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 3.71e-22 ...
  .. ..$ T    : num [1:5, 1:5] 0 0 0 0 1 1 0 0 0 0 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.9534 0.0405 -0.0724 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -9.53e-01 4.05e-02 -7.24e-02 7.98e-22 ...
  ..$ bic      : num -112
  ..$ aicc     : num -131
  ..$ x        : Time-Series [1:768] from 1 to 768: 4958 5287 5481 2070 10126 7892 6632 6179 6630 2401 ...
  ..$ lambda   : atomic [1:1] -0.0729
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:768] from 1 to 768: 4900 5047 5168 4696 4435 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 29  :List of 19
  ..$ coef     : Named num [1:8] 0.736 0.681 -0.922 -1.258 -0.516 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 4.14e-08
  ..$ var.coef : num [1:8, 1:8] 0.000764 -0.000844 0.000288 -0.000803 0.001226 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 5532
  ..$ aic      : num -11047
  ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.29e-03 -1.62e-04 1.60e-04 6.31e-05 5.41e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.28758364070675,  1.28738322499306, 1.287617| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.736 0.681 -0.922
  .. ..$ theta: num [1:5] -1.258 -0.516 1.297 -0.269 -0.233
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 1.39e-04 -2.58e-04 -1.83e-05 1.62e-04 -2.29e-05 ...
  .. ..$ P    : num [1:7, 1:7] 0 0 0 0 0 ...
  .. ..$ T    : num [1:7, 1:7] 0.736 0.681 -0.922 0 0 ...
  .. ..$ V    : num [1:7, 1:7] 1 -1.258 -0.516 1.297 -0.269 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -1.258 -0.516 1.297 -0.269 ...
  ..$ bic      : num -11005
  ..$ aicc     : num -11046
  ..$ x        : Time-Series [1:779] from 1 to 779: 5269 4554 5411 5564 10796 7235 5721 6590 7061 5518 ...
  ..$ lambda   : atomic [1:1] -0.776
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 2525 5118 4798 5294 6063 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 30  :List of 20
  ..$ coef     : Named num [1:4] -0.487 -0.223 0.196 -0.005
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "drift"
  ..$ sigma2   : num 28.8
  ..$ var.coef : num [1:4, 1:4] 2.73e-02 6.21e-03 -2.71e-02 1.17e-05 6.21e-03 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "drift"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "drift"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num -2404
  ..$ aic      : num 4817
  ..$ arma     : int [1:7] 2 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.059 1.935 -4.065 1.443 11.616 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(59.009921726543,  61.0382149091668, 56.386506| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.487 -0.223
  .. ..$ theta: num 0.196
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] -0.449 -0.357 59.615
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -5.94e-22 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] -0.487 -0.223 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 0.196 0 0.196 0.0384 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 1.96e-01 -5.06e-23 1.96e-01 3.84e-02 ...
  ..$ xreg     : int [1:777, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num 4841
  ..$ aicc     : num 4817
  ..$ x        : Time-Series [1:777] from 1 to 777: 5683 6219 5035 5643 9174 8705 5718 7957 6182 5131 ...
  ..$ lambda   : atomic [1:1] 0.358
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 5668 5707 6061 5282 5671 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 31  :List of 19
  ..$ coef     : Named num [1:8] 0.654 0.66 -0.839 -0.117 -0.627 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 7.49e-10
  ..$ var.coef : num [1:8, 1:8] 0.00214 -0.00078 -0.000508 -0.002186 -0.000673 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7128
  ..$ aic      : num -14238
  ..$ arma     : int [1:7] 3 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: -1.22e-05 1.00e-05 1.49e-05 -1.12e-05 4.46e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999880380177298,  0.999897786722261, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 784
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.654 0.66 -0.839
  .. ..$ theta: num [1:4] -0.117 -0.627 0.476 0.243
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 4.07e-05 -2.24e-05 -2.84e-05 1.54e-05 4.78e-06
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] 0.654 0.66 -0.839 0 0 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.117 -0.627 0.476 0.243 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 -0.117 -0.627 0.476 0.243 ...
  ..$ bic      : num -14196
  ..$ aicc     : num -14237
  ..$ x        : Time-Series [1:784] from 1 to 784: 5122 5623 6140 5607 7857 6480 6335 6066 7314 5033 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5464 5323 5624 5982 5819 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 32  :List of 20
  ..$ coef     : Named num [1:3] -6.37e-01 -2.38e-01 5.47e-06
  .. ..- attr(*, "names")= chr [1:3] "ar1" "ar2" "drift"
  ..$ sigma2   : num 5.28e-06
  ..$ var.coef : num [1:3, 1:3] 1.52e-03 7.82e-04 -1.35e-09 7.82e-04 1.52e-03 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:3] "ar1" "ar2" "drift"
  .. .. ..$ : chr [1:3] "ar1" "ar2" "drift"
  ..$ mask     : logi [1:3] TRUE TRUE TRUE
  ..$ loglik   : num 2889
  ..$ aic      : num -5770
  ..$ arma     : int [1:7] 2 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:621] from 1 to 621: 0.001596 -0.001753 -0.000145 -0.004319 0.005923 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.59601038446368,  1.59391037698159, 1.594849| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 620
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.637 -0.238
  .. ..$ theta: num 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 0.00044 -0.000194 1.595006
  .. ..$ P    : num [1:3, 1:3] 0.00 -1.10e-17 4.62e-17 -1.10e-17 -7.00e-35 ...
  .. ..$ T    : num [1:3, 1:3] -0.637 -0.238 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 0 0 0 0 0 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -2.61e-18 2.94e-17 -2.61e-18 0.00 ...
  ..$ xreg     : int [1:621, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num -5752
  ..$ aicc     : num -5770
  ..$ x        : Time-Series [1:621] from 1 to 621: 3668 2676 3058 1768 6573 5410 5277 4292 4414 1913 ...
  ..$ lambda   : atomic [1:1] -0.623
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:621] from 1 to 621: 2871 3466 3125 3018 2385 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 33  :List of 19
  ..$ coef     : Named num [1:10] 0.664 0.559 -0.113 -1.027 0.429 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 172
  ..$ var.coef : num [1:10, 1:10] 0.001491 0.000443 -0.000386 -0.002548 0.002628 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -3105
  ..$ aic      : num 6233
  ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 4.28 -6.383 3.484 -0.538 28.23 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(171.235467126574,  162.232264171273, 166.9284| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] 0.664 0.559 -0.113 -1.027 0.429
  .. ..$ theta: num [1:4] -0.132 -0.627 -0.236 0.881
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 22.48 -5.31 -17.52 -7.64 18.68
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] 0.664 0.559 -0.113 -1.027 0.429 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.132 -0.627 -0.236 0.881 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 -0.132 -0.627 -0.236 0.881 ...
  ..$ bic      : num 6284
  ..$ aicc     : num 6233
  ..$ x        : Time-Series [1:779] from 1 to 779: 8910 7987 8462 8293 11480 10678 7791 9322 8295 9339 ...
  ..$ lambda   : atomic [1:1] 0.488
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 8465 8636 8108 8348 8348 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 34  :List of 20
  ..$ coef     : Named num [1:2] -3.29e-01 4.43e-08
  .. ..- attr(*, "names")= chr [1:2] "ma1" "drift"
  ..$ sigma2   : num 1.74e-09
  ..$ var.coef : num [1:2, 1:2] 1.50e-03 8.17e-08 8.17e-08 1.28e-09
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "drift"
  .. .. ..$ : chr [1:2] "ma1" "drift"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 7311
  ..$ aic      : num -14617
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -1.57e-05 -4.61e-06 1.39e-05 4.93e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999946893992605,  0.999930088682986, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.329
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 2.87e-05 -8.94e-06 1.00
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 3.53e-21 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.329 0 -0.329 0.108 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.29e-01 8.75e-22 -3.29e-01 1.08e-01 ...
  ..$ xreg     : int [1:784, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num -14603
  ..$ aicc     : num -14617
  ..$ x        : Time-Series [1:784] from 1 to 784: 7766 6870 6885 7707 11768 8576 8224 7667 8123 7045 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 886 7699 7110 6960 7447 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 35  :List of 19
  ..$ coef     : Named num -0.37
  .. ..- attr(*, "names")= chr "ar1"
  ..$ sigma2   : num 2.03e-09
  ..$ var.coef : num [1, 1] 0.00111
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr "ar1"
  .. .. ..$ : chr "ar1"
  ..$ mask     : logi TRUE
  ..$ loglik   : num 7074
  ..$ aic      : num -14143
  ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.31e-05 1.70e-05 1.30e-05 7.39e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999922246098883,  0.99990770812858, 0.99993| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num -0.37
  .. ..$ theta: num(0) 
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:2] 1 1
  .. ..$ a    : num [1:2] 9.63e-06 1.00
  .. ..$ P    : num [1:2, 1:2] 0.00 -6.23e-21 -6.23e-21 6.23e-21
  .. ..$ T    : num [1:2, 1:2] -0.37 1 0 1
  .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:2, 1:2] 1.00 -2.30e-21 -2.30e-21 6.23e-21
  ..$ bic      : num -14134
  ..$ aicc     : num -14143
  ..$ x        : Time-Series [1:779] from 1 to 779: 6519 5955 6868 7097 14536 11508 10066 9909 9946 7284 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 867 6459 6152 6499 7011 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 36  :List of 19
  ..$ coef     : Named num [1:7] 0.413 0.735 -0.579 -0.819 -0.778 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 3.2e-05
  ..$ var.coef : num [1:7, 1:7] 0.006877 0.000568 -0.003342 -0.007109 0.00381 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 2335
  ..$ aic      : num -4653
  ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00291 -0.0105 -0.00226 0.00216 0.01133 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.90699738038605,  2.89487345709204, 2.894533| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.413 0.735 -0.579
  .. ..$ theta: num [1:4] -0.8185 -0.7782 0.6997 -0.0773
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.001774 -0.007329 -0.001108 0.003741 -0.000463 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] 0.413 0.735 -0.579 0 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.8185 -0.7782 0.6997 -0.0773 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -0.8185 -0.7782 0.6997 -0.0773 ...
  ..$ bic      : num -4618
  ..$ aicc     : num -4653
  ..$ x        : Time-Series [1:622] from 1 to 622: 9333 7407 7361 7806 10329 8902 9645 8494 8956 8545 ...
  ..$ lambda   : atomic [1:1] -0.327
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 8816 9039 7675 7499 8260 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 37  :List of 19
  ..$ coef     : Named num [1:10] 1.0434 0.0155 -0.1624 -0.5294 0.2092 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.268
  ..$ var.coef : num [1:10, 1:10] 0.00781 -0.01119 0.00195 0.00533 -0.00197 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -590
  ..$ aic      : num 1201
  ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.1294 -0.0335 0.0924 0.5916 -0.1065 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(15.0165212979815,  14.9118294896086, 14.96645| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 780
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] 1.0434 0.0155 -0.1624 -0.5294 0.2092
  .. ..$ theta: num [1:4] -0.428 -0.341 -0.14 0.686
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 0.7336 -0.5555 -0.3923 -0.0795 0.3652
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] 1.0434 0.0155 -0.1624 -0.5294 0.2092 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.428 -0.341 -0.14 0.686 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 -0.428 -0.341 -0.14 0.686 ...
  ..$ bic      : num 1252
  ..$ aicc     : num 1201
  ..$ x        : Time-Series [1:780] from 1 to 780: 7369 7081 7230 8922 7795 7143 6760 7900 7967 8828 ...
  ..$ lambda   : atomic [1:1] 0.109
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 7015 7172 6980 7140 8114 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 38  :List of 19
  ..$ coef     : Named num [1:6] 2.161 -1.738 0.437 -1.585 0.821 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 0.000105
  ..$ var.coef : num [1:6, 1:6] 0.00317 -0.00518 0.00276 -0.00192 0.00141 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 2465
  ..$ aic      : num -4917
  ..$ arma     : int [1:7] 3 2 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.00816 -0.00979 -0.0034 0.00473 0.02306 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.72457039291493,  2.71795170391307, 2.720684| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 2.161 -1.738 0.437
  .. ..$ theta: num [1:2] -1.585 0.821
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:3] 1 0 0
  .. ..$ a    : num [1:3] 0.013 -0.0241 0.011
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 0.00 0.00 4.44e-16 ...
  .. ..$ T    : num [1:3, 1:3] 2.161 -1.738 0.437 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -1.585 0.821 -1.585 2.513 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1 -1.585 0.821 -1.585 2.513 ...
  ..$ bic      : num -4884
  ..$ aicc     : num -4917
  ..$ x        : Time-Series [1:779] from 1 to 779: 4506 3995 4196 5233 9738 6773 6224 6155 5890 5347 ...
  ..$ lambda   : atomic [1:1] -0.347
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 5265 4782 4466 4777 5839 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 39  :List of 19
  ..$ coef     : Named num [1:2] 0.254 -0.989
  .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  ..$ sigma2   : num 1.26e-08
  ..$ var.coef : num [1:2, 1:2] 1.24e-03 -3.09e-05 -3.09e-05 2.76e-05
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 6017
  ..$ aic      : num -12028
  ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.03e-03 -4.39e-05 -1.07e-05 -1.65e-04 2.72e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.03465933671525,  1.03460354872205, 1.034611| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num 0.254
  .. ..$ theta: num -0.989
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 7.34e-05 -1.16e-04 1.03
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 8.85e-17 0.00 5.02e-10 ...
  .. ..$ T    : num [1:3, 1:3] 0.254 0 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -0.989 0 -0.989 0.978 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.89e-01 3.27e-17 -9.89e-01 9.78e-01 ...
  ..$ bic      : num -12014
  ..$ aicc     : num -12028
  ..$ x        : Time-Series [1:779] from 1 to 779: 4144 3527 3604 2435 9136 5510 4154 5120 4766 2398 ...
  ..$ lambda   : atomic [1:1] -0.966
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 956 3996 3712 3517 3193 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 40  :List of 19
  ..$ coef     : Named num [1:5] -0.193 0.525 -0.115 -0.178 -0.77
  .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 5.58e+10
  ..$ var.coef : num [1:5, 1:5] 4.17e-03 -1.85e-05 -1.09e-03 -3.06e-03 2.17e-03 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num -10687
  ..$ aic      : num 21386
  ..$ arma     : int [1:7] 3 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:776] from 1 to 776: 724 -35936 -51034 265100 419849 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(724164.557066078,  683292.278005351, 636276.8| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 775
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] -0.193 0.525 -0.115
  .. ..$ theta: num [1:2] -0.178 -0.77
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 76412 -87973 -122599 862235
  .. ..$ P    : num [1:4, 1:4] 0.00 2.78e-17 0.00 5.57e-17 2.78e-17 ...
  .. ..$ T    : num [1:4, 1:4] -0.193 0.525 -0.115 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.178 -0.77 0 -0.178 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.78e-01 -7.70e-01 1.98e-17 -1.78e-01 ...
  ..$ bic      : num 21413
  ..$ aicc     : num 21386
  ..$ x        : Time-Series [1:776] from 1 to 776: 4672 4511 4321 5479 6735 5524 4498 5685 4882 4867 ...
  ..$ lambda   : atomic [1:1] 1.66
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:776] from 1 to 776: 4669 4653 4527 4489 5354 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 41  :List of 19
  ..$ coef     : Named num [1:2] 0.521 -0.976
  .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  ..$ sigma2   : num 2.25e-06
  ..$ var.coef : num [1:2, 1:2] 1.29e-03 -7.98e-05 -7.98e-05 5.66e-05
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 3158
  ..$ aic      : num -6310
  ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00176 -0.000488 0.000532 -0.001111 0.001414 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.7604658935845,  1.75991220806412, 1.7606294| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num 0.521
  .. ..$ theta: num -0.976
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 0.000669 -0.000969 1.763244
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 2.14e-21 0.00 3.33e-15 ...
  .. ..$ T    : num [1:3, 1:3] 0.521 0 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -0.976 0 -0.976 0.953 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.76e-01 5.11e-22 -9.76e-01 9.53e-01 ...
  ..$ bic      : num -6297
  ..$ aicc     : num -6310
  ..$ x        : Time-Series [1:622] from 1 to 622: 4461 4194 4545 3940 4839 4860 4128 4303 4044 4219 ...
  ..$ lambda   : atomic [1:1] -0.563
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 3692 4428 4281 4449 4122 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 42  :List of 19
  ..$ coef     : Named num [1:8] 0.707 0.702 -0.928 -1.32 -0.373 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 1.61e-09
  ..$ var.coef : num [1:8, 1:8] 0.000586 -0.000146 -0.000216 -0.000617 0.000348 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7410
  ..$ aic      : num -14802
  ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.35e-05 1.30e-05 -6.32e-07 4.76e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99995001860758,  0.99993124553275, 0.999954| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.707 0.702 -0.928
  .. ..$ theta: num [1:5] -1.32 -0.373 1.256 -0.353 -0.188
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 8.44e-06 -2.73e-05 1.76e-05 -2.56e-06 -1.93e-06 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 -2.22e-16 -1.67e-16 2.22e-16 -1.11e-16 ...
  .. ..$ T    : num [1:7, 1:7] 0.707 0.702 -0.928 0 0 ...
  .. ..$ V    : num [1:7, 1:7] 1 -1.32 -0.373 1.256 -0.353 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -1.32 -0.373 1.256 -0.353 ...
  ..$ bic      : num -14760
  ..$ aicc     : num -14802
  ..$ x        : Time-Series [1:779] from 1 to 779: 7959 6925 8273 7587 14737 12216 10569 10298 10841 7648 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 889 7638 7472 7624 8660 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 43  :List of 19
  ..$ coef     : Named num [1:5] 1.674 -0.941 -1.535 0.828 2.651
  .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 0.000124
  ..$ var.coef : num [1:5, 1:5] 8.67e-04 -6.07e-04 -1.19e-03 4.92e-04 -1.14e-07 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 2399
  ..$ aic      : num -4787
  ..$ arma     : int [1:7] 2 2 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.001308 -0.004115 0.000679 -0.008731 0.024988 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.64973842926548,  2.64649194153076, 2.650717| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] 1.674 -0.941
  .. ..$ theta: num [1:2] -1.535 0.828
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:3] 1 0 0
  .. ..$ a    : num [1:3] 0.00913 -0.01388 0.00509
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 0.00 0.00 2.66e-15 ...
  .. ..$ T    : num [1:3, 1:3] 1.674 -0.941 0 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -1.535 0.828 -1.535 2.356 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1 -1.535 0.828 -1.535 2.356 ...
  ..$ bic      : num -4759
  ..$ aicc     : num -4787
  ..$ x        : Time-Series [1:779] from 1 to 779: 6243 5790 6389 5167 12218 8600 7918 8132 8246 5308 ...
  ..$ lambda   : atomic [1:1] -0.361
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6439 6372 6287 6303 6296 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 44  :List of 19
  ..$ coef     : Named num [1:10] -0.525 0.256 0.581 0.127 -0.607 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 3.14e-09
  ..$ var.coef : num [1:10, 1:10] 0.001882 0.002089 0.000882 -0.000658 -0.000917 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 6764
  ..$ aic      : num -13505
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -2.66e-05 6.53e-06 -2.51e-05 1.06e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999861287801532,  0.999816037499558, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.525 0.256 0.581 0.127 -0.607
  .. ..$ theta: num [1:5] -0.1399 -0.6784 -0.6743 0.0232 0.5578
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 4.39e-05 -1.03e-04 3.66e-05 -1.65e-05 -2.51e-06 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 -6.94e-18 ...
  .. ..$ T    : num [1:7, 1:7] -0.525 0.256 0.581 0.127 -0.607 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.1399 -0.6784 -0.6743 0.0232 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.1399 -0.6784 -0.6743 0.0232 ...
  ..$ bic      : num -13454
  ..$ aicc     : num -13505
  ..$ x        : Time-Series [1:784] from 1 to 784: 4666 3853 4407 3652 9818 6149 6284 5397 6699 3195 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 824 4292 4284 4020 4808 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 45  :List of 19
  ..$ coef     : Named num [1:7] 2.125 -1.679 0.402 -1.522 0.716 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 4.09
  ..$ var.coef : num [1:7, 1:7] 0.00998 -0.01658 0.00905 -0.00973 0.01257 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -1651
  ..$ aic      : num 3318
  ..$ arma     : int [1:7] 3 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -1.605 -0.55 0.548 0.7 1.795 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(33.4709980204569,  33.7068725783257, 35.11697| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 2.125 -1.679 0.402
  .. ..$ theta: num [1:3] -1.522 0.716 0.09
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:4] 1 0 0 0
  .. ..$ a    : num [1:4] 2.096 -3.814 1.636 0.109
  .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:4, 1:4] 2.125 -1.679 0.402 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -1.522 0.716 0.09 -1.522 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1 -1.522 0.716 0.09 -1.522 ...
  ..$ bic      : num 3355
  ..$ aicc     : num 3318
  ..$ x        : Time-Series [1:779] from 1 to 779: 4270 4368 4988 5566 6616 5518 5235 5955 5868 5455 ...
  ..$ lambda   : atomic [1:1] 0.28
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4969 4603 4740 5225 5657 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 46  :List of 19
  ..$ coef     : Named num [1:7] 2.1663 -1.7123 0.3741 0.0384 -1.6138 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.34e-09
  ..$ var.coef : num [1:7, 1:7] 0.003253 -0.005572 0.00328 -0.000178 -0.001652 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 5473
  ..$ aic      : num -10930
  ..$ arma     : int [1:7] 4 2 0 0 1 0 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: -3.09e-05 -5.39e-06 -1.68e-05 1.39e-05 6.14e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999826578144851,  0.999836181905615, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 622
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] 2.1663 -1.7123 0.3741 0.0384
  .. ..$ theta: num [1:3] -1.614 0.847 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:4] 1 0 0 0
  .. ..$ a    : num [1:4] 7.11e-05 -1.39e-04 6.94e-05 2.32e-06
  .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. ..$ T    : num [1:4, 1:4] 2.1663 -1.7123 0.3741 0.0384 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -1.614 0.847 0 -1.614 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1 -1.614 0.847 0 -1.614 ...
  ..$ bic      : num -10895
  ..$ aicc     : num -10930
  ..$ x        : Time-Series [1:622] from 1 to 622: 4016 4177 4125 4848 7788 5793 5501 5503 5985 4857 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 4585 4273 4431 4542 5269 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 47  :List of 19
  ..$ coef     : Named num [1:4] -0.4613 0.5046 -0.0864 -0.8942
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "ma2"
  ..$ sigma2   : num 4.78e-09
  ..$ var.coef : num [1:4, 1:4] 0.001195 0.000963 -0.000321 0.000262 0.000963 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 6539
  ..$ aic      : num -13069
  ..$ arma     : int [1:7] 2 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.09e-03 -1.28e-05 -3.70e-05 -8.83e-06 1.31e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.08503141131099,  1.08501475430077, 1.084979| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] -0.461 0.505
  .. ..$ theta: num [1:2] -0.0864 -0.8942
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 5.13e-05 -2.90e-05 -3.50e-05 1.09
  .. ..$ P    : num [1:4, 1:4] 0.00 -1.39e-17 0.00 -1.29e-16 -1.39e-17 ...
  .. ..$ T    : num [1:4, 1:4] -0.461 0.505 0 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.0864 -0.8942 0 -0.0864 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.64e-02 -8.94e-01 -7.05e-17 -8.64e-02 ...
  ..$ bic      : num -13045
  ..$ aicc     : num -13069
  ..$ x        : Time-Series [1:784] from 1 to 784: 6538 6199 5580 5673 9881 8729 9057 7493 7409 5021 ...
  ..$ lambda   : atomic [1:1] -0.921
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 1351 6457 6230 5821 6022 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 48  :List of 19
  ..$ coef     : Named num [1:8] -1.4399 -0.9305 0.0325 0.471 0.7411 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.00202
  ..$ var.coef : num [1:8, 1:8] 0.0023 0.00384 0.00352 0.00143 -0.0016 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 1321
  ..$ aic      : num -2623
  ..$ arma     : int [1:7] 4 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.00439 -0.00403 0.00528 -0.0347 0.10403 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.38747211180177,  4.38154588494194, 4.391271| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] -1.4399 -0.9305 0.0325 0.471
  .. ..$ theta: num [1:4] 0.7411 -0.0842 -0.8202 -0.6943
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.03867 -0.01492 0.01338 -0.00474 -0.01135 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] -1.4399 -0.9305 0.0325 0.471 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 0.7411 -0.0842 -0.8202 -0.6943 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 0.7411 -0.0842 -0.8202 -0.6943 ...
  ..$ bic      : num -2581
  ..$ aicc     : num -2623
  ..$ x        : Time-Series [1:784] from 1 to 784: 4091 3989 4158 3418 6718 5460 4393 4657 4648 3831 ...
  ..$ lambda   : atomic [1:1] -0.175
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 4015 4058 4065 3953 4220 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 49  :List of 20
  ..$ coef     : Named num [1:2] -0.170606 0.000018
  .. ..- attr(*, "names")= chr [1:2] "ar1" "drift"
  ..$ sigma2   : num 2.19e-05
  ..$ var.coef : num [1:2, 1:2] 1.25e-03 -4.55e-09 -4.55e-09 2.18e-08
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "drift"
  .. .. ..$ : chr [1:2] "ar1" "drift"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 3063
  ..$ aic      : num -6120
  ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.00233 -0.0066 0.00249 0.00395 0.01 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.33029819523373,  2.32361437548974, 2.327269| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num -0.171
  .. ..$ theta: num(0) 
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:2] 1 1
  .. ..$ a    : num [1:2] 0.00294 2.32678
  .. ..$ P    : num [1:2, 1:2] 0.00 -8.81e-21 -8.81e-21 8.81e-21
  .. ..$ T    : num [1:2, 1:2] -0.171 1 0 1
  .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:2, 1:2] 1.00 -1.50e-21 -1.50e-21 8.81e-21
  ..$ xreg     : int [1:777, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num -6106
  ..$ aicc     : num -6120
  ..$ x        : Time-Series [1:777] from 1 to 777: 5866 4622 5250 5937 8731 7290 6532 6399 7062 6127 ...
  ..$ lambda   : atomic [1:1] -0.418
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 5384 5848 4809 5138 5816 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 50  :List of 19
  ..$ coef     : Named num [1:2] -0.1307 -0.0502
  .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  ..$ sigma2   : num 0.00438
  ..$ var.coef : num [1:2, 1:2] 0.001405 0.000364 0.000364 0.001791
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 1010
  ..$ aic      : num -2014
  ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00472 -0.03346 0.02655 0.04518 0.10729 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.72296932495699,  4.68918552235314, 4.719910| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num [1:2] -0.1307 -0.0502
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 0.02004 -0.00365 -0.00109 4.81776
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -4.25e-21 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.1307 -0.0502 0 -0.1307 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.31e-01 -5.02e-02 -3.17e-22 -1.31e-01 ...
  ..$ bic      : num -2000
  ..$ aicc     : num -2014
  ..$ x        : Time-Series [1:779] from 1 to 779: 3804 3388 3764 4380 6298 4734 3615 4176 4608 4395 ...
  ..$ lambda   : atomic [1:1] -0.151
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 3742 3800 3436 3741 4270 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 51  :List of 19
  ..$ coef     : Named num [1:4] 0.679 -0.1899 -0.0934 -0.9795
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ sigma2   : num 1.68e-07
  ..$ var.coef : num [1:4, 1:4] 0.001693 -0.001121 0.000505 -0.000113 -0.001121 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 3969
  ..$ aic      : num -7929
  ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 1.45e-03 -2.89e-04 7.38e-04 5.01e-05 5.03e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.44736492544213,  1.44702864613274, 1.447894| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.679 -0.1899 -0.0934
  .. ..$ theta: num [1:2] -0.98 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 2.03e-04 -3.84e-04 -1.81e-05 1.45
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 2.28e-20 -2.44e-19 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 0.679 -0.1899 -0.0934 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.98 0 0 -0.98 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.80e-01 0.00 -1.38e-20 -9.80e-01 ...
  ..$ bic      : num -7907
  ..$ aicc     : num -7929
  ..$ x        : Time-Series [1:622] from 1 to 622: 5152 4585 6323 6605 8125 6233 4729 6503 7322 6079 ...
  ..$ lambda   : atomic [1:1] -0.689
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 3297 5065 4787 6466 6458 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 52  :List of 19
  ..$ coef     : Named num [1:7] 2.154 -1.73 0.428 -2.612 2.479 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 1.06e-07
  ..$ var.coef : num [1:7, 1:7] 0.0156 -0.0265 0.0149 -0.0159 0.0383 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 4116
  ..$ aic      : num -8215
  ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 1.39e-03 -7.97e-05 3.64e-05 4.24e-05 4.19e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.39264283129069,  1.39254729369268, 1.392602| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 2.154 -1.73 0.428
  .. ..$ theta: num [1:4] -2.611922 2.478928 -0.859129 0.000149
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 2.23e-04 -8.15e-04 8.79e-04 -3.12e-04 5.40e-08 ...
  .. ..$ P    : num [1:6, 1:6] 1.11e-16 -8.88e-16 4.44e-16 -2.22e-16 2.71e-20 ...
  .. ..$ T    : num [1:6, 1:6] 2.154 -1.73 0.428 0 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 -2.611922 2.478928 -0.859129 0.000149 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -2.611922 2.478928 -0.859129 0.000149 ...
  ..$ bic      : num -8180
  ..$ aicc     : num -8215
  ..$ x        : Time-Series [1:622] from 1 to 622: 7176 6796 7011 7211 9928 8195 7530 7311 8929 8003 ...
  ..$ lambda   : atomic [1:1] -0.717
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 3792 7111 6868 7036 7520 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 53  :List of 19
  ..$ coef     : Named num [1:9] -1.342 -0.777 0.148 0.5 -0.044 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.00322
  ..$ var.coef : num [1:9, 1:9] 0.00333 0.00375 0.00135 -0.00183 -0.00215 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 1140
  ..$ aic      : num -2259
  ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.0127 -0.0148 -0.0163 -0.092 0.1247 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.68671096931498,  4.65611696982447, 4.652481| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 784
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.342 -0.777 0.148 0.5 -0.044
  .. ..$ theta: num [1:4] 1.708 1.593 0.733 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 0.10059 0.08453 0.08447 0.04389 -0.00331
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -1.342 -0.777 0.148 0.5 -0.044 ...
  .. ..$ V    : num [1:5, 1:5] 1 1.708 1.593 0.733 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 1.708 1.593 0.733 0 ...
  ..$ bic      : num -2213
  ..$ aicc     : num -2259
  ..$ x        : Time-Series [1:784] from 1 to 784: 5367 4767 4701 3298 8330 5576 5241 5640 5283 3510 ...
  ..$ lambda   : atomic [1:1] -0.159
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5107 5047 5006 4644 5040 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 54  :List of 19
  ..$ coef     : Named num [1:8] -0.482 -0.236 0.347 -0.111 -0.189 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.00688
  ..$ var.coef : num [1:8, 1:8] 0.003212 0.000247 0.000219 -0.000537 -0.000334 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 844
  ..$ aic      : num -1670
  ..$ arma     : int [1:7] 5 2 0 0 1 0 0
  ..$ residuals: Time-Series [1:785] from 1 to 785: -0.0321 -0.0307 0.0329 0.0376 0.0301 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(5.69706275003294,  5.68348963765527, 5.742385| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 785
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.482 -0.236 0.347 -0.111 -0.189
  .. ..$ theta: num [1:4] 1.08 0.844 0 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 0.1288 0.1127 0.0843 -0.0244 -0.0188
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -0.482 -0.236 0.347 -0.111 -0.189 ...
  .. ..$ V    : num [1:5, 1:5] 1 1.08 0.844 0 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 1.08 0.844 0 0 ...
  ..$ bic      : num -1628
  ..$ aicc     : num -1670
  ..$ x        : Time-Series [1:785] from 1 to 785: 6868 6631 7730 8628 9019 7571 7556 7181 7831 9073 ...
  ..$ lambda   : atomic [1:1] -0.108
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:785] from 1 to 785: 7468 7181 7094 7811 8325 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 55  :List of 19
  ..$ coef     : Named num [1:10] -0.517 0.267 0.633 0.185 -0.539 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.00542
  ..$ var.coef : num [1:10, 1:10] 0.002444 0.002235 0.000923 -0.001113 -0.000883 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 930
  ..$ aic      : num -1838
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00478 -0.02186 0.01778 -0.04486 0.12347 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.78360766389403,  4.75111864424898, 4.790174| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.517 0.267 0.633 0.185 -0.539
  .. ..$ theta: num [1:5] -0.1947 -0.6593 -0.6698 0.0419 0.589
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 0.0227 -0.1146 0.0298 0.0055 -0.0166 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 6.94e-18 ...
  .. ..$ T    : num [1:7, 1:7] -0.517 0.267 0.633 0.185 -0.539 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.1947 -0.6593 -0.6698 0.0419 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.1947 -0.6593 -0.6698 0.0419 ...
  ..$ bic      : num -1787
  ..$ aicc     : num -1838
  ..$ x        : Time-Series [1:780] from 1 to 780: 4516 4031 4622 3583 7164 6212 6439 6454 5619 3652 ...
  ..$ lambda   : atomic [1:1] -0.15
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 4441 4350 4341 4182 4563 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 56  :List of 19
  ..$ coef     : Named num [1:4] 0.197 -0.459 -0.263 -0.23
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ma1" "ma2" "ma3"
  ..$ sigma2   : num 2.23
  ..$ var.coef : num [1:4, 1:4] 0.02321 -0.02283 0.00938 0.01158 -0.02283 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num -1419
  ..$ aic      : num 2847
  ..$ arma     : int [1:7] 1 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:781] from 1 to 781: 0.0305 1.2525 -0.6342 0.4916 3.1316 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(30.4936873444812,  31.8976962991993, 31.10854| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 780
  ..$ model    :List of 10
  .. ..$ phi  : num 0.197
  .. ..$ theta: num [1:3] -0.459 -0.263 -0.23
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] 1.365 -0.905 -0.368 -0.334 34.297
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -5.82e-21 ...
  .. ..$ T    : num [1:5, 1:5] 0.197 0 0 0 1 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.459 -0.263 -0.23 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -4.59e-01 -2.63e-01 -2.30e-01 -9.39e-22 ...
  ..$ bic      : num 2871
  ..$ aicc     : num 2848
  ..$ x        : Time-Series [1:781] from 1 to 781: 5715 6710 6136 6384 8954 8523 6931 6999 7030 7210 ...
  ..$ lambda   : atomic [1:1] 0.248
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 5695 5817 6594 6035 6369 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 57  :List of 19
  ..$ coef     : Named num [1:10] -0.4035 0.3358 0.5964 0.0486 -0.5948 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.05e-07
  ..$ var.coef : num [1:10, 1:10] 0.003849 0.002297 0.0002 -0.002776 -0.000866 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 5095
  ..$ aic      : num -10168
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:769] from 1 to 769: 1.40e-03 -6.54e-05 -7.61e-06 -2.75e-04 6.86e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.39506976731438,  1.39497537299736, 1.395006| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 768
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.4035 0.3358 0.5964 0.0486 -0.5948
  .. ..$ theta: num [1:5] -0.1943 -0.6187 -0.5508 0.0842 0.3966
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 2.17e-04 -5.60e-04 1.06e-04 -8.30e-05 -2.46e-05 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 -1.39e-17 ...
  .. ..$ T    : num [1:7, 1:7] -0.4035 0.3358 0.5964 0.0486 -0.5948 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.1943 -0.6187 -0.5508 0.0842 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.1943 -0.6187 -0.5508 0.0842 ...
  ..$ bic      : num -10117
  ..$ aicc     : num -10168
  ..$ x        : Time-Series [1:769] from 1 to 769: 10719 9988 10222 8112 19314 14203 11842 12947 12230 7309 ...
  ..$ lambda   : atomic [1:1] -0.716
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:769] from 1 to 769: 4841 10485 10280 9756 10241 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 58  :List of 19
  ..$ coef     : Named num [1:5] 1.682 -0.945 -2.334 1.974 -0.623
  .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 2.43e-09
  ..$ var.coef : num [1:5, 1:5] 0.000376 -0.000348 -0.000682 0.001235 -0.000543 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 5630
  ..$ aic      : num -11249
  ..$ arma     : int [1:7] 2 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:623] from 1 to 623: 1.00e-03 -2.06e-05 1.28e-05 1.41e-05 8.90e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99984352041338,  0.999816843813967, 0.99983| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 622
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] 1.682 -0.945
  .. ..$ theta: num [1:3] -2.334 1.974 -0.623
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] 2.05e-06 -3.28e-05 3.73e-05 -1.36e-05 1.00
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -1.14e-17 ...
  .. ..$ T    : num [1:5, 1:5] 1.682 -0.945 0 0 1 ...
  .. ..$ V    : num [1:5, 1:5] 1 -2.334 1.974 -0.623 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -2.33 1.97 -6.23e-01 -4.43e-18 ...
  ..$ bic      : num -11222
  ..$ aicc     : num -11249
  ..$ x        : Time-Series [1:623] from 1 to 623: 4309 3865 4239 4452 8439 6704 5385 5833 5863 4585 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:623] from 1 to 623: 812 4199 4021 4189 4820 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 59  :List of 19
  ..$ coef     : Named num [1:9] -1.2585 -0.923 -0.2913 -0.0302 -0.3048 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 44.5
  ..$ var.coef : num [1:9, 1:9] 0.00532 0.00604 0.00282 -0.00222 -0.00259 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -2590
  ..$ aic      : num 5200
  ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:782] from 1 to 782: -0.339 -1.9752 0.0961 -12.3348 9.494 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(57.1483602396751,  55.2025019258398, 57.74530| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 782
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.2585 -0.923 -0.2913 -0.0302 -0.3048
  .. ..$ theta: num [1:4] 1.41 1.262 0.541 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 6.947 1.683 3.812 2.985 -0.345
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -1.2585 -0.923 -0.2913 -0.0302 -0.3048 ...
  .. ..$ V    : num [1:5, 1:5] 1 1.41 1.262 0.541 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 1.41 1.262 0.541 0 ...
  ..$ bic      : num 5247
  ..$ aicc     : num 5200
  ..$ x        : Time-Series [1:782] from 1 to 782: 5177 4722 5322 2384 8744 6252 6991 5798 5963 2273 ...
  ..$ lambda   : atomic [1:1] 0.359
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 5259 5184 5298 4660 5907 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 60  :List of 19
  ..$ coef     : Named num [1:10] -0.645 0.0718 0.5087 0.1867 -0.5071 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.000103
  ..$ var.coef : num [1:10, 1:10] 0.003802 0.004805 0.002939 -0.000551 -0.001618 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 2473
  ..$ aic      : num -4924
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0026 -0.00446 -0.00131 -0.0182 0.02265 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.60341003648283,  2.59661552104264, 2.598151| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.645 0.0718 0.5087 0.1867 -0.5071
  .. ..$ theta: num [1:5] -0.0471 -0.5965 -0.7541 -0.0729 0.5424
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] -0.00151 -0.01694 0.00521 0.00229 -0.00017 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 -6.94e-18 0.00 0.00 0.00 ...
  .. ..$ T    : num [1:7, 1:7] -0.645 0.0718 0.5087 0.1867 -0.5071 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.0471 -0.5965 -0.7541 -0.0729 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.0471 -0.5965 -0.7541 -0.0729 ...
  ..$ bic      : num -4873
  ..$ aicc     : num -4923
  ..$ x        : Time-Series [1:780] from 1 to 780: 6759 5697 5916 3505 10344 8969 7225 7500 6717 3870 ...
  ..$ lambda   : atomic [1:1] -0.369
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 6322 6366 6112 5222 5602 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 61  :List of 20
  ..$ coef     : Named num [1:6] -0.394 0.46 -0.052 -0.112 -0.865 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 1.75
  ..$ var.coef : num [1:6, 1:6] 0.005318 -0.000748 -0.00179 -0.004107 0.004012 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num -1316
  ..$ aic      : num 2646
  ..$ arma     : int [1:7] 3 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.0248 -1.4893 0.0386 0.5759 1.5933 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(24.7590071063863,  23.012668657777, 23.564689| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] -0.394 0.46 -0.052
  .. ..$ theta: num [1:2] -0.112 -0.865
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] -0.368 -0.802 0.524 24.512
  .. ..$ P    : num [1:4, 1:4] 0.00 1.39e-17 0.00 1.48e-16 1.39e-17 ...
  .. ..$ T    : num [1:4, 1:4] -0.394 0.46 -0.052 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.112 -0.865 0 -0.112 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.12e-01 -8.65e-01 6.95e-17 -1.12e-01 ...
  ..$ xreg     : int [1:777, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num 2679
  ..$ aicc     : num 2646
  ..$ x        : Time-Series [1:777] from 1 to 777: 4233 3221 3518 3923 5127 3982 3727 4144 4125 4115 ...
  ..$ lambda   : atomic [1:1] 0.226
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 4217 4070 3497 3586 4042 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 62  :List of 20
  ..$ coef     : Named num [1:2] -0.49 0.0297
  .. ..- attr(*, "names")= chr [1:2] "ar1" "drift"
  ..$ sigma2   : num 1414
  ..$ var.coef : num [1:2, 1:2] 9.75e-04 -6.40e-06 -6.40e-06 8.17e-01
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "drift"
  .. .. ..$ : chr [1:2] "ar1" "drift"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num -3925
  ..$ aic      : num 7856
  ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.202 -18.102 -7.295 -41.727 90.204 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(201.71438392195,  180.978807919199, 183.88765| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num -0.49
  .. ..$ theta: num(0) 
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:2] 1 1
  .. ..$ a    : num [1:2] 4.94 190.03
  .. ..$ P    : num [1:2, 1:2] 0.0 -3.5e-21 -3.5e-21 3.5e-21
  .. ..$ T    : num [1:2, 1:2] -0.49 1 0 1
  .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:2, 1:2] 1.00 -1.72e-21 -1.72e-21 3.50e-21
  ..$ xreg     : int [1:779, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num 7870
  ..$ aicc     : num 7856
  ..$ x        : Time-Series [1:779] from 1 to 779: 6484 5303 5462 3332 9812 8443 6253 6760 6806 3690 ...
  ..$ lambda   : atomic [1:1] 0.534
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6472 6328 5870 5386 4317 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 63  :List of 19
  ..$ coef     : Named num [1:6] 0.491 0.737 -0.611 -0.74 -0.87 ...
  .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 6.98e-07
  ..$ var.coef : num [1:6, 1:6] 0.003681 -0.000734 -0.000999 -0.003516 0.002225 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 4442
  ..$ aic      : num -8870
  ..$ arma     : int [1:7] 3 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.001613 -0.00019 0.000643 0.00051 0.001048 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.61326670314274,  1.61305056728001, 1.613784| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.491 0.737 -0.611
  .. ..$ theta: num [1:3] -0.74 -0.87 0.622
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] 0.000712 -0.000992 -0.000786 0.000681 1.615919
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -2.27e-18 ...
  .. ..$ T    : num [1:5, 1:5] 0.491 0.737 -0.611 0 1 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.74 -0.87 0.622 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -7.40e-01 -8.70e-01 6.22e-01 -9.65e-19 ...
  ..$ bic      : num -8837
  ..$ aicc     : num -8869
  ..$ x        : Time-Series [1:784] from 1 to 784: 5052 4849 5598 6332 8353 6412 6356 6734 7612 6279 ...
  ..$ lambda   : atomic [1:1] -0.617
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 3804 5027 4933 5679 6481 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 64  :List of 19
  ..$ coef     : Named num [1:4] 0.399 -0.742 -0.107 -0.132
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ma1" "ma2" "ma3"
  ..$ sigma2   : num 2.11e-06
  ..$ var.coef : num [1:4, 1:4] 0.00787 -0.00751 0.00368 0.00357 -0.00751 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 3982
  ..$ aic      : num -7954
  ..$ arma     : int [1:7] 1 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.88e-03 -4.70e-04 5.18e-04 -1.58e-05 2.66e-03 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.88385966547805,  1.88333604197829, 1.883981| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num 0.399
  .. ..$ theta: num [1:3] -0.742 -0.107 -0.132
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] 1.15e-04 -5.39e-04 -2.25e-04 -7.82e-05 1.89
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -7.23e-21 ...
  .. ..$ T    : num [1:5, 1:5] 0.399 0 0 0 1 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.742 -0.107 -0.132 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -7.42e-01 -1.07e-01 -1.32e-01 -1.41e-21 ...
  ..$ bic      : num -7931
  ..$ aicc     : num -7954
  ..$ x        : Time-Series [1:779] from 1 to 779: 7610 7190 7713 7667 10824 8735 8092 9395 8922 8473 ...
  ..$ lambda   : atomic [1:1] -0.526
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6251 7565 7289 7680 7836 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 65  :List of 19
  ..$ coef     : Named num [1:7] -0.5791 0.2108 0.2543 -0.0383 -0.3906 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.00422
  ..$ var.coef : num [1:7, 1:7] 0.00289 0.000658 -0.000253 -0.000445 -0.000683 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 1026
  ..$ aic      : num -2036
  ..$ arma     : int [1:7] 5 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0043 -0.02617 0.00505 -0.13038 0.11511 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.30241131761118,  4.2630712674577, 4.2894974| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.5791 0.2108 0.2543 -0.0383 -0.3906
  .. ..$ theta: num [1:4] -0.245 -0.737 0 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.01448 -0.09888 -0.00712 0.01576 -0.01724 ...
  .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 3.01e-19 3.07e-18 ...
  .. ..$ T    : num [1:6, 1:6] -0.5791 0.2108 0.2543 -0.0383 -0.3906 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.245 -0.737 0 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1.00 -2.45e-01 -7.37e-01 2.53e-18 0.00 ...
  ..$ bic      : num -1998
  ..$ aicc     : num -2035
  ..$ x        : Time-Series [1:780] from 1 to 780: 4738 3949 4460 2217 6614 6777 4716 4987 5976 2747 ...
  ..$ lambda   : atomic [1:1] -0.183
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 4643 4455 4357 3890 3825 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 66  :List of 19
  ..$ coef     : Named num -0.256
  .. ..- attr(*, "names")= chr "ma1"
  ..$ sigma2   : num 3.82e-08
  ..$ var.coef : num [1, 1] 0.00187
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr "ma1"
  .. .. ..$ : chr "ma1"
  ..$ mask     : logi TRUE
  ..$ loglik   : num 5548
  ..$ aic      : num -11093
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.28e-03 2.72e-05 2.48e-04 8.75e-05 2.39e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.28435703222091,  1.28438477326799, 1.284626| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.256
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 0.000173 -0.000043 1.284743
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -3.04e-21 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.2562 0 -0.2562 0.0657 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -2.56e-01 -6.20e-22 -2.56e-01 6.57e-02 ...
  ..$ bic      : num -11083
  ..$ aicc     : num -11093
  ..$ x        : Time-Series [1:777] from 1 to 777: 4993 5099 6221 6358 7867 6431 5659 6281 7734 5643 ...
  ..$ lambda   : atomic [1:1] -0.778
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 2431 4995 5075 5887 6231 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 67  :List of 19
  ..$ coef     : Named num [1:2] -0.786 -0.2
  .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  ..$ sigma2   : num 2.54e-09
  ..$ var.coef : num [1:2, 1:2] 0.00093 -0.000889 -0.000889 0.000925
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 6852
  ..$ aic      : num -13697
  ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 -2.05e-05 -4.27e-06 -3.82e-05 7.00e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999952146194639,  0.999925134042107, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num [1:2] -0.786 -0.2
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 1.33e-06 -3.16e-05 -6.43e-06 1.00
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -1.95e-21 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.786 -0.2 0 -0.786 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -7.86e-01 -2.00e-01 -9.35e-22 -7.86e-01 ...
  ..$ bic      : num -13683
  ..$ aicc     : num -13697
  ..$ x        : Time-Series [1:777] from 1 to 777: 8096 6644 6859 5456 12363 9451 8946 7888 8085 5115 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 891 7690 7066 6889 6629 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 68  :List of 19
  ..$ coef     : Named num [1:2] 0.518 -0.987
  .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  ..$ sigma2   : num 2.04e-09
  ..$ var.coef : num [1:2, 1:2] 1.13e-03 -1.31e-04 -1.31e-04 9.28e-05
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 7119
  ..$ aic      : num -14231
  ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.01e-03 -2.21e-05 -2.66e-05 1.81e-05 2.99e-06 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.00542379989032,  1.00539824648144, 1.005374| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num 0.518
  .. ..$ theta: num -0.987
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 4.12e-05 -4.16e-05 1.01
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 6.23e-23 0.00 3.99e-11 ...
  .. ..$ T    : num [1:3, 1:3] 0.518 0 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -0.987 0 -0.987 0.975 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.87e-01 2.81e-21 -9.87e-01 9.75e-01 ...
  ..$ bic      : num -14217
  ..$ aicc     : num -14231
  ..$ x        : Time-Series [1:784] from 1 to 784: 7669 6463 5645 6782 6912 6379 6083 5957 6347 6376 ...
  ..$ lambda   : atomic [1:1] -0.994
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 913 7482 6588 6073 6778 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 69  :List of 19
  ..$ coef     : Named num [1:5] 1.587 -0.847 -1.31 0.729 7.213
  .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ sigma2   : num 0.0123
  ..$ var.coef : num [1:5, 1:5] 1.53e-03 -1.24e-03 -1.45e-03 3.95e-04 -9.63e-07 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  ..$ loglik   : num 610
  ..$ aic      : num -1208
  ..$ arma     : int [1:7] 2 2 0 0 1 0 0
  ..$ residuals: Time-Series [1:781] from 1 to 781: 0.03794 0.02843 0.00884 -0.12335 0.24799 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(7.25948267164239,  7.26500041514854, 7.250731| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 781
  ..$ model    :List of 10
  .. ..$ phi  : num [1:2] 1.587 -0.847
  .. ..$ theta: num [1:2] -1.31 0.729
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:3] 1 0 0
  .. ..$ a    : num [1:3] 0.121 -0.1472 0.0477
  .. ..$ P    : num [1:3, 1:3] 0 0 0 0 0 ...
  .. ..$ T    : num [1:3, 1:3] 1.587 -0.847 0 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -1.31 0.729 -1.31 1.716 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1 -1.31 0.729 -1.31 1.716 ...
  ..$ bic      : num -1180
  ..$ aicc     : num -1208
  ..$ x        : Time-Series [1:781] from 1 to 781: 9903 9993 9762 7715 13265 11677 10233 9000 10349 7665 ...
  ..$ lambda   : atomic [1:1] -0.0537
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 9307 9538 9622 9429 8817 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 70  :List of 19
  ..$ coef     : Named num [1:9] 0.692 0.433 -0.764 0.198 -0.16 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 8.19e-10
  ..$ var.coef : num [1:9, 1:9] 0.004479 -0.00208 -0.003444 0.002255 0.000859 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7075
  ..$ aic      : num -14130
  ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:782] from 1 to 782: -1.54e-06 -1.95e-05 1.41e-06 1.94e-06 5.86e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999913379341035,  0.99989277567704, 0.99990| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 782
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] 0.692 0.433 -0.764 0.198 -0.16
  .. ..$ theta: num [1:4] -0.304 -0.402 0.622 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 4.42e-05 -2.47e-05 -2.13e-05 1.46e-05 -5.72e-06
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] 0.692 0.433 -0.764 0.198 -0.16 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.304 -0.402 0.622 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 -0.304 -0.402 0.622 0 ...
  ..$ bic      : num -14084
  ..$ aicc     : num -14130
  ..$ x        : Time-Series [1:782] from 1 to 782: 6163 5469 5912 6020 10059 7520 6778 6022 6776 5928 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 6222 6120 5863 5951 6331 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 71  :List of 19
  ..$ coef     : Named num [1:11] -0.352 0.399 0.48 -0.164 -0.837 ...
  .. ..- attr(*, "names")= chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 5.65e-10
  ..$ var.coef : num [1:11, 1:11] 1.06e-03 7.29e-04 -2.99e-06 -4.53e-04 -4.48e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:11] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7193
  ..$ aic      : num -14362
  ..$ arma     : int [1:7] 5 5 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -1.78e-05 -8.43e-06 1.41e-07 -1.11e-05 4.27e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999933626180052,  0.999937646986079, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.352 0.399 0.48 -0.164 -0.837
  .. ..$ theta: num [1:5] 0.653 0.0101 -0.2821 0.0207 0.4682
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. ..$ a    : num [1:6] 3.22e-05 -3.00e-06 -4.99e-06 -1.72e-05 -2.11e-05 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] -0.352 0.399 0.48 -0.164 -0.837 ...
  .. ..$ V    : num [1:6, 1:6] 1 0.653 0.0101 -0.2821 0.0207 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 0.653 0.0101 -0.2821 0.0207 ...
  ..$ bic      : num -14306
  ..$ aicc     : num -14362
  ..$ x        : Time-Series [1:779] from 1 to 779: 7041 7246 7737 7263 13634 10289 9952 9819 11501 7841 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 8051 7717 7729 7901 8618 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 72  :List of 19
  ..$ coef     : Named num [1:10] -0.7522 -0.0545 0.3312 0.1291 -0.4784 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 7.29e-09
  ..$ var.coef : num [1:10, 1:10] 0.004157 0.005719 0.003476 0.000356 -0.001338 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 4956
  ..$ aic      : num -9891
  ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:623] from 1 to 623: -1.61e-05 -1.36e-04 -3.53e-05 -2.24e-04 1.33e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999793314703828,  0.999648306194832, 0.9997| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 623
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.7522 -0.0545 0.3312 0.1291 -0.4784
  .. ..$ theta: num [1:4] 0.933 0.3 -0.262 -0.486
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 7.24e-05 -5.12e-05 -2.48e-05 -4.19e-05 -5.60e-05
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -0.7522 -0.0545 0.3312 0.1291 -0.4784 ...
  .. ..$ V    : num [1:5, 1:5] 1 0.933 0.3 -0.262 -0.486 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 0.933 0.3 -0.262 -0.486 ...
  ..$ bic      : num -9842
  ..$ aicc     : num -9890
  ..$ x        : Time-Series [1:623] from 1 to 623: 3543 2341 3198 1831 8386 5765 5079 4258 4311 2075 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:623] from 1 to 623: 3757 3430 3605 3106 3973 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 73  :List of 19
  ..$ coef     : Named num [1:2] -0.874 -0.103
  .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  ..$ sigma2   : num 2830
  ..$ var.coef : num [1:2, 1:2] 0.00132 -0.00127 -0.00127 0.00144
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. ..$ : chr [1:2] "ma1" "ma2"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num -4223
  ..$ aic      : num 8452
  ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.254 6.281 4.558 -59.451 109.202 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(254.149025733295,  262.513746846693, 264.2668| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num [1:2] -0.874 -0.103
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 37.64 -46.08 -5.27 306.61
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 5.84e-23 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.874 -0.103 0 -0.874 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.74e-01 -1.03e-01 2.60e-23 -8.74e-01 ...
  ..$ bic      : num 8466
  ..$ aicc     : num 8452
  ..$ x        : Time-Series [1:784] from 1 to 784: 3692 3890 3932 2373 6399 5342 4519 5197 4387 2297 ...
  ..$ lambda   : atomic [1:1] 0.616
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 3686 3741 3823 3657 3551 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 74  :List of 19
  ..$ coef     : Named num [1:9] 0.153 1.015 -0.512 -0.476 0.153 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.16e-09
  ..$ var.coef : num [1:9, 1:9] 0.0314 -0.0201 -0.0215 0.0262 -0.0289 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 6886
  ..$ aic      : num -13752
  ..$ arma     : int [1:7] 4 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:776] from 1 to 776: 2.12e-05 -2.86e-05 -2.03e-05 -2.57e-05 8.10e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999930806001656,  0.999884888835551, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] 0.153 1.015 -0.512 -0.476
  .. ..$ theta: num [1:4] 0.153 -0.849 0.334 0.506
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 3.74e-05 5.04e-06 -2.11e-05 -5.99e-06 2.24e-06
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] 0.153 1.015 -0.512 -0.476 0 ...
  .. ..$ V    : num [1:5, 1:5] 1 0.153 -0.849 0.334 0.506 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 0.153 -0.849 0.334 0.506 ...
  ..$ bic      : num -13705
  ..$ aicc     : num -13752
  ..$ x        : Time-Series [1:776] from 1 to 776: 6904 5243 5090 4692 9415 8134 5800 7331 6461 5312 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:776] from 1 to 776: 6022 6168 5675 5335 5344 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 75  :List of 19
  ..$ coef     : Named num -0.392
  .. ..- attr(*, "names")= chr "ma1"
  ..$ sigma2   : num 2.14e-09
  ..$ var.coef : num [1, 1] 0.00198
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr "ma1"
  .. .. ..$ : chr "ma1"
  ..$ mask     : logi TRUE
  ..$ loglik   : num 7062
  ..$ aic      : num -14120
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -1.63e-05 1.29e-05 -7.98e-06 3.49e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999904516468369,  0.999886584516886, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 783
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.392
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] -1.90e-06 -7.79e-07 1.00
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 7.87e-22 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.392 0 -0.392 0.154 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.92e-01 2.22e-22 -3.92e-01 1.54e-01 ...
  ..$ bic      : num -14111
  ..$ aicc     : num -14120
  ..$ x        : Time-Series [1:784] from 1 to 784: 5844 5290 5882 5464 6898 5843 5054 5258 5680 4827 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 854 5790 5466 5713 5559 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 76  :List of 19
  ..$ coef     : Named num -0.352
  .. ..- attr(*, "names")= chr "ar1"
  ..$ sigma2   : num 2.07e-09
  ..$ var.coef : num [1, 1] 0.00141
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr "ar1"
  .. .. ..$ : chr "ar1"
  ..$ mask     : logi TRUE
  ..$ loglik   : num 5802
  ..$ aic      : num -11601
  ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:623] from 1 to 623: 1.00e-03 -3.02e-05 9.26e-07 -1.84e-05 5.55e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999974022035681,  0.999941338316296, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 622
  ..$ model    :List of 10
  .. ..$ phi  : num -0.352
  .. ..$ theta: num(0) 
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:2] 1 1
  .. ..$ a    : num [1:2] 1.52e-05 1.00
  .. ..$ P    : num [1:2, 1:2] 0.00 -3.48e-17 -3.48e-17 3.48e-17
  .. ..$ T    : num [1:2, 1:2] -0.352 1 0 1
  .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:2, 1:2] 1.00 -1.22e-17 -1.22e-17 3.48e-17
  ..$ bic      : num -11592
  ..$ aicc     : num -11601
  ..$ x        : Time-Series [1:623] from 1 to 623: 9837 7445 8203 6914 12311 8321 9005 8112 9093 7813 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:623] from 1 to 623: 908 9604 8141 7919 7318 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 77  :List of 19
  ..$ coef     : Named num [1:8] 0.728 0.647 -0.884 -1.165 -0.599 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 5.18e-06
  ..$ var.coef : num [1:8, 1:8] 0.00279 -0.00365 0.00158 -0.00286 0.00485 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 3642
  ..$ aic      : num -7267
  ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:781] from 1 to 781: 0.002007 -0.002473 0.001839 0.000255 0.00476 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.00707241487974,  2.00410210912823, 2.006665| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 1
  ..$ n.cond   : int 0
  ..$ nobs     : int 780
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.728 0.647 -0.884
  .. ..$ theta: num [1:5] -1.165 -0.599 1.217 -0.175 -0.265
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 0.002691 -0.004619 -0.000871 0.003845 -0.000609 ...
  .. ..$ P    : num [1:7, 1:7] 0 0 0 0 0 ...
  .. ..$ T    : num [1:7, 1:7] 0.728 0.647 -0.884 0 0 ...
  .. ..$ V    : num [1:7, 1:7] 1 -1.165 -0.599 1.217 -0.175 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -1.165 -0.599 1.217 -0.175 ...
  ..$ bic      : num -7225
  ..$ aicc     : num -7266
  ..$ x        : Time-Series [1:781] from 1 to 781: 6573 5316 6376 6461 10350 7535 7781 6968 6881 7130 ...
  ..$ lambda   : atomic [1:1] -0.492
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 5681 6333 5587 6340 6903 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 78  :List of 19
  ..$ coef     : Named num [1:7] 0.7068 0.7225 -0.9293 -1.5178 -0.0806 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 0.00322
  ..$ var.coef : num [1:7, 1:7] 4.78e-04 -8.68e-05 -2.70e-04 -6.31e-04 5.89e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 1132
  ..$ aic      : num -2248
  ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.004268 -0.004545 0.000441 -0.036931 0.119175 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.26834467732629,  4.26195595497084, 4.265844| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.707 0.722 -0.929
  .. ..$ theta: num [1:4] -1.5178 -0.0806 1.3259 -0.7034
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.0807 -0.1616 0.0325 0.0793 -0.0432 ...
  .. ..$ P    : num [1:6, 1:6] 0.00 -2.22e-16 -2.78e-17 2.22e-16 -1.11e-16 ...
  .. ..$ T    : num [1:6, 1:6] 0.707 0.722 -0.929 0 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 -1.5178 -0.0806 1.3259 -0.7034 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -1.5178 -0.0806 1.3259 -0.7034 ...
  ..$ bic      : num -2210
  ..$ aicc     : num -2247
  ..$ x        : Time-Series [1:780] from 1 to 780: 3075 2994 3043 2521 5181 3712 3556 3583 3860 2797 ...
  ..$ lambda   : atomic [1:1] -0.178
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 3021 3051 3037 2933 3072 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 79  :List of 19
  ..$ coef     : Named num -0.504
  .. ..- attr(*, "names")= chr "ma1"
  ..$ sigma2   : num 3.66e-09
  ..$ var.coef : num [1, 1] 0.00177
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr "ma1"
  .. .. ..$ : chr "ma1"
  ..$ mask     : logi TRUE
  ..$ loglik   : num 6605
  ..$ aic      : num -13205
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 -3.70e-05 -4.94e-06 -4.53e-05 1.39e-04 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999868440704389,  0.999826453999085, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 776
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.504
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 1.71e-05 -6.40e-06 1.00
  .. ..$ P    : num [1:3, 1:3] 0.0 0.0 -3.4e-22 0.0 0.0 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.504 0 -0.504 0.254 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -5.04e-01 -1.14e-22 -5.04e-01 2.54e-01 ...
  ..$ bic      : num -13196
  ..$ aicc     : num -13205
  ..$ x        : Time-Series [1:777] from 1 to 777: 4827 4014 4210 3563 8444 6286 5261 4996 5329 3494 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 829 4715 4299 4248 3879 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 80  :List of 19
  ..$ coef     : num(0) 
  ..$ sigma2   : num 1015
  ..$ var.coef : num(0) 
  ..$ mask     : logi(0) 
  ..$ loglik   : num -3797
  ..$ aic      : num 7596
  ..$ arma     : int [1:7] 0 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.227 6.791 13.942 36.646 52.043 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(227.169301856619,  233.960064688439, 247.9016| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : num 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num(0) 
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:2] 1 1
  .. ..$ a    : num [1:2] 16.2 299.6
  .. ..$ P    : num [1:2, 1:2] 0.00 -7.42e-23 -7.42e-23 7.42e-23
  .. ..$ T    : num [1:2, 1:2] 0 1 0 1
  .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:2, 1:2] 1.00 0.00 0.00 7.42e-23
  ..$ bic      : num 7600
  ..$ aicc     : num 7596
  ..$ x        : Time-Series [1:779] from 1 to 779: 5495 5787 6407 8166 10977 8213 7002 7530 7822 7249 ...
  ..$ lambda   : atomic [1:1] 0.565
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 5485 5495 5787 6407 8166 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 81  :List of 19
  ..$ coef     : Named num [1:8] 0.4338 -0.0515 -0.8945 0.4525 -0.8841 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.0527
  ..$ var.coef : num [1:8, 1:8] 0.004696 0.000123 0.000468 0.002773 -0.003417 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 35.1
  ..$ aic      : num -52.2
  ..$ arma     : int [1:7] 4 4 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.0111 -0.4713 0.2042 -0.0311 0.329 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(11.1453648294304,  10.550199077084, 10.853326| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] 0.4338 -0.0515 -0.8945 0.4525
  .. ..$ theta: num [1:4] -0.884 -0.116 0.853 -0.82
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.358 -0.214 -0.104 0.177 -0.192 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] 0.4338 -0.0515 -0.8945 0.4525 0 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.884 -0.116 0.853 -0.82 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 -0.884 -0.116 0.853 -0.82 ...
  ..$ bic      : num -12.3
  ..$ aicc     : num -51.9
  ..$ x        : Time-Series [1:622] from 1 to 622: 7181 4874 5943 6311 8546 6574 6743 5781 6984 7537 ...
  ..$ lambda   : atomic [1:1] 0.0494
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 7130 6629 5201 6439 6917 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 82  :List of 19
  ..$ coef     : Named num [1:10] -0.633 0.148 0.563 0.236 -0.483 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 9.34e-06
  ..$ var.coef : num [1:10, 1:10] 0.00362 0.00447 0.00226 -0.00067 -0.00157 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 3404
  ..$ aic      : num -6785
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00201 0.000135 -0.000255 -0.003316 0.006186 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.00983698152278,  2.01003915527628, 2.009601| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.633 0.148 0.563 0.236 -0.483
  .. ..$ theta: num [1:5] -0.0555 -0.6688 -0.6462 -0.128 0.5122
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 0.001428 -0.00475 0.001657 0.000183 -0.000916 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 -2.08e-17 0.00 0.00 -2.78e-17 ...
  .. ..$ T    : num [1:7, 1:7] -0.633 0.148 0.563 0.236 -0.483 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.0555 -0.6688 -0.6462 -0.128 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.0555 -0.6688 -0.6462 -0.128 ...
  ..$ bic      : num -6734
  ..$ aicc     : num -6785
  ..$ x        : Time-Series [1:779] from 1 to 779: 8047 8184 7892 5799 14645 11770 10794 10918 10660 5289 ...
  ..$ lambda   : atomic [1:1] -0.492
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6853 8092 8061 7442 8082 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 83  :List of 19
  ..$ coef     : Named num [1:7] 0.651 0.703 -0.9 -0.488 -0.581 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 5.07e-05
  ..$ var.coef : num [1:7, 1:7] 1.13e-03 -4.74e-05 -5.58e-04 -1.38e-03 -2.36e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 2750
  ..$ aic      : num -5483
  ..$ arma     : int [1:7] 3 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00276 -0.00766 -0.00412 -0.00944 0.01687 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.39061348506058,  2.3797959313861, 2.3822892| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.651 0.703 -0.9
  .. ..$ theta: num [1:3] -0.488 -0.581 0.737
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:4] 1 0 0 0
  .. ..$ a    : num [1:4] 0.001069 -0.003106 0.000788 -0.002881
  .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..$ T    : num [1:4, 1:4] 0.651 0.703 -0.9 0 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.488 -0.581 0.737 -0.488 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1 -0.488 -0.581 0.737 -0.488 ...
  ..$ bic      : num -5446
  ..$ aicc     : num -5483
  ..$ x        : Time-Series [1:779] from 1 to 779: 4102 3060 3264 2649 5746 4773 4631 4298 4776 2954 ...
  ..$ lambda   : atomic [1:1] -0.404
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 3794 3752 3645 3363 3480 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 84  :List of 19
  ..$ coef     : Named num [1:7] 0.219 0.95 -0.449 -0.22 -0.774 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.48e-09
  ..$ var.coef : num [1:7, 1:7] 0.00496 -0.0011 -0.00257 0.00215 -0.00377 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7625
  ..$ aic      : num -15235
  ..$ arma     : int [1:7] 4 3 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.46e-05 1.39e-06 -3.39e-06 3.51e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999997010866548,  0.999978044671405, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] 0.219 0.95 -0.449 -0.22
  .. ..$ theta: num [1:3] -0.774 -0.869 0.679
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. ..$ a    : num [1:5] 1.05e-05 -1.48e-05 -2.83e-06 5.74e-06 1.00
  .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 4.88e-17 ...
  .. ..$ T    : num [1:5, 1:5] 0.219 0.95 -0.449 -0.22 1 ...
  .. ..$ V    : num [1:5, 1:5] 1 -0.774 -0.869 0.679 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1.00 -7.74e-01 -8.69e-01 6.79e-01 4.02e-17 ...
  ..$ bic      : num -15198
  ..$ aicc     : num -15235
  ..$ x        : Time-Series [1:779] from 1 to 779: 12709 10242 11274 10274 19582 15019 12951 12981 13462 10406 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 928 12044 11101 10645 11610 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 85  :List of 20
  ..$ coef     : Named num [1:2] -4.75e-01 8.74e-08
  .. ..- attr(*, "names")= chr [1:2] "ar1" "drift"
  ..$ sigma2   : num 2.91e-09
  ..$ var.coef : num [1:2, 1:2] 8.25e-04 1.97e-08 1.97e-08 1.06e-09
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "drift"
  .. .. ..$ : chr [1:2] "ar1" "drift"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 8127
  ..$ aic      : num -16249
  ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  ..$ residuals: Time-Series [1:942] from 1 to 942: 1.00e-03 6.40e-05 8.33e-06 -9.10e-06 1.56e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999838622895527,  0.999910864529877, 0.9998| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 941
  ..$ model    :List of 10
  .. ..$ phi  : num -0.475
  .. ..$ theta: num(0) 
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:2] 1 1
  .. ..$ a    : num [1:2] 1.07e-05 1.00
  .. ..$ P    : num [1:2, 1:2] 0.00 2.28e-22 2.28e-22 -2.28e-22
  .. ..$ T    : num [1:2, 1:2] -0.475 1 0 1
  .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:2, 1:2] 1.00 1.08e-22 1.08e-22 -2.28e-22
  ..$ xreg     : int [1:942, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num -16234
  ..$ aicc     : num -16249
  ..$ x        : Time-Series [1:942] from 1 to 942: 4220 6069 5246 5339 5774 10509 8990 7300 6523 7434 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:942] from 1 to 942: 809 4371 5026 5611 5298 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 86  :List of 19
  ..$ coef     : Named num [1:8] 0.8 0.616 -0.996 0.108 -0.492 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.449
  ..$ var.coef : num [1:8, 1:8] 0.00487 -0.00321 -0.00282 0.0033 -0.00348 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -789
  ..$ aic      : num 1595
  ..$ arma     : int [1:7] 4 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:778] from 1 to 778: -0.158 -0.676 -0.348 -0.426 1.449 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(14.763201085347,  14.1243961643442, 14.218456| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:4] 0.8 0.616 -0.996 0.108
  .. ..$ theta: num [1:3] -0.492 -0.6 0.734
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:4] 1 0 0 0
  .. ..$ a    : num [1:4] 0.605 -0.37 -0.342 0.19
  .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. ..$ T    : num [1:4, 1:4] 0.8 0.616 -0.996 0.108 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.492 -0.6 0.734 -0.492 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1 -0.492 -0.6 0.734 -0.492 ...
  ..$ bic      : num 1637
  ..$ aicc     : num 1596
  ..$ x        : Time-Series [1:778] from 1 to 778: 4230 3371 3487 3289 6623 5631 4334 4739 4530 3505 ...
  ..$ lambda   : atomic [1:1] 0.126
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:778] from 1 to 778: 4469 4285 3947 3831 4038 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 87  :List of 19
  ..$ coef     : Named num [1:11] -1.093 -1.123 -1.029 -0.919 -0.868 ...
  .. ..- attr(*, "names")= chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 369
  ..$ var.coef : num [1:11, 1:11] 7.58e-04 8.43e-04 5.66e-04 4.25e-05 -1.92e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:11] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -3426
  ..$ aic      : num 6875
  ..$ arma     : int [1:7] 5 5 0 0 1 0 0
  ..$ residuals: Time-Series [1:784] from 1 to 784: -1.33 -8.65 -16.83 -40.84 41.89 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(161.031172769098,  151.772957508451, 141.7001| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 784
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.093 -1.123 -1.029 -0.919 -0.868
  .. ..$ theta: num [1:5] 1.171 1.353 1.191 0.857 0.624
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. ..$ a    : num [1:6] 8.98 -8.74 10.17 14.77 13.22 ...
  .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. ..$ T    : num [1:6, 1:6] -1.093 -1.123 -1.029 -0.919 -0.868 ...
  .. ..$ V    : num [1:6, 1:6] 1 1.171 1.353 1.191 0.857 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1 1.171 1.353 1.191 0.857 ...
  ..$ bic      : num 6931
  ..$ aicc     : num 6876
  ..$ x        : Time-Series [1:784] from 1 to 784: 5636 5028 4405 2810 10252 7522 6396 5820 7238 2772 ...
  ..$ lambda   : atomic [1:1] 0.512
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5726 5595 5469 5106 6808 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 88  :List of 19
  ..$ coef     : Named num [1:9] -1.167 -0.871 -0.415 -0.223 -0.422 ...
  .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 13
  ..$ var.coef : num [1:9, 1:9] 0.00413 0.00473 0.00245 -0.00131 -0.00162 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -2104
  ..$ aic      : num 4228
  ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: -0.4358 -0.0383 -0.7076 -7.4163 4.7063 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(31.5511490949698,  32.0376944001306, 31.23059| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 780
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -1.167 -0.871 -0.415 -0.223 -0.422
  .. ..$ theta: num [1:4] 1.316 1.104 0.514 0
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 3.2958 0.0958 1.5581 0.3959 -1.4386
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -1.167 -0.871 -0.415 -0.223 -0.422 ...
  .. ..$ V    : num [1:5, 1:5] 1 1.316 1.104 0.514 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 1.316 1.104 0.514 0 ...
  ..$ bic      : num 4275
  ..$ aicc     : num 4229
  ..$ x        : Time-Series [1:780] from 1 to 780: 5289 5576 5106 1870 10051 8485 7137 6776 6704 2003 ...
  ..$ lambda   : atomic [1:1] 0.258
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 5546 5599 5516 4775 6329 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 89  :List of 19
  ..$ coef     : Named num [1:10] -0.763 0.0157 0.4817 0.2821 -0.368 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.000427
  ..$ var.coef : num [1:10, 1:10] 0.010805 0.015157 0.00938 0.000724 -0.003631 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 1530
  ..$ aic      : num -3039
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00351 -0.01958 -0.01064 -0.04987 0.0557 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(3.50724306786307,  3.47614236237408, 3.480223| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.763 0.0157 0.4817 0.2821 -0.368
  .. ..$ theta: num [1:5] -0.0816 -0.6129 -0.5793 -0.1609 0.4612
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 0.01324 -0.02662 0.00432 -0.00251 -0.00329 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 -2.78e-17 0.00 0.00 -2.78e-17 ...
  .. ..$ T    : num [1:7, 1:7] -0.763 0.0157 0.4817 0.2821 -0.368 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.0816 -0.6129 -0.5793 -0.1609 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.0816 -0.6129 -0.5793 -0.1609 ...
  ..$ bic      : num -2990
  ..$ aicc     : num -3038
  ..$ x        : Time-Series [1:622] from 1 to 622: 6635 5002 5185 3225 8960 7443 7057 5772 6393 3470 ...
  ..$ lambda   : atomic [1:1] -0.255
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 6420 5962 5703 4868 5279 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 90  :List of 20
  ..$ coef     : Named num [1:2] -0.379732 0.000966
  .. ..- attr(*, "names")= chr [1:2] "ma1" "drift"
  ..$ sigma2   : num 0.304
  ..$ var.coef : num [1:2, 1:2] 1.45e-03 8.93e-07 8.93e-07 1.50e-04
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ma1" "drift"
  .. .. ..$ : chr [1:2] "ma1" "drift"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num -639
  ..$ aic      : num 1284
  ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:778] from 1 to 778: 0.0149 -0.4846 -0.1225 0.1083 1.1161 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(14.9434068409552,  14.4260525746627, 14.47539| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 777
  ..$ model    :List of 10
  .. ..$ phi  : num(0) 
  .. ..$ theta: num -0.38
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 0.672 -0.27 14.379
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 3.41e-22 0.00 0.00 ...
  .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. ..$ V    : num [1:3, 1:3] 1 -0.38 0 -0.38 0.144 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.80e-01 9.38e-23 -3.80e-01 1.44e-01 ...
  ..$ xreg     : int [1:778, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr "drift"
  ..$ bic      : num 1298
  ..$ aicc     : num 1284
  ..$ x        : Time-Series [1:778] from 1 to 778: 8256 6727 6861 7299 11084 8981 7087 7574 7970 7100 ...
  ..$ lambda   : atomic [1:1] 0.104
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:778] from 1 to 778: 8208 8151 7204 6991 7184 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 91  :List of 19
  ..$ coef     : Named num [1:4] 0.518 0.115 -0.1 -0.963
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ sigma2   : num 2.86e-05
  ..$ var.coef : num [1:4, 1:4] 1.36e-03 -6.05e-04 -7.08e-06 -9.80e-05 -6.05e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 2964
  ..$ aic      : num -5917
  ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:778] from 1 to 778: 0.002294 -0.005218 -0.00047 0.000104 0.012972 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.29420793601765,  2.28833887849549, 2.289443| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 777
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.518 0.115 -0.1
  .. ..$ theta: num [1:2] -0.963 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 5.21e-05 -3.36e-03 -1.42e-04 2.30
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 5.35e-19 -5.33e-18 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 0.518 0.115 -0.1 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.963 0 0 -0.963 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.63e-01 0.00 -1.52e-18 -9.63e-01 ...
  ..$ bic      : num -5894
  ..$ aicc     : num -5917
  ..$ x        : Time-Series [1:778] from 1 to 778: 5087 4125 4285 4324 7652 6758 5861 5239 5835 4395 ...
  ..$ lambda   : atomic [1:1] -0.424
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:778] from 1 to 778: 4676 4965 4356 4308 4570 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 92  :List of 19
  ..$ coef     : Named num [1:4] 0.6337 0.0613 -0.1795 -0.9898
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ sigma2   : num 3.79e-05
  ..$ var.coef : num [1:4, 1:4] 1.25e-03 -7.96e-04 7.85e-05 -1.19e-05 -7.96e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 2857
  ..$ aic      : num -5703
  ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00232 0.000126 0.004644 -0.00021 0.016559 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.32030679340155,  2.32044846446879, 2.325608| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.6337 0.0613 -0.1795
  .. ..$ theta: num [1:2] -0.99 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 0.005029 -0.006135 0.000155 2.33378
  .. ..$ P    : num [1:4, 1:4] 0.0 0.0 -1.6e-17 8.9e-17 0.0 ...
  .. ..$ T    : num [1:4, 1:4] 0.6337 0.0613 -0.1795 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.99 0 0 -0.99 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.90e-01 0.00 1.87e-17 -9.90e-01 ...
  ..$ bic      : num -5680
  ..$ aicc     : num -5703
  ..$ x        : Time-Series [1:779] from 1 to 779: 4129 4148 4934 4759 9685 6620 6452 5888 5545 5437 ...
  ..$ lambda   : atomic [1:1] -0.418
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 3835 4131 4218 4794 4985 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 93  :List of 19
  ..$ coef     : Named num [1:10] -0.74179 0.00143 0.49848 0.27327 -0.40618 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 0.273
  ..$ var.coef : num [1:10, 1:10] 0.005388 0.007553 0.004994 0.000256 -0.00193 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -596
  ..$ aic      : num 1213
  ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.0369 0.0967 0.1488 -0.8491 0.7388 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(11.6910435472495,  11.8514868755181, 11.90358| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.74179 0.00143 0.49848 0.27327 -0.40618
  .. ..$ theta: num [1:4] 0.88 0.278 -0.349 -0.465
  .. ..$ Delta: num(0) 
  .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. ..$ a    : num [1:5] 0.26346 -0.40855 0.00507 0.09567 0.00859
  .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. ..$ T    : num [1:5, 1:5] -0.74179 0.00143 0.49848 0.27327 -0.40618 ...
  .. ..$ V    : num [1:5, 1:5] 1 0.88 0.278 -0.349 -0.465 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:5, 1:5] 1 0.88 0.278 -0.349 -0.465 ...
  ..$ bic      : num 1264
  ..$ aicc     : num 1213
  ..$ x        : Time-Series [1:779] from 1 to 779: 5520 6036 6213 3207 9394 7385 6712 6605 8189 3565 ...
  ..$ lambda   : atomic [1:1] 0.0676
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 5635 5720 5720 5204 6274 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 94  :List of 19
  ..$ coef     : Named num [1:7] -0.17 0.398 0.175 -0.12 -0.446 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 2.14e-09
  ..$ var.coef : num [1:7, 1:7] 6.35e-03 -1.97e-03 -1.42e-03 5.72e-04 4.01e-05 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 7024
  ..$ aic      : num -14033
  ..$ arma     : int [1:7] 5 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.59e-06 -8.80e-07 -2.24e-05 8.59e-05 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999904252363291,  0.999901444445018, 0.9999| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.17 0.398 0.175 -0.12 -0.446
  .. ..$ theta: num [1:4] -0.452 -0.532 0 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 6.12e-06 -4.10e-05 9.25e-06 7.36e-06 -1.79e-06 ...
  .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 -1.53e-17 -5.71e-17 ...
  .. ..$ T    : num [1:6, 1:6] -0.17 0.398 0.175 -0.12 -0.446 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.452 -0.532 0 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1.00 -4.52e-01 -5.32e-01 -3.55e-17 0.00 ...
  ..$ bic      : num -13996
  ..$ aicc     : num -14033
  ..$ x        : Time-Series [1:779] from 1 to 779: 5835 5741 5737 4966 11748 9091 7425 7423 7299 5653 ...
  ..$ lambda   : atomic [1:1] -1
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 854 5794 5766 5587 5850 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 95  :List of 19
  ..$ coef     : Named num [1:2] 0.169 -0.99
  .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  ..$ sigma2   : num 0.000387
  ..$ var.coef : num [1:2, 1:2] 1.28e-03 -3.06e-05 -3.06e-05 2.94e-05
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. ..$ : chr [1:2] "ar1" "ma1"
  ..$ mask     : logi [1:2] TRUE TRUE
  ..$ loglik   : num 1954
  ..$ aic      : num -3903
  ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00302 -0.00856 -0.00224 -0.02439 0.03868 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(3.0207732058344,  3.00963071725562, 3.0116060| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num 0.169
  .. ..$ theta: num -0.99
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:3] 1 0 1
  .. ..$ a    : num [1:3] 0.00709 -0.01321 3.01878
  .. ..$ P    : num [1:3, 1:3] 0.00 0.00 1.86e-22 0.00 1.64e-09 ...
  .. ..$ T    : num [1:3, 1:3] 0.169 0 1 1 0 ...
  .. ..$ V    : num [1:3, 1:3] 1 -0.99 0 -0.99 0.979 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.90e-01 3.26e-20 -9.90e-01 9.79e-01 ...
  ..$ bic      : num -3889
  ..$ aicc     : num -3902
  ..$ x        : Time-Series [1:780] from 1 to 780: 7770 6522 6723 4644 11985 10371 9232 8809 7882 4119 ...
  ..$ lambda   : atomic [1:1] -0.311
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 7403 7455 6961 6620 6286 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 96  :List of 19
  ..$ coef     : Named num [1:7] -0.668 -0.0101 -0.0851 -0.2105 -0.3709 ...
  .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 8.7
  ..$ var.coef : num [1:7, 1:7] 2.28e-03 6.96e-04 3.19e-06 2.32e-04 -3.04e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num -1947
  ..$ aic      : num 3910
  ..$ arma     : int [1:7] 5 2 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0241 0.1296 -0.0963 -4.776 6.208 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(24.1147558790783,  24.3091468425947, 24.09073| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.668 -0.0101 -0.0851 -0.2105 -0.3709
  .. ..$ theta: num [1:4] -0.228 -0.75 0 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. ..$ a    : num [1:6] 0.0693 -4.415 -0.4669 0.6331 0.3586 ...
  .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 1.47e-18 2.58e-18 ...
  .. ..$ T    : num [1:6, 1:6] -0.668 -0.0101 -0.0851 -0.2105 -0.3709 ...
  .. ..$ V    : num [1:6, 1:6] 1 -0.228 -0.75 0 0 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:6, 1:6] 1.00 -2.28e-01 -7.50e-01 2.31e-18 0.00 ...
  ..$ bic      : num 3947
  ..$ aicc     : num 3910
  ..$ x        : Time-Series [1:780] from 1 to 780: 3999 4122 3984 1384 8978 7028 6511 6255 5667 1461 ...
  ..$ lambda   : atomic [1:1] 0.224
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 3984 4040 4044 3267 3673 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 97  :List of 19
  ..$ coef     : Named num [1:10] -0.587 0.209 0.626 0.24 -0.5 ...
  .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ sigma2   : num 1.39e-06
  ..$ var.coef : num [1:10, 1:10] 0.00282 0.00308 0.00136 -0.00112 -0.00131 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 4150
  ..$ aic      : num -8278
  ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.001628 0.000137 -0.000023 -0.001811 0.002444 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.62796224586026,  1.62818049618764, 1.628034| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 779
  ..$ model    :List of 10
  .. ..$ phi  : num [1:5] -0.587 0.209 0.626 0.24 -0.5
  .. ..$ theta: num [1:5] -0.176 -0.665 -0.635 -0.026 0.571
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 3.50e-04 -1.74e-03 4.43e-04 3.64e-05 -1.54e-04 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 3.47e-17 ...
  .. ..$ T    : num [1:7, 1:7] -0.587 0.209 0.626 0.24 -0.5 ...
  .. ..$ V    : num [1:7, 1:7] 1 -0.176 -0.665 -0.635 -0.026 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -0.176 -0.665 -0.635 -0.026 ...
  ..$ bic      : num -8227
  ..$ aicc     : num -8278
  ..$ x        : Time-Series [1:780] from 1 to 780: 5735 5992 5818 3863 10668 7737 6864 8052 7540 4087 ...
  ..$ lambda   : atomic [1:1] -0.611
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 4272 5829 5845 5263 5924 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 98  :List of 19
  ..$ coef     : Named num [1:4] 0.6387 0.0289 -0.1421 -0.9847
  .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ sigma2   : num 4.77e-07
  ..$ var.coef : num [1:4, 1:4] 1.28e-03 -8.07e-04 1.01e-04 -2.78e-05 -8.07e-04 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  ..$ loglik   : num 4561
  ..$ aic      : num -9112
  ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.001521 0.00042 0.000467 0.000541 0.001559 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.52079486056249,  1.5212644776116, 1.5217140| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 778
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 0.6387 0.0289 -0.1421
  .. ..$ theta: num [1:2] -0.985 0
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:4] 1 0 0 1
  .. ..$ a    : num [1:4] 2.87e-04 -4.61e-04 -7.96e-05 1.52
  .. ..$ P    : num [1:4, 1:4] 0.00 0.00 -1.01e-18 7.08e-18 0.00 ...
  .. ..$ T    : num [1:4, 1:4] 0.6387 0.0289 -0.1421 1 1 ...
  .. ..$ V    : num [1:4, 1:4] 1 -0.985 0 0 -0.985 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.85e-01 0.00 1.34e-18 -9.85e-01 ...
  ..$ bic      : num -9089
  ..$ aicc     : num -9112
  ..$ x        : Time-Series [1:779] from 1 to 779: 3169 3483 3835 4299 6406 4649 4002 4569 4659 3975 ...
  ..$ lambda   : atomic [1:1] -0.654
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 2416 3200 3470 3799 4214 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
 $ 99  :List of 19
  ..$ coef     : Named num [1:8] 1.594 -0.77 -0.118 -2.04 1.217 ...
  .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ sigma2   : num 0.000169
  ..$ var.coef : num [1:8, 1:8] 0.0998 -0.1701 0.0965 -0.098 0.2127 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  ..$ loglik   : num 1817
  ..$ aic      : num -3617
  ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00304 -0.01839 0.0081 0.00458 0.02809 ...
  ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(3.0442983265908,  3.02198374025874, 3.0336253| __truncated__ ...
  ..$ series   : chr "y.xts"
  ..$ code     : int 0
  ..$ n.cond   : int 0
  ..$ nobs     : int 621
  ..$ model    :List of 10
  .. ..$ phi  : num [1:3] 1.594 -0.77 -0.118
  .. ..$ theta: num [1:5] -2.04048 1.2171 -0.00674 -0.00614 -0.14685
  .. ..$ Delta: num 1
  .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. ..$ a    : num [1:7] 0.005906 -0.021547 0.015775 -0.001044 0.000576 ...
  .. ..$ P    : num [1:7, 1:7] 0.00 -4.44e-16 2.22e-16 -8.67e-19 -7.81e-18 ...
  .. ..$ T    : num [1:7, 1:7] 1.594 -0.77 -0.118 0 0 ...
  .. ..$ V    : num [1:7, 1:7] 1 -2.04048 1.2171 -0.00674 -0.00614 ...
  .. ..$ h    : num 0
  .. ..$ Pn   : num [1:7, 1:7] 1 -2.04048 1.2171 -0.00674 -0.00614 ...
  ..$ bic      : num -3577
  ..$ aicc     : num -3616
  ..$ x        : Time-Series [1:622] from 1 to 622: 4367 3333 3827 4100 6514 5534 3781 4467 4157 4101 ...
  ..$ lambda   : atomic [1:1] -0.302
  .. ..- attr(*, "biasadj")= logi FALSE
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 4203 4158 3474 3876 4465 ...
  ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  [list output truncated]
 - attr(*, "split_type")= chr "data.frame"
 - attr(*, "split_labels")='data.frame':	1115 obs. of  1 variable:
  ..$ Store: int [1:1115] 1 2 3 4 5 6 7 8 9 10 ...

Modelado multivariado mediante la funcion $tslm$ de la librería $forecast$



In [187]:

    
str(train.store.new)









    



'data.frame':	844338 obs. of  25 variables:
 $ Store                    : int  1 1 1 1 1 1 1 1 1 1 ...
 $ DayOfWeek                : int  3 4 5 6 1 2 3 4 5 6 ...
 $ Date                     : Date, format: "2013-01-02" "2013-01-03" ...
 $ Sales                    : int  5530 4327 4486 4997 7176 5580 5471 4892 4881 4952 ...
 $ Customers                : int  668 578 619 635 785 654 626 615 592 646 ...
 $ Open                     : int  1 1 1 1 1 1 1 1 1 1 ...
 $ Promo                    : int  0 0 0 0 1 1 1 1 1 0 ...
 $ StateHoliday             : Factor w/ 4 levels "0","a","b","c": 1 1 1 1 1 1 1 1 1 1 ...
 $ SchoolHoliday            : num  1 1 1 1 1 1 1 1 1 0 ...
 $ StoreType                : Factor w/ 4 levels "a","b","c","d": 3 3 3 3 3 3 3 3 3 3 ...
 $ Assortment               : Factor w/ 3 levels "a","b","c": 1 1 1 1 1 1 1 1 1 1 ...
 $ CompetitionDistance      : num  1270 1270 1270 1270 1270 1270 1270 1270 1270 1270 ...
 $ CompetitionOpenSinceMonth: num  9 9 9 9 9 9 9 9 9 9 ...
 $ CompetitionOpenSinceYear : num  2008 2008 2008 2008 2008 ...
 $ Promo2                   : int  0 0 0 0 0 0 0 0 0 0 ...
 $ Promo2SinceWeek          : num  0 0 0 0 0 0 0 0 0 0 ...
 $ Promo2SinceYear          : num  0 0 0 0 0 0 0 0 0 0 ...
 $ PromoInterval            : Factor w/ 4 levels "","Feb,May,Aug,Nov",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ Year                     : int  2013 2013 2013 2013 2013 2013 2013 2013 2013 2013 ...
 $ Month                    : int  1 1 1 1 1 1 1 1 1 1 ...
 $ Day                      : int  2 3 4 5 7 8 9 10 11 12 ...
 $ WeekOfYear               : int  1 1 1 1 2 2 2 2 2 2 ...
 $ SalesPerCustomer         : num  8.28 7.49 7.25 7.87 9.14 ...
 $ CompetitionOpen          : num  52 52 52 52 52 52 52 52 52 52 ...
 $ PromoOpen                : num  24156 24156 24156 24156 24156 ...



In [200]:

    
## variables with single value
which(sapply(train.store.new, function(x) { length(unique(x)) }) == 1)
## count levels before dropping redundant ones
sapply(train.store.new[sapply(train.store.new, is.factor)], nlevels)
## extract factor columns and drop redundant levels
fctr <- lapply(train.store.new[sapply(train.store.new, is.factor)], droplevels)
## count levels after dropping redundant ones
sapply(fctr, nlevels)









    




Open: 6






    





	StateHoliday
		4
	StoreType
		4
	Assortment
		3
	PromoInterval
		4








    





	StateHoliday
		4
	StoreType
		4
	Assortment
		3
	PromoInterval
		4



In [1]:

    
# Funcion para generar los modelos TSLM por tienda

tslm_fit = function(store){
  Sales <- ts(store$Sales, frequency = 365)
  DayOfWeek <- store$DayOfWeek
  StateHoliday <- droplevels(store$StateHoliday)
  SchoolHoliday <- store$SchoolHoliday
  Promo <- store$Promo
  Promo2 <- store$Promo2
  if(nlevels(StateHoliday)>1) {
  fit <- tslm(Sales ~ trend + season + 
                      DayOfWeek + StateHoliday + SchoolHoliday + 
                      Promo + Promo2
             )
  } else {
  fit <- tslm(Sales ~ trend + season + 
                      DayOfWeek + SchoolHoliday + 
                      Promo + Promo2
             )   
  }
  return(fit)
}



In [2]:

    
system.time(
    out.tslm <- dlply(train.store.new, .(Store), tslm_fit)
)









    



Error in dlply(train.store.new, .(Store), tslm_fit): could not find function "dlply"
Traceback:

1. system.time(out.tslm <- dlply(train.store.new, .(Store), tslm_fit))





    



Timing stopped at: 0.003 0.001 0.006



In [208]:

    
str(out.tslm)









    



List of 1115
 $ 1   :List of 14
  ..$ coefficients : Named num [1:370] 4833.629 -0.636 -424.39 -720.799 -1020.803 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:781] from 1 to 3.14: 150 -693 -303 444 1303 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:781] -132999 -3236 801 441 -629 ...
  .. ..- attr(*, "names")= chr [1:781] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:781] from 1 to 3.14: 5380 5020 4789 4553 5873 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:781, 1:370] -27.9464 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:781] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 412
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b58ca60> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	781 obs. of  7 variables:
  .. ..$ Sales        : int [1:781] 5530 4327 4486 4997 7176 5580 5471 4892 4881 4952 ...
  .. ..$ trend        : int [1:781] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:781] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:781] 1 1 1 1 1 1 1 1 1 0 ...
  .. ..$ Promo        : int [1:781] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:781] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b58ca60> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 2   :List of 14
  ..$ coefficients : Named num [1:371] 5238.342 0.217 -287.647 389.706 -443.06 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 16.9 398.7 403.4 -310.3 -27.8 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -1.39e+05 2.97e+03 -7.87e+02 2.20e+03 5.73 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 4405 3760 4081 2652 6803 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:371] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 414
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa273ab28a0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  8 variables:
  .. ..$ Sales        : int [1:784] 4422 4159 4484 2342 6775 6318 6763 5618 4810 2630 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa273ab28a0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 3   :List of 14
  ..$ coefficients : Named num [1:370] 7290.78 -0.35 -642.96 -451.21 -641.03 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -22.3 14.6 304.8 -237.8 1921.7 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -193771 240 -746 129 -1035 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 6845 5887 5764 4761 10325 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b8b39f8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 6823 5902 6069 4523 12247 9800 8001 7772 9292 4455 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b8b39f8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 4   :List of 14
  ..$ coefficients : Named num [1:370] 9258.49 1.11 310.39 -486.22 -530.54 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 405 -1618 -796 1502 2219 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -269875 7858 1830 1371 1199 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 9536 9865 9086 8836 9893 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f098d80> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 9941 8247 8290 10338 12112 10031 8857 9472 10512 9719 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f098d80> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 5   :List of 14
  ..$ coefficients : Named num [1:371] 5027.302 -0.042 -438.357 87.75 -503.273 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: 240 585 1477 -370 217 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -130517 1655 -2127 -481 -2251 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 4013 2880 2979 1960 6761 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:371] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 409
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281e3af40> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  8 variables:
  .. ..$ Sales        : int [1:779] 4253 3465 4456 1590 6978 5718 5974 4999 5159 1760 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:779] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281e3af40> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 6   :List of 14
  ..$ coefficients : Named num [1:371] 7247.4 -2.63 -269.59 -478.18 -1220.75 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: 66.8 -164.4 1093.4 -28.9 337.5 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -153884 -15199 592 -1411 -2094 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 6022 5562 4999 3901 8254 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:371] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f4bfa28> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  8 variables:
  .. ..$ Sales        : int [1:780] 6089 5398 6092 3872 8591 7099 6749 6282 6829 3829 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:780] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f4bfa28> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 7   :List of 14
  ..$ coefficients : Named num [1:371] 8324.05 1.72 1559.6 -280.13 991.42 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:786] from 1 to 3.15: 248 -1836 1020 -1160 1485 ...
  .. ..- attr(*, "names")= chr [1:786] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:786] -247192 9832 -298 -4343 2596 ...
  .. ..- attr(*, "names")= chr [1:786] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:786] from 1 to 3.15: 7996 9067 6738 6378 11233 ...
  .. ..- attr(*, "names")= chr [1:786] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:786, 1:371] -28.0357 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:786] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 416
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b7db660> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	786 obs. of  8 variables:
  .. ..$ Sales        : int [1:786] 8244 7231 7758 5218 12718 10073 7049 8234 7115 4236 ...
  .. ..$ trend        : int [1:786] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:786] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:786] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:786] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:786] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b7db660> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 8   :List of 14
  ..$ coefficients : Named num [1:370] 5870.13 2.07 212.63 -496.08 -1285.48 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 815 440 780 242 514 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -155102 14647.5 1093.7 1977.9 -95.7 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 4604 4402 3279 2095 6902 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d39e908> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5419 4842 4059 2337 7416 6333 5038 6084 4997 2660 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d39e908> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 9   :List of 14
  ..$ coefficients : Named num [1:370] 5872.3 3.2 -854.2 -987 -1492.8 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -702.3 -41.6 394.6 525.3 1358.5 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -183159 21667 -179 -219 -1325 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 5605 4644 4403 3729 6215 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e868638> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4903 4602 4798 4254 7574 6206 4699 5340 5855 4657 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e868638> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 10  :List of 14
  ..$ coefficients : Named num [1:370] 5570.008 0.956 63.115 266.564 -493.851 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -98.7 -135.4 263.5 161.9 1155.1 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -155915.8 6714.1 266.6 1546.5 44.3 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 4911 4810 4851 4094 6649 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b87fad8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 4812 4675 5114 4256 7804 5394 5696 5419 5556 4402 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b87fad8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 11  :List of 14
  ..$ coefficients : Named num [1:370] 8870.681 -0.458 -146.384 -1006.101 -1246.736 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 632 -476 1062 -184 455 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -224867 -586 350 449 -613 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 8281 7851 6706 5918 9484 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d640140> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 8913 7375 7768 5734 9939 9422 8458 8525 8745 5752 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d640140> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 12  :List of 14
  ..$ coefficients : Named num [1:370] 6695.393 0.772 509.456 -59.089 227.359 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -992 -1452 -896 741 1920 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -212509 7198 152 1185 1339 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 6021 6319 5538 5651 9090 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29967dca8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5029 4867 4642 6392 11010 9114 8311 7591 7999 6342 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29967dca8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 13  :List of 14
  ..$ coefficients : Named num [1:370] 2606.177 0.886 457.564 761.211 1116.911 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:621] from 1 to 2.7: 579.8 23.3 -142.3 348.1 1403.6 ...
  .. ..- attr(*, "names")= chr [1:621] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:621] -125465.3 3666.9 -33.9 -1396.2 -1313.3 ...
  .. ..- attr(*, "names")= chr [1:621] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:621] from 1 to 2.7: 3157 3651 3990 3937 6842 ...
  .. ..- attr(*, "names")= chr [1:621] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:621, 1:370] -24.9199 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:621] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 252
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bf28cd0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	621 obs. of  7 variables:
  .. ..$ Sales        : int [1:621] 3737 3674 3848 4285 8246 6700 5296 5432 6075 4592 ...
  .. ..$ trend        : int [1:621] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:621] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:621] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:621] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:621] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bf28cd0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 14  :List of 14
  ..$ coefficients : Named num [1:370] 6501.657 0.304 -893.134 -524.426 -1318.169 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -231.7 -77.9 463.1 -595.8 425.9 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -153747 2882 -924 310 -1675 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 5485 4247 4271 3115 7362 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bcf84e0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 5253 4169 4734 2519 7788 6920 5391 6046 6159 3020 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bcf84e0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 15  :List of 14
  ..$ coefficients : Named num [1:370] 5854.304 0.804 355.558 -230.55 -278.125 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -1028 -881 -198 344 1442 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -186840 6566 648 1007 778 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 5729 6021 5372 5194 7607 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29a368640> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 4701 5140 5174 5538 9049 7439 6777 6818 7621 5429 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29a368640> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 16  :List of 14
  ..$ coefficients : Named num [1:370] 6960.24 1.63 -371.06 -61.45 83.59 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: 729 220 537 -361 536 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -214097 12005 -1155 -1301 -1964 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 6190 5430 5351 4707 9477 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d51efb8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 6919 5650 5888 4346 10013 8370 7898 7017 7498 4559 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d51efb8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 17  :List of 14
  ..$ coefficients : Named num [1:370] 6775.516 -0.101 -32.343 440.839 -924.306 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:782] from 1 to 3.14: 76.8 191.7 1043 165.7 1826.9 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:782] -177172 1902 1969 1802 -1823 ...
  .. ..- attr(*, "names")= chr [1:782] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:782] from 1 to 3.14: 5516 4910 4810 2410 9452 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:782, 1:370] -27.9643 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:782] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 413
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa275c01aa0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	782 obs. of  7 variables:
  .. ..$ Sales        : int [1:782] 5593 5102 5853 2576 11279 9034 7450 7259 7711 3031 ...
  .. ..$ trend        : int [1:782] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:782] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:782] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:782] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:782] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa275c01aa0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 18  :List of 14
  ..$ coefficients : Named num [1:370] 5439.4 1.69 359.34 330.15 -59.84 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:782] from 1 to 3.14: 92.9 -89.3 1249 -265.3 1033.3 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:782] -183453 12634 1447 987 -289 ...
  .. ..- attr(*, "names")= chr [1:782] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:782] from 1 to 3.14: 5050 5172 4906 3953 6810 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:782, 1:370] -27.9643 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:782] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 413
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bc29ea8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	782 obs. of  7 variables:
  .. ..$ Sales        : int [1:782] 5143 5083 6155 3688 7843 6653 6553 6903 6797 3768 ...
  .. ..$ trend        : int [1:782] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:782] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:782] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:782] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:782] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bc29ea8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 19  :List of 14
  ..$ coefficients : Named num [1:370] 6825.83 1.54 -1195.79 -1024.19 -1222.61 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -93.6 -290.2 1021.9 164.8 740.5 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -180439 10844 -1237 -364 -1308 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 5857 4328 4167 3604 8237 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e843ad0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 5763 4038 5189 3769 8978 7369 6149 6753 6725 3950 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e843ad0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 20  :List of 14
  ..$ coefficients : Named num [1:370] 7442.9 2.36 1142.69 -17.11 -741.66 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:619] from 1 to 2.69: 669.6 265.6 161.1 -98.4 394 ...
  .. ..- attr(*, "names")= chr [1:619] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:619] -192990 10636 862 -1480 -4668 ...
  .. ..- attr(*, "names")= chr [1:619] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:619] from 1 to 2.69: 6440 7090 5438 3740 9268 ...
  .. ..- attr(*, "names")= chr [1:619] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:619, 1:370] -24.8797 0.0402 0.0402 0.0402 0.0402 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:619] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 250
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27371bb20> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	619 obs. of  7 variables:
  .. ..$ Sales        : int [1:619] 7110 7356 5599 3642 9662 9065 7764 8175 6745 4527 ...
  .. ..$ trend        : int [1:619] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:619] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:619] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:619] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:619] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27371bb20> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 21  :List of 14
  ..$ coefficients : Named num [1:370] 3106.006 0.885 188.768 -169.798 243.601 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: 109 165 968 1381 1689 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -152818 7033 -1116 -1656 -1040 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 3571 3810 3503 3653 7891 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2739daf18> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 3680 3975 4471 5034 9580 7288 6618 5569 5869 5329 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2739daf18> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 22  :List of 14
  ..$ coefficients : Named num [1:370] 3648.367 0.777 421.034 215.573 -307.416 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:619] from 1 to 2.69: 0.239 62.02 529.295 -77.509 925.497 ...
  .. ..- attr(*, "names")= chr [1:619] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:619] -112602 3552 -912 -914 -1931 ...
  .. ..- attr(*, "names")= chr [1:619] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:619] from 1 to 2.69: 3514 3832 3524 2723 5582 ...
  .. ..- attr(*, "names")= chr [1:619] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:619, 1:370] -24.8797 0.0402 0.0402 0.0402 0.0402 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:619] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 250
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f267348> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	619 obs. of  7 variables:
  .. ..$ Sales        : int [1:619] 3514 3894 4053 2645 6507 5779 5254 4742 4750 2665 ...
  .. ..$ trend        : int [1:619] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:619] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:619] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:619] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:619] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f267348> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 23  :List of 14
  ..$ coefficients : Named num [1:370] 5515.983 0.149 -930.243 -886.906 -1540.88 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1057 103 226 507 1778 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -154074 2626 -412 -249 -1601 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 5580 4598 4590 3667 7297 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2808f3d18> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4523 4701 4816 4174 9075 6998 5800 6023 6377 4314 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2808f3d18> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 24  :List of 14
  ..$ coefficients : Named num [1:370] 8381.54 1.33 -837.14 -648.78 -1446.21 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1465 -571 1117 1306 2119 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -262032 12215 -1399 -710 -2827 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 8372 7324 7302 5669 11334 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2829aca30> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 6907 6753 8419 6975 13453 10349 9474 9823 10333 7297 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2829aca30> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 25  :List of 14
  ..$ coefficients : Named num [1:370] 13529.34 -1.72 -935.38 -1997.88 -2324.46 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:750] from 1 to 3.05: 56.4 -121.5 682.8 309.3 467.3 ...
  .. ..- attr(*, "names")= chr [1:750] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:750] -305869 -7391 -1971 -4333 -2435 ...
  .. ..- attr(*, "names")= chr [1:750] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:750] from 1 to 3.05: 11888 10530 9046 8678 14046 ...
  .. ..- attr(*, "names")= chr [1:750] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:750, 1:370] -27.3861 0.0365 0.0365 0.0365 0.0365 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:750] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.04 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 381
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f764a08> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	750 obs. of  7 variables:
  .. ..$ Sales        : int [1:750] 11944 10409 9729 8987 14513 14243 11539 11835 11194 9227 ...
  .. ..$ trend        : int [1:750] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:750] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:750] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:750] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:750] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f764a08> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 26  :List of 14
  ..$ coefficients : Named num [1:370] 5474.1 1.03 116.14 -723.8 -1206.46 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:782] from 1 to 3.14: 84.3 -306.5 749.9 991.8 2138.9 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:782] -186569 8035 2217 729 -410 ...
  .. ..- attr(*, "names")= chr [1:782] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:782] from 1 to 3.14: 5866 5960 5099 4137 7969 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:782, 1:370] -27.9643 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:782] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 413
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f2d3400> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	782 obs. of  7 variables:
  .. ..$ Sales        : int [1:782] 5950 5654 5849 5129 10108 7450 7124 6818 7223 5310 ...
  .. ..$ trend        : int [1:782] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:782] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:782] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:782] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:782] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29f2d3400> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 27  :List of 14
  ..$ coefficients : Named num [1:370] 9330.618 0.863 -1045.051 -1052.571 -1048.436 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -328 224 986 1411 2958 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -264552 8885 -751 -268 -1072 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 9002 7669 7375 6558 12636 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b4f4c08> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 8674 7893 8361 7969 15594 11608 9803 10434 11571 8046 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b4f4c08> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 28  :List of 14
  ..$ coefficients : Named num [1:370] 6397.36 -1.05 -607.74 -788.74 -1513.19 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:768] from 1 to 3.1: -796 563 1359 -287 1792 ...
  .. ..- attr(*, "names")= chr [1:768] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:768] -147259 -6057 527 -1875 -2768 ...
  .. ..- attr(*, "names")= chr [1:768] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:768] from 1 to 3.1: 5754 4724 4122 2357 8334 ...
  .. ..- attr(*, "names")= chr [1:768] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:768, 1:370] -27.7128 0.0361 0.0361 0.0361 0.0361 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:768] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.04 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 399
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b629148> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	768 obs. of  7 variables:
  .. ..$ Sales        : int [1:768] 4958 5287 5481 2070 10126 7892 6632 6179 6630 2401 ...
  .. ..$ trend        : int [1:768] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:768] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:768] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:768] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:768] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b629148> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 29  :List of 14
  ..$ coefficients : Named num [1:370] 6754.91 3.42 -1598.1 -1659.38 -2306.48 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1025.1 -31.6 997.1 1785.1 2883.7 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -205555 23314 -812 -725 -1978 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 6294 4586 4414 3779 7912 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e8bd6a8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 5269 4554 5411 5564 10796 7235 5721 6590 7061 5518 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e8bd6a8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 30  :List of 14
  ..$ coefficients : Named num [1:370] 5889.91 -3.04 -137.5 -471.34 -490.78 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: 31.3 817 79 910.8 1135.6 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -147591 -17070 -634 -1405 -1688 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 5652 5402 4956 4732 8038 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b8f79f8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 5683 6219 5035 5643 9174 8705 5718 7957 6182 5131 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b8f79f8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 31  :List of 14
  ..$ coefficients : Named num [1:370] 5031.757 0.358 479.261 -176.146 -277.776 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -221 -246 880 573 1581 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -164148 3206 925 599 406 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 5343 5869 5260 5034 6276 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d27a8d0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5122 5623 6140 5607 7857 6480 6335 6066 7314 5033 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d27a8d0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 32  :List of 14
  ..$ coefficients : Named num [1:370] 3580.487 0.705 53.471 365.115 -178.652 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:621] from 1 to 2.7: 661.3 -109.2 236.1 17.4 681.2 ...
  .. ..- attr(*, "names")= chr [1:621] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:621] -101370 2898 -603 -1846 -2023 ...
  .. ..- attr(*, "names")= chr [1:621] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:621] from 1 to 2.7: 3007 2785 2822 1751 5892 ...
  .. ..- attr(*, "names")= chr [1:621] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:621, 1:370] -24.9199 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:621] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 252
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa282321b50> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	621 obs. of  7 variables:
  .. ..$ Sales        : int [1:621] 3668 2676 3058 1768 6573 5410 5277 4292 4414 1913 ...
  .. ..$ trend        : int [1:621] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:621] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:621] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:621] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:621] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa282321b50> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 33  :List of 14
  ..$ coefficients : Named num [1:370] 8173.402 -0.412 -408.967 -415.038 -1293.316 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: 520 -51.2 372.8 1069.5 2050.6 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -235472 -1648 226 116 -1334 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 8390 8038 8089 7224 9429 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa275ad4ab0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 8910 7987 8462 8293 11480 10678 7791 9322 8295 9339 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa275ad4ab0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 34  :List of 14
  ..$ coefficients : Named num [1:370] 8406.195 0.776 -76.508 -87.016 -750.77 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -54.3 -738.4 -577.5 865.2 2150.5 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -224882 4876 1094 2334 1058 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 7820 7608 7463 6842 9617 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bee8b48> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 7766 6870 6885 7707 11768 8576 8224 7667 8123 7045 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bee8b48> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 35  :List of 14
  ..$ coefficients : Named num [1:370] 8797.17 3.34 -1724.8 -1847.36 -2204.64 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1833 -417 875 2046 2552 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -270818 23378 -1399 -1168 -2434 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 8352 6372 5993 5051 11984 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bbb2d40> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 6519 5955 6868 7097 14536 11508 10066 9909 9946 7284 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bbb2d40> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 36  :List of 14
  ..$ coefficients : Named num [1:370] 7790.767 0.963 -1068.096 -719.193 145.29 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 1526 637 210 -318 220 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -233528 5281 -2186 -1659 -1318 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 7807 6770 7151 8124 10109 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29baa59c0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 9333 7407 7361 7806 10329 8902 9645 8494 8956 8545 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29baa59c0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 37  :List of 14
  ..$ coefficients : Named num [1:370] 5739.745 -0.822 -1797.273 -1431.477 -1046.143 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: -181 921 298 1787 887 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -198688 -3571 -406 -422 -803 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 7550 6160 6932 7135 6908 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:370] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 411
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c5b3550> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  7 variables:
  .. ..$ Sales        : int [1:780] 7369 7081 7230 8922 7795 7143 6760 7900 7967 8828 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:780] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c5b3550> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 38  :List of 14
  ..$ coefficients : Named num [1:370] 5591.566 0.541 -849.6 -1456.54 -1534.005 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1049 -746 26 962 2482 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -167593 4261 -161 -1277 -1273 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 5555 4741 4170 4271 7256 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2774024b0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4506 3995 4196 5233 9738 6773 6224 6155 5890 5347 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2774024b0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 39  :List of 14
  ..$ coefficients : Named num [1:370] 4845.14 1.08 -775.79 -811.08 -1016.22 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: 93.3 598.5 1057.3 687 2018 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -135438 10204 -1467 -932 -2039 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 4051 2928 2547 1748 7118 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29cb12e70> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4144 3527 3604 2435 9136 5510 4154 5120 4766 2398 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29cb12e70> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 40  :List of 14
  ..$ coefficients : Named num [1:370] 4152.315 -0.631 -313.221 -593.442 124.606 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:776] from 1 to 3.12: -74.3 -32 -51.7 541.5 900.4 ...
  .. ..- attr(*, "names")= chr [1:776] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:776] -136563 -4002 -786 -1083 -432 ...
  .. ..- attr(*, "names")= chr [1:776] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:776] from 1 to 3.12: 4746 4543 4373 4938 5835 ...
  .. ..- attr(*, "names")= chr [1:776] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:776, 1:370] -27.8568 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:776] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 407
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa280cdca00> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	776 obs. of  7 variables:
  .. ..$ Sales        : int [1:776] 4672 4511 4321 5479 6735 5524 4498 5685 4882 4867 ...
  .. ..$ trend        : int [1:776] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:776] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:776] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:776] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:776] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa280cdca00> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 41  :List of 14
  ..$ coefficients : Named num [1:370] 3036.11 3.91 -743.42 -428.34 338.48 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 380.3 757.3 693.8 -23.3 -689.5 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -133056 16358 -692 -113 -291 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 4081 3437 3851 3963 5528 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c294950> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 4461 4194 4545 3940 4839 4860 4128 4303 4044 4219 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c294950> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 42  :List of 14
  ..$ coefficients : Named num [1:370] 9175.75 1.58 -1570.66 -336.32 -1046.25 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -632 145 498 900 2494 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -284078 12715 -2974 -425 -2158 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 8591 6780 7775 6687 12243 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c0d88d8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 7959 6925 8273 7587 14737 12216 10569 10298 10841 7648 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c0d88d8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 43  :List of 14
  ..$ coefficients : Named num [1:370] 7527.7 -0.983 -854.056 -148.466 -981.48 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -500 204 400 437 1901 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -190431 -4696 -1319 424 -1616 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 6743 5586 5989 4730 10317 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b7b2238> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 6243 5790 6389 5167 12218 8600 7918 8132 8246 5308 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b7b2238> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 44  :List of 14
  ..$ coefficients : Named num [1:370] 5670.204 0.325 -168.602 262.129 -290.668 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -131.6 -493.9 -88.5 -34.3 2165.3 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -153398 2795 -280 2221 795 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 4798 4347 4496 3686 7653 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d0b0a38> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 4666 3853 4407 3652 9818 6149 6284 5397 6699 3195 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d0b0a38> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 45  :List of 14
  ..$ coefficients : Named num [1:370] 4.48e+03 2.55e-02 -4.22e+02 -7.64e+02 -1.15e+03 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -801 -452 339 1200 747 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -149278.8 707.9 43.6 -848.4 -1259.2 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 5071 4820 4649 4366 5869 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274d55f10> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4270 4368 4988 5566 6616 5518 5235 5955 5868 5455 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274d55f10> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 46  :List of 14
  ..$ coefficients : Named num [1:370] 3540.92 1.15 -489.52 -467.55 711.39 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 200 793 661 253 1035 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -133486 4587 -700 -592 -601 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 3816 3384 3464 4595 6753 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281b3ef88> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 4016 4177 4125 4848 7788 5793 5501 5503 5985 4857 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281b3ef88> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 47  :List of 14
  ..$ coefficients : Named num [1:370] 7000.9 1.4 37.1 -646.9 -449.4 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 603 487 812 686 1291 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -200063 10231 232 784 838 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 5935 5712 4768 4987 8590 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d1615b8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 6538 6199 5580 5673 9881 8729 9057 7493 7409 5021 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d1615b8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 48  :List of 14
  ..$ coefficients : Named num [1:370] 4670.48 -1.27 379.02 226.39 -455.11 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 192 -134 344 135 1068 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -110179 -6269 532 1147 -123 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 3899 4123 3814 3283 5650 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2856341b8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 4091 3989 4158 3418 6718 5460 4393 4657 4648 3831 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2856341b8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 49  :List of 14
  ..$ coefficients : Named num [1:370] 4807.74 1.91 -1039.09 -898.52 -374.02 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: -137 -462 -94.6 786.6 904.6 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -203600 12770 -2492 -2053 -1432 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 6003 5084 5345 5150 7826 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2733da548> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 5866 4622 5250 5937 8731 7290 6532 6399 7062 6127 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2733da548> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 50  :List of 14
  ..$ coefficients : Named num [1:370] 4012.952 0.534 -977.56 -1088.535 -1073.341 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -521 -28.2 390 1028.9 1322.1 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -118789 4050 -216 -528 -447 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 4325 3416 3374 3351 4976 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28a027590> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 3804 3388 3764 4380 6298 4734 3615 4176 4608 4395 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28a027590> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 51  :List of 14
  ..$ coefficients : Named num [1:370] 3382.79 2.24 -759.5 331.5 1265.2 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 592.7 468.2 798.2 59.5 646.8 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -166481 9593 -1614 372 770 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 4559 4117 5525 6545 7478 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa284899540> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 5152 4585 6323 6605 8125 6233 4729 6503 7322 6079 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa284899540> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 52  :List of 14
  ..$ coefficients : Named num [1:370] 5916.12 -2.52 -307.73 -61.96 1186.96 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 115 -110 -294 -813 -650 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -184754 -9669 -499 67 -162 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 7061 6906 7305 8024 10578 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa280f7bee0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 7176 6796 7011 7211 9928 8195 7530 7311 8929 8003 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa280f7bee0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 53  :List of 14
  ..$ coefficients : Named num [1:370] 5560.739 0.483 112.779 -695.442 -733.685 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 262 -218 756 -135 1383 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -147414.6 4147.8 685.3 668.9 61.2 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 5105 4985 3945 3433 6947 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d4bd6d8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5367 4767 4701 3298 8330 5576 5241 5640 5283 3510 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d4bd6d8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 54  :List of 14
  ..$ coefficients : Named num [1:371] 4992.91 0.42 1953.21 1872.32 485.66 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:785] from 1 to 3.15: 318 -2301 -1550 578 1049 ...
  .. ..- attr(*, "names")= chr [1:785] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:785] -221552 4328 2752 2589 779 ...
  .. ..- attr(*, "names")= chr [1:785] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:785] from 1 to 3.15: 6550 8932 9280 8050 7970 ...
  .. ..- attr(*, "names")= chr [1:785] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:785, 1:371] -28.0179 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:785] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c0b5308> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	785 obs. of  8 variables:
  .. ..$ Sales        : int [1:785] 6868 6631 7730 8628 9019 7571 7556 7181 7831 9073 ...
  .. ..$ trend        : int [1:785] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:785] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:785] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:785] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:785] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c0b5308> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 55  :List of 14
  ..$ coefficients : Named num [1:371] 5173.76 1.73 -716.83 -935.19 -1274.83 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: 269 629 1701 1265 1112 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -128443 13042 1469 -470 -603 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 4247 3402 2921 2318 6052 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:371] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29a79f038> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  8 variables:
  .. ..$ Sales        : int [1:780] 4516 4031 4622 3583 7164 6212 6439 6454 5619 3652 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:780] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29a79f038> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 56  :List of 14
  ..$ coefficients : Named num [1:370] 4633.33 3.24 882.83 -226.55 -413.52 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:781] from 1 to 3.14: 227.1 69.9 335.9 501.6 2427.7 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:781] -204617 19373 2419 1119 212 ...
  .. ..- attr(*, "names")= chr [1:781] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:781] from 1 to 3.14: 5488 6640 5800 5882 6526 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:781, 1:370] -27.9464 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:781] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 412
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274d4c978> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	781 obs. of  7 variables:
  .. ..$ Sales        : int [1:781] 5715 6710 6136 6384 8954 8523 6931 6999 7030 7210 ...
  .. ..$ trend        : int [1:781] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:781] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:781] 1 1 1 1 1 1 1 1 1 0 ...
  .. ..$ Promo        : int [1:781] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:781] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274d4c978> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 57  :List of 14
  ..$ coefficients : Named num [1:371] 13271.48 -4.29 -1560 -1719.65 -1963.46 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:769] from 1 to 3.1: -381.9 441.4 1378.4 55.5 3372.4 ...
  .. ..- attr(*, "names")= chr [1:769] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:769] -294100 -22765 419 -793 -4388 ...
  .. ..- attr(*, "names")= chr [1:769] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:769] from 1 to 3.1: 11101 9547 8844 8056 15942 ...
  .. ..- attr(*, "names")= chr [1:769] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:769, 1:371] -27.7308 0.0361 0.0361 0.0361 0.0361 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:769] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.04 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 399
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bb63278> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	769 obs. of  8 variables:
  .. ..$ Sales        : int [1:769] 10719 9988 10222 8112 19314 14203 11842 12947 12230 7309 ...
  .. ..$ trend        : int [1:769] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:769] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:769] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:769] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:769] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bb63278> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 58  :List of 14
  ..$ coefficients : Named num [1:371] 3990.55 3.77 -256.61 -444.72 -27.6 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:623] from 1 to 2.7: 633 502 1120 832 702 ...
  .. ..- attr(*, "names")= chr [1:623] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:623] -158150 16600 -764 -1119 -519 ...
  .. ..- attr(*, "names")= chr [1:623] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:623] from 1 to 2.7: 3676 3363 3119 3620 7737 ...
  .. ..- attr(*, "names")= chr [1:623] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:623, 1:371] -24.96 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:623] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bc2d5c8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	623 obs. of  8 variables:
  .. ..$ Sales        : int [1:623] 4309 3865 4239 4452 8439 6704 5385 5833 5863 4585 ...
  .. ..$ trend        : int [1:623] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:623] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:623] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:623] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:623] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bc2d5c8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 59  :List of 14
  ..$ coefficients : Named num [1:370] 6306.9829 0.0422 78.3687 555.1582 -138.5296 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:782] from 1 to 3.14: 202 209 873 -540 1022 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:782] -153840 2433 1734 1629 -676 ...
  .. ..- attr(*, "names")= chr [1:782] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:782] from 1 to 3.14: 4975 4513 4449 2924 7722 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:782, 1:370] -27.9643 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:782] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 413
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29440bc68> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	782 obs. of  7 variables:
  .. ..$ Sales        : int [1:782] 5177 4722 5322 2384 8744 6252 6991 5798 5963 2273 ...
  .. ..$ trend        : int [1:782] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:782] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:782] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:782] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:782] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29440bc68> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 60  :List of 14
  ..$ coefficients : Named num [1:371] 7978 2.8 -709.4 -900.7 -1904 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: 511 602 1554 688 678 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -224352 20421 1097 -2166 -2971 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 6248 5095 4362 2817 9666 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:371] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bb846a0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  8 variables:
  .. ..$ Sales        : int [1:780] 6759 5697 5916 3505 10344 8969 7225 7500 6717 3870 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:780] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bb846a0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 61  :List of 14
  ..$ coefficients : Named num [1:370] 3422.72 1.98 -987.09 -138.52 -282.29 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: 451 418 -142 736 345 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -131625 13406 -1679 -202 -637 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 3782 2803 3660 3187 4782 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28112cb18> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 4233 3221 3518 3923 5127 3982 3727 4144 4125 4115 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28112cb18> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 62  :List of 14
  ..$ coefficients : Named num [1:370] 7844.625 0.407 -1132.576 -653.985 -1245.163 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -7.7 434.1 604.8 -325.1 639.9 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -181527 4466 -1403 274 -1672 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 6492 4869 4857 3657 9172 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29aee8190> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 6484 5303 5462 3332 9812 8443 6253 6760 6806 3690 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29aee8190> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 63  :List of 14
  ..$ coefficients : Named num [1:370] 5250.12 1.89 -22.98 -310.29 -1024.43 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -858 -1255 -437 804 2009 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -194779 13079 988 1433 567 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 5910 6104 6035 5528 6344 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d47e3c8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5052 4849 5598 6332 8353 6412 6356 6734 7612 6279 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d47e3c8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 64  :List of 14
  ..$ coefficients : Named num [1:370] 7713.39 3.64 -2141.92 -1848.41 -2445.59 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1482.3 -17.5 -45.1 863.7 971.3 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -289140 25854 -1641 -1579 -2538 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 9092 7208 7758 6803 9853 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2815c3fb8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 7610 7190 7713 7667 10824 8735 8092 9395 8922 8473 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2815c3fb8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 65  :List of 14
  ..$ coefficients : Named num [1:370] 5082.408 0.388 -171.267 -565.121 -886.172 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: 223.2 -96.8 1105.8 -192.1 162.3 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -142795 4629 770 -1704 -1940 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 4515 4046 3354 2409 6452 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:370] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 411
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274e2aea8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  7 variables:
  .. ..$ Sales        : int [1:780] 4738 3949 4460 2217 6614 6777 4716 4987 5976 2747 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:780] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274e2aea8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 66  :List of 14
  ..$ coefficients : Named num [1:370] 4465.616 0.574 -280.869 -154.072 155.778 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: -318.2 -64.2 798.1 940.5 930.9 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -170436 4048 -1168 -723 -218 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 5311 5163 5423 5417 6936 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa286a59270> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 4993 5099 6221 6358 7867 6431 5659 6281 7734 5643 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa286a59270> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 67  :List of 14
  ..$ coefficients : Named num [1:370] 7427.405 0.938 -152.744 -269.154 -402.57 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: 1417 522 1257 857 1487 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -218229 8216 -305 -1212 -2421 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 6679 6122 5602 4599 10876 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28a4a2c08> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 8096 6644 6859 5456 12363 9451 8946 7888 8085 5115 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28a4a2c08> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 68  :List of 14
  ..$ coefficients : Named num [1:370] 6489.58 1.86 -507.64 -2048.62 -1081.51 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 8.31 -887.46 -361.9 193.15 741.03 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -211771 11709 468 -2179 -507 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 7661 7350 6007 6589 6171 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b92f8a8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 7669 6463 5645 6782 6912 6379 6083 5957 6347 6376 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b92f8a8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 69  :List of 14
  ..$ coefficients : Named num [1:370] 9003.619 -0.698 234.982 344.703 -1604.55 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:781] from 1 to 3.14: 74.26 1.74 -266.52 -291.8 1135.77 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:781] -263435 -3947 2575 2609 -2439 ...
  .. ..- attr(*, "names")= chr [1:781] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:781] from 1 to 3.14: 9829 9991 10029 8007 12129 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:781, 1:370] -27.9464 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:781] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 412
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d7be380> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	781 obs. of  7 variables:
  .. ..$ Sales        : int [1:781] 9903 9993 9762 7715 13265 11677 10233 9000 10349 7665 ...
  .. ..$ trend        : int [1:781] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:781] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:781] 1 1 1 1 1 1 1 1 1 0 ...
  .. ..$ Promo        : int [1:781] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:781] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29d7be380> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 70  :List of 14
  ..$ coefficients : Named num [1:370] 6501.813 0.487 221.586 229.506 -180.124 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:782] from 1 to 3.14: -73.3 -860.2 -296.4 471.5 1423.6 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:782] -184789 4637 1039 2531 1385 ...
  .. ..- attr(*, "names")= chr [1:782] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:782] from 1 to 3.14: 6236 6329 6208 5548 8635 ...
  .. ..- attr(*, "names")= chr [1:782] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:782, 1:370] -27.9643 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:782] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 413
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29aec7a30> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	782 obs. of  7 variables:
  .. ..$ Sales        : int [1:782] 6163 5469 5912 6020 10059 7520 6778 6022 6776 5928 ...
  .. ..$ trend        : int [1:782] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:782] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:782] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:782] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:782] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29aec7a30> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 71  :List of 14
  ..$ coefficients : Named num [1:370] 9110.471 0.487 -1393.836 -1474.408 -1913.061 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1713 134 953 1554 1925 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -252900 5259 -1288 -1002 -2424 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 8754 7112 6784 5709 11709 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2829d1918> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 7041 7246 7737 7263 13634 10289 9952 9819 11501 7841 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2829d1918> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 72  :List of 14
  ..$ coefficients : Named num [1:371] 4703.67 0.79 -1272.57 -654.63 -969.72 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:623] from 1 to 2.7: -181 238 826 189 1017 ...
  .. ..- attr(*, "names")= chr [1:623] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:623] -110324 2987 -1004 -628 -1620 ...
  .. ..- attr(*, "names")= chr [1:623] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:623] from 1 to 2.7: 3724 2103 2372 1642 7369 ...
  .. ..- attr(*, "names")= chr [1:623] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:623, 1:371] -24.96 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:623] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274f416a8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	623 obs. of  8 variables:
  .. ..$ Sales        : int [1:623] 3543 2341 3198 1831 8386 5765 5079 4258 4311 2075 ...
  .. ..$ trend        : int [1:623] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:623] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:623] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:623] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:623] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa274f416a8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 73  :List of 14
  ..$ coefficients : Named num [1:370] 4830.9 0.57 262.41 164.83 -303.08 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -67.8 216 703.8 -64.5 594 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -128155.4 5208.5 -78.1 1217.7 -180.7 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 3760 3674 3228 2437 5805 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa292a83bf8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 3692 3890 3932 2373 6399 5342 4519 5197 4387 2297 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa292a83bf8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 74  :List of 14
  ..$ coefficients : Named num [1:370] 6.11e+03 -5.97e-03 -5.47e+02 -7.20e+02 -7.36e+01 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:776] from 1 to 3.12: 1151.06 262.73 507.06 9.88 1043.97 ...
  .. ..- attr(*, "names")= chr [1:776] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:776] -174290 1815 -1167 -1862 -2608 ...
  .. ..- attr(*, "names")= chr [1:776] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:776] from 1 to 3.12: 5753 4980 4583 4682 8371 ...
  .. ..- attr(*, "names")= chr [1:776] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:776, 1:370] -27.8568 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:776] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 407
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bee9d08> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	776 obs. of  7 variables:
  .. ..$ Sales        : int [1:776] 6904 5243 5090 4692 9415 8134 5800 7331 6461 5312 ...
  .. ..$ trend        : int [1:776] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:776] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:776] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:776] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:776] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28bee9d08> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 75  :List of 14
  ..$ coefficients : Named num [1:370] 5228.41 1.06 204.42 -55.82 -966.43 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: 222 -580 228 942 1530 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -168657 6744 694 745 -911 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 5622 5870 5654 4522 5368 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28069ae78> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5844 5290 5882 5464 6898 5843 5054 5258 5680 4827 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28069ae78> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 76  :List of 14
  ..$ coefficients : Named num [1:371] 7617.29 2.06 -1651.66 -1645.83 -2090.61 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:623] from 1 to 2.7: 1515 726 1430 1099 1561 ...
  .. ..- attr(*, "names")= chr [1:623] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:623] -224628 8342 -1116 -1047 -2015 ...
  .. ..- attr(*, "names")= chr [1:623] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:623] from 1 to 2.7: 8322 6719 6773 5815 10750 ...
  .. ..- attr(*, "names")= chr [1:623] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:623, 1:371] -24.96 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:623] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e620070> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	623 obs. of  8 variables:
  .. ..$ Sales        : int [1:623] 9837 7445 8203 6914 12311 8321 9005 8112 9093 7813 ...
  .. ..$ trend        : int [1:623] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:623] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:623] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:623] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:623] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e620070> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 77  :List of 14
  ..$ coefficients : Named num [1:370] 5966.29 1.71 -103.23 -179.78 -811.3 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:781] from 1 to 3.14: 48.4 -1195.5 -149 477.4 1843 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:781] -212993 11385 1791 1869 -616 ...
  .. ..- attr(*, "names")= chr [1:781] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:781] from 1 to 3.14: 6525 6511 6525 5984 8507 ...
  .. ..- attr(*, "names")= chr [1:781] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:781, 1:370] -27.9464 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:781] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 412
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281078778> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	781 obs. of  7 variables:
  .. ..$ Sales        : int [1:781] 6573 5316 6376 6461 10350 7535 7781 6968 6881 7130 ...
  .. ..$ trend        : int [1:781] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:781] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:781] 1 1 1 1 1 1 1 1 1 0 ...
  .. ..$ Promo        : int [1:781] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:781] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281078778> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 78  :List of 14
  ..$ coefficients : Named num [1:370] 3108.401 0.387 13.289 -282.755 -307.234 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: 162 179 636 388 602 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -103823 3824 373 -1216 -1151 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 2913 2815 2407 2133 4579 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:370] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 411
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2874c36a0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  7 variables:
  .. ..$ Sales        : int [1:780] 3075 2994 3043 2521 5181 3712 3556 3583 3860 2797 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:780] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2874c36a0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 79  :List of 14
  ..$ coefficients : Named num [1:370] 4802.751 0.652 -425.041 -338.081 -308.188 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:777] from 1 to 3.13: 377 215 550 425 805 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:777] -152593 5600 -1154 -1401 -1938 ...
  .. ..- attr(*, "names")= chr [1:777] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:777] from 1 to 3.13: 4450 3799 3660 3138 7639 ...
  .. ..- attr(*, "names")= chr [1:777] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:777, 1:370] -27.8747 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:777] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b8f62d8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	777 obs. of  7 variables:
  .. ..$ Sales        : int [1:777] 4827 4014 4210 3563 8444 6286 5261 4996 5329 3494 ...
  .. ..$ trend        : int [1:777] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:777] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:777] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:777] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:777] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b8f62d8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 80  :List of 14
  ..$ coefficients : Named num [1:370] 6675.59 1.03 -1084.63 -1821.32 -1783.67 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1906 -793 299 1690 2684 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -212575 7830 315 -1419 -865 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 7401 6580 6108 6476 8293 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2824f22a8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 5495 5787 6407 8166 10977 8213 7002 7530 7822 7249 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2824f22a8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 81  :List of 14
  ..$ coefficients : Named num [1:370] 5519.24 2.14 -1786.66 -535.82 110.25 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 1452 731 348 -518 755 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -174223 9796 -2157 -113 707 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 5729 4143 5595 6829 7791 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27a57f178> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 7181 4874 5943 6311 8546 6574 6743 5781 6984 7537 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27a57f178> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 82  :List of 14
  ..$ coefficients : Named num [1:370] 9793.159 0.672 -1920.953 -1786.48 -2111.577 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -1210 1232 1189 424 1817 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -251744 7158 -1478 -583 -2176 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 9257 6952 6703 5375 12828 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27bbb4d18> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 8047 8184 7892 5799 14645 11770 10794 10918 10660 5289 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27bbb4d18> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 83  :List of 14
  ..$ coefficients : Named num [1:370] 4311.213 0.172 -804.076 -728.939 -1047.746 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: 209.7 87.9 333 83 676.1 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -108508 1719 -687 -358 -1074 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 3892 2972 2931 2566 5070 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c765920> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4102 3060 3264 2649 5746 4773 4631 4298 4776 2954 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c765920> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 84  :List of 14
  ..$ coefficients : Named num [1:370] 13804.95 1.42 -2311.1 -1862.64 -2693.99 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -117.9 79.6 1016.5 1286.1 3503.2 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -361609 11445 -1702 -315 -2425 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 12827 10162 10258 8988 16079 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28b198e98> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 12709 10242 11274 10274 19582 15019 12951 12981 13462 10406 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28b198e98> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 85  :List of 14
  ..$ coefficients : Named num [1:373] -6039.705 0.336 9172.827 8007.216 8787.272 ...
  .. ..- attr(*, "names")= chr [1:373] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:942] from 1 to 3.58: 720 716 354 -1037 -2766 ...
  .. ..- attr(*, "names")= chr [1:942] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:942] -223206 4548 -1797 -2667 -164 ...
  .. ..- attr(*, "names")= chr [1:942] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 371
  ..$ fitted.values: Time-Series [1:942] from 1 to 3.58: 3500 5353 4892 6376 8540 ...
  .. ..- attr(*, "names")= chr [1:942] "1" "2" "3" "4" ...
  ..$ assign       : int [1:373] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:942, 1:373] -30.692 0.0326 0.0326 0.0326 0.0326 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:942] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:373] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:373] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:373] 1.03 1.05 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:373] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 371
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 571
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:4] "0" "a" "b" "c"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27c8ece60> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	942 obs. of  8 variables:
  .. ..$ Sales        : int [1:942] 4220 6069 5246 5339 5774 10509 8990 7300 6523 7434 ...
  .. ..$ trend        : int [1:942] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:942] 2 3 4 5 6 7 1 2 3 4 ...
  .. ..$ StateHoliday : Factor w/ 4 levels "0","a","b","c": 2 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:942] 1 1 1 1 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:942] 0 0 0 0 0 0 1 1 1 1 ...
  .. ..$ Promo2       : int [1:942] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa27c8ece60> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 86  :List of 14
  ..$ coefficients : Named num [1:370] 4456.946 0.201 -540.517 -710.069 -922.609 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:778] from 1 to 3.13: -318 -545 -168 306 785 ...
  .. ..- attr(*, "names")= chr [1:778] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:778] -130957 3286 -168 -623 -1367 ...
  .. ..- attr(*, "names")= chr [1:778] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:778] from 1 to 3.13: 4548 3916 3655 2983 5838 ...
  .. ..- attr(*, "names")= chr [1:778] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:778, 1:370] -27.8927 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:778] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 409
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bb14c28> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	778 obs. of  7 variables:
  .. ..$ Sales        : int [1:778] 4230 3371 3487 3289 6623 5631 4334 4739 4530 3505 ...
  .. ..$ trend        : int [1:778] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:778] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:778] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:778] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:778] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29bb14c28> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 87  :List of 14
  ..$ coefficients : Named num [1:370] 7.58e+03 8.08e-02 -7.10e+02 -6.79e+02 -1.34e+03 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:784] from 1 to 3.15: -413 206.7 70.1 -330 1954.9 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:784] -164225 961 -452 1518 -531 ...
  .. ..- attr(*, "names")= chr [1:784] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:784] from 1 to 3.15: 6049 4821 4335 3140 8297 ...
  .. ..- attr(*, "names")= chr [1:784] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:784, 1:370] -28 0.0357 0.0357 0.0357 0.0357 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:784] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 415
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa285fb8150> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	784 obs. of  7 variables:
  .. ..$ Sales        : int [1:784] 5636 5028 4405 2810 10252 7522 6396 5820 7238 2772 ...
  .. ..$ trend        : int [1:784] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:784] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:784] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:784] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:784] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa285fb8150> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 88  :List of 14
  ..$ coefficients : Named num [1:370] 7128.325 0.124 85.719 -118.435 -1119.929 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: 108.66 997.99 1420.2 -9.83 622.21 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -168253 2789 1348 -1945 -2564 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 5180 4578 3686 1880 9429 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:370] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 411
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281cffdc8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  7 variables:
  .. ..$ Sales        : int [1:780] 5289 5576 5106 1870 10051 8485 7137 6776 6704 2003 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:780] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281cffdc8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 89  :List of 14
  ..$ coefficients : Named num [1:370] 6336.283 0.756 -1238.873 -60.246 -1113.981 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 1048 935 220 -312 893 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -148925 3511 -1390 -125 -3124 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 5587 4067 4965 3537 8067 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2818ef270> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 6635 5002 5185 3225 8960 7443 7057 5772 6393 3470 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2818ef270> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 90  :List of 14
  ..$ coefficients : Named num [1:370] 7460.71 0.94 -466.37 -912.88 -644.86 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:778] from 1 to 3.13: 790 -195 462 948 1194 ...
  .. ..- attr(*, "names")= chr [1:778] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:778] -234766 7308 -555 -1467 -1282 ...
  .. ..- attr(*, "names")= chr [1:778] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:778] from 1 to 3.13: 7466 6922 6399 6351 9890 ...
  .. ..- attr(*, "names")= chr [1:778] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:778, 1:370] -27.8927 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:778] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 409
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b5a7718> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	778 obs. of  7 variables:
  .. ..$ Sales        : int [1:778] 8256 6727 6861 7299 11084 8981 7087 7574 7970 7100 ...
  .. ..$ trend        : int [1:778] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:778] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:778] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:778] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:778] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b5a7718> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 91  :List of 14
  ..$ coefficients : Named num [1:371] 4819.979 -0.719 -75.789 -277.229 5.67 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:778] from 1 to 3.13: -432.7 -1246.7 -813.1 -69.7 372.1 ...
  .. ..- attr(*, "names")= chr [1:778] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:778] -155055 -3263 -650 -1126 -1294 ...
  .. ..- attr(*, "names")= chr [1:778] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:778] from 1 to 3.13: 5520 5372 5098 4394 7280 ...
  .. ..- attr(*, "names")= chr [1:778] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:778, 1:371] -27.8927 0.0359 0.0359 0.0359 0.0359 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:778] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 408
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b46aed0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	778 obs. of  8 variables:
  .. ..$ Sales        : int [1:778] 5087 4125 4285 4324 7652 6758 5861 5239 5835 4395 ...
  .. ..$ trend        : int [1:778] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:778] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:778] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:778] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:778] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b46aed0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 92  :List of 14
  ..$ coefficients : Named num [1:370] 3818.65 1.78 -321.44 -46.77 -528.43 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: 164 475 958 1301 2639 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -167371 12249 -1312 -887 -1717 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 3965 3673 3976 3458 7046 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e8d4d20> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 4129 4148 4934 4759 9685 6620 6452 5888 5545 5437 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29e8d4d20> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 93  :List of 14
  ..$ coefficients : Named num [1:370] 6746.62 -0.35 -946.75 -637.27 -1542.57 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -862 909 1085 -148 372 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -166491 315 -832 236 -2193 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 6382 5127 5128 3355 9022 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b96aee8> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 5520 6036 6213 3207 9394 7385 6712 6605 8189 3565 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29b96aee8> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 94  :List of 14
  ..$ coefficients : Named num [1:370] 6972.885 0.832 -1047.498 -1114.586 -1661.755 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -754 413 690 939 2050 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -198755 7221 -1140 -889 -2365 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 6589 5328 5047 4027 9698 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28757fb58> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 5835 5741 5737 4966 11748 9091 7425 7423 7299 5653 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa28757fb58> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 95  :List of 14
  ..$ coefficients : Named num [1:371] 9635.21 -1.27 -1093.36 -1504.37 -2274.91 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: -344 114 1260 486 848 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -213333 -6410 858 -2541 -2964 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 8114 6408 5463 4158 11137 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:371] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa293164028> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  8 variables:
  .. ..$ Sales        : int [1:780] 7770 6522 6723 4644 11985 10371 9232 8809 7882 4119 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:780] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa293164028> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 96  :List of 14
  ..$ coefficients : Named num [1:371] 6008.336 0.587 -297.486 -404.939 -912.141 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: -202 974 1584 131 999 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -144583 5896 511 -2412 -2190 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 4201 3148 2400 1253 7979 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:371] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2739752e0> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  8 variables:
  .. ..$ Sales        : int [1:780] 3999 4122 3984 1384 8978 7028 6511 6255 5667 1461 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:780] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa2739752e0> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 97  :List of 14
  ..$ coefficients : Named num [1:371] 7032.359 0.864 -779.942 -958.867 -1523.393 ...
  .. ..- attr(*, "names")= chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:780] from 1 to 3.13: -258 1131 1484 441 1636 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:780] -187216 7554 715 -1755 -2138 ...
  .. ..- attr(*, "names")= chr [1:780] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 370
  ..$ fitted.values: Time-Series [1:780] from 1 to 3.13: 5993 4861 4334 3422 9032 ...
  .. ..- attr(*, "names")= chr [1:780] "1" "2" "3" "4" ...
  ..$ assign       : int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:780, 1:371] -27.9285 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:780] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:371] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:371] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 2
  .. .. .. ..$ season      : chr "contr.treatment"
  .. .. .. ..$ StateHoliday: chr "contr.treatment"
  .. ..$ qraux: num [1:371] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:371] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 370
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 2
  .. ..$ season      : chr "contr.treatment"
  .. ..$ StateHoliday: chr "contr.treatment"
  ..$ xlevels      :List of 2
  .. ..$ season      : chr [1:365] "1" "2" "3" "4" ...
  .. ..$ StateHoliday: chr [1:2] "0" "a"
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday +      Promo + Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c9cc670> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	780 obs. of  8 variables:
  .. ..$ Sales        : int [1:780] 5735 5992 5818 3863 10668 7737 6864 8052 7540 4087 ...
  .. ..$ trend        : int [1:780] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:780] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ StateHoliday : Factor w/ 2 levels "0","a": 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ SchoolHoliday: num [1:780] 1 0 0 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:780] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:780] 0 0 0 0 0 0 0 0 0 0 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + StateHoliday + SchoolHoliday + Promo +      Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:8, 1:7] 0 1 0 0 0 0 0 0 0 0 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:7] "trend" "season" "DayOfWeek" "StateHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:7] 1 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa29c9cc670> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, StateHoliday, SchoolHoliday, Promo,      Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:8] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:8] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 98  :List of 14
  ..$ coefficients : Named num [1:370] 3650.04 1.78 -565.5 -615.45 -638.94 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:779] from 1 to 3.13: -918 -110 219 858 1230 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:779] -142619 12267 -704 -917 -968 ...
  .. ..- attr(*, "names")= chr [1:779] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:779] from 1 to 3.13: 4087 3593 3616 3441 5176 ...
  .. ..- attr(*, "names")= chr [1:779] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:779, 1:370] -27.9106 0.0358 0.0358 0.0358 0.0358 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:779] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.06 1.03 1.02 1.01 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 410
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa289857068> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	779 obs. of  7 variables:
  .. ..$ Sales        : int [1:779] 3169 3483 3835 4299 6406 4649 4002 4569 4659 3975 ...
  .. ..$ trend        : int [1:779] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:779] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:779] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:779] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:779] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa289857068> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
 $ 99  :List of 14
  ..$ coefficients : Named num [1:370] 3291.57 3.02 -1483.78 -1052.57 128.32 ...
  .. ..- attr(*, "names")= chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  ..$ residuals    : Time-Series [1:622] from 1 to 2.7: 621 977 945 120 774 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ effects      : Named num [1:622] -127955 13355 -1593 -860 -335 ...
  .. ..- attr(*, "names")= chr [1:622] "(Intercept)" "trend" "season2" "season3" ...
  ..$ rank         : int 369
  ..$ fitted.values: Time-Series [1:622] from 1 to 2.7: 3746 2356 2882 3980 5740 ...
  .. ..- attr(*, "names")= chr [1:622] "1" "2" "3" "4" ...
  ..$ assign       : int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  ..$ qr           :List of 5
  .. ..$ qr   : num [1:622, 1:370] -24.9399 0.0401 0.0401 0.0401 0.0401 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:622] "1" "2" "3" "4" ...
  .. .. .. ..$ : chr [1:370] "(Intercept)" "trend" "season2" "season3" ...
  .. .. ..- attr(*, "assign")= int [1:370] 0 1 2 2 2 2 2 2 2 2 ...
  .. .. ..- attr(*, "contrasts")=List of 1
  .. .. .. ..$ season: chr "contr.treatment"
  .. ..$ qraux: num [1:370] 1.04 1.07 1.05 1.04 1.03 ...
  .. ..$ pivot: int [1:370] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ tol  : num 1e-07
  .. ..$ rank : int 369
  .. ..- attr(*, "class")= chr "qr"
  ..$ df.residual  : int 253
  ..$ contrasts    :List of 1
  .. ..$ season: chr "contr.treatment"
  ..$ xlevels      :List of 1
  .. ..$ season: chr [1:365] "1" "2" "3" "4" ...
  ..$ call         : language tslm(formula = Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo +      Promo2)
  ..$ terms        :Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. ..- attr(*, "intercept")= int 1
  .. .. ..- attr(*, "response")= int 1
  .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281aa8e08> 
  .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ model        :'data.frame':	622 obs. of  7 variables:
  .. ..$ Sales        : int [1:622] 4367 3333 3827 4100 6514 5534 3781 4467 4157 4101 ...
  .. ..$ trend        : int [1:622] 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ season       : Factor w/ 365 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
  .. ..$ DayOfWeek    : int [1:622] 3 4 5 6 1 2 3 4 5 6 ...
  .. ..$ SchoolHoliday: num [1:622] 1 1 1 0 0 0 0 0 0 0 ...
  .. ..$ Promo        : int [1:622] 0 0 0 0 1 1 1 1 1 0 ...
  .. ..$ Promo2       : int [1:622] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..- attr(*, "terms")=Classes 'terms', 'formula'  language Sales ~ trend + season + DayOfWeek + SchoolHoliday + Promo + Promo2
  .. .. .. ..- attr(*, "variables")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "factors")= int [1:7, 1:6] 0 1 0 0 0 0 0 0 0 1 ...
  .. .. .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. .. .. ..$ : chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  .. .. .. .. .. ..$ : chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "term.labels")= chr [1:6] "trend" "season" "DayOfWeek" "SchoolHoliday" ...
  .. .. .. ..- attr(*, "order")= int [1:6] 1 1 1 1 1 1
  .. .. .. ..- attr(*, "intercept")= int 1
  .. .. .. ..- attr(*, "response")= int 1
  .. .. .. ..- attr(*, ".Environment")=<environment: 0x7fa281aa8e08> 
  .. .. .. ..- attr(*, "predvars")= language list(Sales, trend, season, DayOfWeek, SchoolHoliday, Promo, Promo2)
  .. .. .. ..- attr(*, "dataClasses")= Named chr [1:7] "numeric" "numeric" "factor" "numeric" ...
  .. .. .. .. ..- attr(*, "names")= chr [1:7] "Sales" "trend" "season" "DayOfWeek" ...
  ..$ method       : chr "Linear regression model"
  ..- attr(*, "class")= chr [1:2] "tslm" "lm"
  [list output truncated]
 - attr(*, "split_type")= chr "data.frame"
 - attr(*, "split_labels")='data.frame':	1115 obs. of  1 variable:
  ..$ Store: int [1:1115] 1 2 3 4 5 6 7 8 9 10 ...

Predicción



In [212]:

    
min(test.store$Date)
max(test.store$Date)

max(test.store$Date) - min(test.store$Date)
as.numeric(max(test.store$Date) - min(test.store$Date)) / 7









    




2015-08-01






    




2015-09-17






    





Time difference of 47 days






    




6.71428571428571

Predicción con ARIMA

Solo tenemos que llevar el horizonte temporal hasta el tiempo requerido de predicción, en nuestro caso, tomando como referencia el test dataset son 6.7 semanas futuras, es decir unos 47 días a partir de la fecha fin del train dataset (exclusive).



In [15]:

    
fcast.arima <- lapply(out.arima, function(x) forecast(x, h=47))



In [19]:

    
str(fcast.arima)









    



List of 1115
 $ 1   :List of 10
  ..$ method   : chr "ARIMA(3,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] -0.657 -0.142 -0.219 0.486
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ sigma2   : num 7.2e-08
  .. ..$ var.coef : num [1:4, 1:4] 0.00835 0.002027 -0.000895 -0.007578 0.002027 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 5322
  .. ..$ aic      : num -10633
  .. ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:781] from 1 to 781: 1.31e-03 -3.60e-04 -1.36e-05 1.74e-04 4.32e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.31007390199431,  1.30969538468098, 1.309755| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 780
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] -0.657 -0.142 -0.219
  .. .. ..$ theta: num [1:2] 0.486 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 7.01e-05 2.62e-06 -1.64e-05 1.31
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 -5.71e-18 2.61e-17 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.657 -0.142 -0.219 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 0.486 0 0 0.486 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 4.86e-01 0.00 1.47e-18 4.86e-01 ...
  .. ..$ bic      : num -10610
  .. ..$ aicc     : num -10633
  .. ..$ x        : Time-Series [1:781] from 1 to 781: 5530 4327 4486 4997 7176 5580 5471 4892 4881 4952 ...
  .. ..$ lambda   : atomic [1:1] -0.762
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:781] from 1 to 781: 2732 5457 4523 4477 5157 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 782 to 828: 5110 5118 5081 5137 5104 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 782 to 828: 4132 3906 3725 3675 3544 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 782 to 828: 6586 7195 7638 8064 8471 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:781] from 1 to 781: 5530 4327 4486 4997 7176 5580 5471 4892 4881 4952 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 2732 5457 4523 4477 5157 ...
  ..$ residuals: Time-Series [1:781] from 1 to 781: 1.31e-03 -3.60e-04 -1.36e-05 1.74e-04 4.32e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 2   :List of 10
  ..$ method   : chr "ARIMA(4,0,5) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.574 -0.14 -0.934 -0.42 0.817 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.0061
  .. ..$ var.coef : num [1:10, 1:10] 0.02634 0.00319 0.00254 0.02367 -0.02549 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 891
  .. ..$ aic      : num -1759
  .. ..$ arma     : int [1:7] 4 5 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: -0.01165 -0.02426 -0.00351 -0.17983 0.12001 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.69853618066949,  4.68173538869948, 4.702328| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 784
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] -0.574 -0.14 -0.934 -0.42
  .. .. ..$ theta: num [1:5] 0.817 0.4015 0.9429 0.5065 -0.0242
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. .. ..$ a    : num [1:6] 0.07039 -0.01197 -0.00227 0.05821 0.0262 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.574 -0.14 -0.934 -0.42 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 0.817 0.402 0.943 0.507 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 0.817 0.402 0.943 0.507 ...
  .. ..$ bic      : num -1708
  .. ..$ aicc     : num -1759
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 4422 4159 4484 2342 6775 6318 6763 5618 4810 2630 ...
  .. ..$ lambda   : atomic [1:1] -0.155
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 4616 4545 4542 4385 4303 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 3842 4971 4473 5590 4276 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 2709 3421 3089 3806 2951 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 5560 7389 6624 8412 6338 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 4422 4159 4484 2342 6775 6318 6763 5618 4810 2630 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 4616 4545 4542 4385 4303 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: -0.01165 -0.02426 -0.00351 -0.17983 0.12001 ...
  ..- attr(*, "class")= chr "forecast"
 $ 3   :List of 10
  ..$ method   : chr "ARIMA(5,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.628 0.113 0.504 0.17 -0.51 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.000113
  .. ..$ var.coef : num [1:10, 1:10] 0.003502 0.004292 0.002342 -0.000502 -0.001395 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 2438
  .. ..$ aic      : num -4855
  .. ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00167 -0.00374 -0.00176 -0.01228 0.02374 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.61977813667363,  2.61393053048493, 2.615080| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.628 0.113 0.504 0.17 -0.51
  .. .. ..$ theta: num [1:4] 0.981 0.351 -0.344 -0.475
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 0.009503 0.00035 0.000667 -0.003296 -0.007137
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -0.628 0.113 0.504 0.17 -0.51 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 0.981 0.351 -0.344 -0.475 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 0.981 0.351 -0.344 -0.475 ...
  .. ..$ bic      : num -4803
  .. ..$ aicc     : num -4854
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 6823 5902 6069 4523 12247 9800 8001 7772 9292 4455 ...
  .. ..$ lambda   : atomic [1:1] -0.367
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 6540 6470 6338 6003 6318 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5655 7420 6104 5574 6562 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4164 5201 4344 4007 4617 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 7983 11165 9005 8114 9824 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 6823 5902 6069 4523 12247 9800 8001 7772 9292 4455 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6540 6470 6338 6003 6318 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00167 -0.00374 -0.00176 -0.01228 0.02374 ...
  ..- attr(*, "class")= chr "forecast"
 $ 4   :List of 10
  ..$ method   : chr "ARIMA(0,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] -0.126 -0.196
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  .. ..$ sigma2   : num 1.54e-09
  .. ..$ var.coef : num [1:2, 1:2] 0.00292 0.00241 0.00241 0.0039
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 7528
  .. ..$ aic      : num -15049
  .. ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -2.00e-05 -1.12e-06 1.99e-05 1.64e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999975086284638,  0.999954409310638, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num [1:2] -0.126 -0.196
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 2.48e-05 -2.89e-06 -5.06e-06 1.00
  .. .. ..$ P    : num [1:4, 1:4] 0.0 0.0 0.0 3.1e-21 0.0 ...
  .. .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.126 -0.196 0 -0.126 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.26e-01 -1.96e-01 -2.34e-22 -1.26e-01 ...
  .. ..$ bic      : num -15036
  .. ..$ aicc     : num -15049
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 9941 8247 8290 10338 12112 10031 8857 9472 10512 9719 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 909 9879 8368 8573 10106 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 13451 12594 12594 12594 12594 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 8023 6839 6476 6179 5931 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 41572 79383 228188 NA NA ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 9941 8247 8290 10338 12112 10031 8857 9472 10512 9719 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 909 9879 8368 8573 10106 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -2.00e-05 -1.12e-06 1.99e-05 1.64e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 5   :List of 10
  ..$ method   : chr "ARIMA(5,0,5) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:11] -1.092 -1.166 -1.096 -0.969 -0.88 ...
  .. .. ..- attr(*, "names")= chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.0876
  .. ..$ var.coef : num [1:11, 1:11] 6.55e-04 6.17e-04 5.40e-04 2.07e-04 3.67e-05 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:11] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -153
  .. ..$ aic      : num 331
  .. ..$ arma     : int [1:7] 5 5 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -0.00851 -0.1516 0.01486 -0.70328 0.25794 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(7.75108283524211,  7.57475007087681, 7.791114| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.092 -1.166 -1.096 -0.969 -0.88
  .. .. ..$ theta: num [1:5] 1.106 1.364 1.217 0.914 0.667
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. .. ..$ a    : num [1:6] 0.0972 -0.3229 -0.1058 -0.0523 0.0296 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] -1.092 -1.166 -1.096 -0.969 -0.88 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 1.106 1.364 1.217 0.914 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 1.106 1.364 1.217 0.914 ...
  .. ..$ bic      : num 387
  .. ..$ aicc     : num 331
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4253 3465 4456 1590 6978 5718 5974 4999 5159 1760 ...
  .. ..$ lambda   : atomic [1:1] -0.0182
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 4295 4132 4380 3575 5158 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 2619 5760 4667 4508 4299 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 1693 3701 2982 2876 2725 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 4064 8998 7332 7093 6809 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4253 3465 4456 1590 6978 5718 5974 4999 5159 1760 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4295 4132 4380 3575 5158 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.00851 -0.1516 0.01486 -0.70328 0.25794 ...
  ..- attr(*, "class")= chr "forecast"
 $ 6   :List of 10
  ..$ method   : chr "ARIMA(5,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] -1.2963 -0.8581 -0.0716 0.2229 -0.1645 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.0693
  .. ..$ var.coef : num [1:9, 1:9] 0.0078 0.00853 0.00366 -0.0042 -0.00417 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -63.2
  .. ..$ aic      : num 146
  .. ..$ arma     : int [1:7] 5 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00922 -0.08688 0.04731 -0.35671 0.44581 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(9.21983942367567,  9.08524518233759, 9.220390| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.2963 -0.8581 -0.0716 0.2229 -0.1645
  .. .. ..$ theta: num [1:4] 0.5598 -0.0702 -0.7563 -0.5835
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.184 -0.219 -0.03 -0.115 -0.066 ...
  .. .. ..$ P    : num [1:6, 1:6] 0.00 0.00 1.39e-17 0.00 0.00 ...
  .. .. ..$ T    : num [1:6, 1:6] -1.2963 -0.8581 -0.0716 0.2229 -0.1645 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 0.5598 -0.0702 -0.7563 -0.5835 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 0.5598 -0.0702 -0.7563 -0.5835 ...
  .. ..$ bic      : num 193
  .. ..$ aicc     : num 147
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 6089 5398 6092 3872 8591 7099 6749 6282 6829 3829 ...
  .. ..$ lambda   : atomic [1:1] 0.0128
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 6039 5835 5840 5333 5771 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 3745 5391 4265 4259 4514 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 2763 3942 3078 3072 3256 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 5071 7364 5902 5896 6249 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 6089 5398 6092 3872 8591 7099 6749 6282 6829 3829 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 6039 5835 5840 5333 5771 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00922 -0.08688 0.04731 -0.35671 0.44581 ...
  ..- attr(*, "class")= chr "forecast"
 $ 7   :List of 10
  ..$ method   : chr "ARIMA(2,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:6] -0.0706 -0.3689 -0.7873 0.4757 -0.3799 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 0.0622
  .. ..$ var.coef : num [1:6, 1:6] 0.02138 -0.00344 -0.01952 0.02141 -0.00668 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num -22
  .. ..$ aic      : num 58
  .. ..$ arma     : int [1:7] 2 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:786] from 1 to 786: 0.008931 -0.093886 0.000225 -0.343216 0.563337 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(8.93056724262743,  8.80195315333357, 8.870966| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 785
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.0706 -0.3689
  .. .. ..$ theta: num [1:4] -0.787 0.476 -0.38 -0.244
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.277 -0.454 0.165 -0.153 -0.101 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.0706 -0.3689 0 0 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.787 0.476 -0.38 -0.244 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -0.787 0.476 -0.38 -0.244 ...
  .. ..$ bic      : num 90.7
  .. ..$ aicc     : num 58.2
  .. ..$ x        : Time-Series [1:786] from 1 to 786: 8244 7231 7758 5218 12718 10073 7049 8234 7115 4236 ...
  .. ..$ lambda   : atomic [1:1] -0.00215
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:786] from 1 to 786: 8169 7957 7756 7403 7160 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 787 to 833: 9463 10435 10600 9214 9252 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 787 to 833: 6832 7508 7512 6477 6499 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 787 to 833: 13111 14506 14960 13112 13175 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:786] from 1 to 786: 8244 7231 7758 5218 12718 10073 7049 8234 7115 4236 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:786] from 1 to 786: 8169 7957 7756 7403 7160 ...
  ..$ residuals: Time-Series [1:786] from 1 to 786: 0.008931 -0.093886 0.000225 -0.343216 0.563337 ...
  ..- attr(*, "class")= chr "forecast"
 $ 8   :List of 10
  ..$ method   : chr "ARIMA(1,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:3] -0.343 -0.469 -0.506
  .. .. ..- attr(*, "names")= chr [1:3] "ar1" "ma1" "ma2"
  .. ..$ sigma2   : num 12.6
  .. ..$ var.coef : num [1:3, 1:3] 0.00894 -0.0073 0.00712 -0.0073 0.00683 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  .. .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  .. ..$ mask     : logi [1:3] TRUE TRUE TRUE
  .. ..$ loglik   : num -2102
  .. ..$ aic      : num 4213
  .. ..$ arma     : int [1:7] 1 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 0.0346 -0.8833 -1.7953 -5.5158 6.5815 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(34.605247508431,  33.4475430468026, 31.703713| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.343
  .. .. ..$ theta: num [1:2] -0.469 -0.506
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 0.1 -3.1 -1.65 39.5
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 5.17e-23 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.343 0 0 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.469 -0.506 0 -0.469 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -4.69e-01 -5.06e-01 1.32e-23 -4.69e-01 ...
  .. ..$ bic      : num 4232
  .. ..$ aicc     : num 4213
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5419 4842 4059 2337 7416 6333 5038 6084 4997 2660 ...
  .. ..$ lambda   : atomic [1:1] 0.273
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 5401 5278 4867 4304 3951 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 6445 6114 6226 6187 6201 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 4148 3876 3955 3926 3935 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 9551 9170 9323 9274 9292 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5419 4842 4059 2337 7416 6333 5038 6084 4997 2660 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5401 5278 4867 4304 3951 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.0346 -0.8833 -1.7953 -5.5158 6.5815 ...
  ..- attr(*, "class")= chr "forecast"
 $ 9   :List of 10
  ..$ method   : chr "ARIMA(2,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] -0.4255 0.5073 -0.0811 -0.8846
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. ..$ sigma2   : num 4.48e-09
  .. ..$ var.coef : num [1:4, 1:4] 0.002381 0.000641 -0.001718 0.001603 0.000641 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 6536
  .. ..$ aic      : num -13063
  .. ..$ arma     : int [1:7] 2 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.09e-03 -2.19e-05 8.29e-06 -4.40e-05 1.69e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.08515719213164,  1.0851311890386, 1.0851484| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.425 0.507
  .. .. ..$ theta: num [1:2] -0.0811 -0.8846
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 3.23e-05 -1.61e-05 -2.57e-05 1.09
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -1.28e-16 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.425 0.507 0 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.0811 -0.8846 0 -0.0811 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.11e-02 -8.85e-01 -6.09e-17 -8.11e-02 ...
  .. ..$ bic      : num -13040
  .. ..$ aicc     : num -13063
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4903 4602 4798 4254 7574 6206 4699 5340 5855 4657 ...
  .. ..$ lambda   : atomic [1:1] -0.921
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 1255 4853 4702 4708 4599 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 7609 7706 7249 7484 7162 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 5737 5630 5316 5434 5247 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 11158 12006 11207 11809 11095 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4903 4602 4798 4254 7574 6206 4699 5340 5855 4657 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 1255 4853 4702 4708 4599 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.09e-03 -2.19e-05 8.29e-06 -4.40e-05 1.69e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 10  :List of 10
  ..$ method   : chr "ARIMA(0,1,1) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:2] -6.4e-01 5.9e-08
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "drift"
  .. ..$ sigma2   : num 2.29e-09
  .. ..$ var.coef : num [1:2, 1:2] 4.84e-03 1.34e-06 1.34e-06 1.65e-09
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "drift"
  .. .. .. ..$ : chr [1:2] "ma1" "drift"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 6999
  .. ..$ aic      : num -13991
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -4.64e-06 1.49e-05 -2.98e-05 8.74e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99986779450382,  0.999861700653274, 0.99988| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.64
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 2.24e-05 -1.80e-05 1.00
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 2.49e-23 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.64 0 -0.64 0.409 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -6.40e-01 9.73e-24 -6.40e-01 4.09e-01 ...
  .. ..$ xreg     : int [1:784, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num -13977
  .. ..$ aicc     : num -13991
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 4812 4675 5114 4256 7804 5394 5696 5419 5556 4402 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 828 4779 4751 4874 4641 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 6366 6369 6371 6373 6376 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 4579 4501 4430 4364 4303 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 10440 10885 11341 11812 12300 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 4812 4675 5114 4256 7804 5394 5696 5419 5556 4402 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 828 4779 4751 4874 4641 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -4.64e-06 1.49e-05 -2.98e-05 8.74e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 11  :List of 10
  ..$ method   : chr "ARIMA(2,0,2) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:5] -0.322 0.64 0.757 -0.122 1.409
  .. .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 1.21e-07
  .. ..$ var.coef : num [1:5, 1:5] 2.37e-03 2.16e-03 -2.52e-03 -2.26e-03 7.68e-09 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 5134
  .. ..$ aic      : num -10255
  .. ..$ arma     : int [1:7] 2 2 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 2.19e-04 -1.62e-04 -1.65e-05 -5.00e-04 5.75e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.40880169584566,  1.40847994352751, 1.408572| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 784
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.322 0.64
  .. .. ..$ theta: num [1:2] 0.757 -0.122
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:3] 1 0 0
  .. .. ..$ a    : num [1:3] 5.04e-04 1.85e-04 -3.79e-05
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 0.00 0.00 7.77e-16 ...
  .. .. ..$ T    : num [1:3, 1:3] -0.322 0.64 0 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 0.757 -0.122 0.757 0.573 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1 0.757 -0.122 0.757 0.573 ...
  .. ..$ bic      : num -10227
  .. ..$ aicc     : num -10255
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 8913 7375 7768 5734 9939 9422 8458 8525 8745 5752 ...
  .. ..$ lambda   : atomic [1:1] -0.709
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 7815 8086 7842 7373 7037 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 7713 8986 7306 8572 7157 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 6110 6802 5652 6434 5527 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 10198 12718 9999 12290 9822 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 8913 7375 7768 5734 9939 9422 8458 8525 8745 5752 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 7815 8086 7842 7373 7037 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 2.19e-04 -1.62e-04 -1.65e-05 -5.00e-04 5.75e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 12  :List of 10
  ..$ method   : chr "ARIMA(3,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.71 0.689 -0.919 -1.257 -0.418 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 1.93e-09
  .. ..$ var.coef : num [1:8, 1:8] 5.90e-04 -2.84e-04 -9.11e-05 -5.96e-04 4.35e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7181
  .. ..$ aic      : num -14344
  .. ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -4.91e-06 -9.71e-06 4.68e-05 6.63e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999876767389667,  0.999870144433433, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.71 0.689 -0.919
  .. .. ..$ theta: num [1:5] -1.257 -0.418 1.216 -0.35 -0.159
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 1.35e-05 -3.52e-05 6.69e-06 1.06e-05 -1.51e-06 ...
  .. .. ..$ P    : num [1:7, 1:7] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:7, 1:7] 0.71 0.689 -0.919 0 0 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -1.257 -0.418 1.216 -0.35 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -1.257 -0.418 1.216 -0.35 ...
  .. ..$ bic      : num -14302
  .. ..$ aicc     : num -14344
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5029 4867 4642 6392 11010 9114 8311 7591 7999 6342 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 835 4986 4861 4921 6365 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 7288 7171 6234 6459 6085 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 5170 4972 4446 4544 4349 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 12346 12863 10425 11158 10127 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5029 4867 4642 6392 11010 9114 8311 7591 7999 6342 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 835 4986 4861 4921 6365 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -4.91e-06 -9.71e-06 4.68e-05 6.63e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 13  :List of 10
  ..$ method   : chr "ARIMA(2,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:6] 1.682 -0.948 -1.235 0.476 0.106 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 1.48e-08
  .. ..$ var.coef : num [1:6, 1:6] 3.26e-04 -2.72e-04 -3.87e-04 -3.91e-05 2.17e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 4720
  .. ..$ aic      : num -9425
  .. ..$ arma     : int [1:7] 2 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:621] from 1 to 621: -8.90e-05 -5.27e-05 -2.08e-05 1.14e-05 2.44e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.132335676811,  1.1323236269455, 1.132356002| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] 1.682 -0.948
  .. .. ..$ theta: num [1:3] -1.235 0.476 0.106
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:4] 1 0 0 0
  .. .. ..$ a    : num [1:4] 2.91e-04 -4.13e-04 9.37e-05 1.89e-05
  .. .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:4, 1:4] 1.682 -0.948 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -1.235 0.476 0.106 -1.235 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1 -1.235 0.476 0.106 -1.235 ...
  .. ..$ bic      : num -9394
  .. ..$ aicc     : num -9425
  .. ..$ x        : Time-Series [1:621] from 1 to 621: 3737 3674 3848 4285 8246 6700 5296 5432 6075 4592 ...
  .. ..$ lambda   : atomic [1:1] -0.883
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:621] from 1 to 621: 4273 3965 3968 4208 4785 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 622 to 668: 5279 4210 3681 3450 3477 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 622 to 668: 4045 3306 2944 2786 2804 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 622 to 668: 7484 5727 4864 4492 4535 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:621] from 1 to 621: 3737 3674 3848 4285 8246 6700 5296 5432 6075 4592 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:621] from 1 to 621: 4273 3965 3968 4208 4785 ...
  ..$ residuals: Time-Series [1:621] from 1 to 621: -8.90e-05 -5.27e-05 -2.08e-05 1.14e-05 2.44e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 14  :List of 10
  ..$ method   : chr "ARIMA(2,1,0)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] -0.73 -0.338
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "ar2"
  .. ..$ sigma2   : num 0.000151
  .. ..$ var.coef : num [1:2, 1:2] 0.00114 0.00062 0.00062 0.00114
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "ar2"
  .. .. .. ..$ : chr [1:2] "ar1" "ar2"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 2320
  .. ..$ aic      : num -4634
  .. ..$ arma     : int [1:7] 2 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.002551 -0.007577 0.000136 -0.028782 0.028562 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.55133744009416,  2.54172845777618, 2.547115| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.73 -0.338
  .. .. ..$ theta: num 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 0.005383 -0.000618 2.554348
  .. .. ..$ P    : num [1:3, 1:3] 0.00 2.11e-17 -6.25e-17 2.11e-17 -1.95e-34 ...
  .. .. ..$ T    : num [1:3, 1:3] -0.73 -0.338 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 0 0 0 0 0 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 7.13e-18 -4.56e-17 7.13e-18 0.00 ...
  .. ..$ bic      : num -4620
  .. ..$ aicc     : num -4634
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 5253 4169 4734 2519 7788 6920 5391 6046 6159 3020 ...
  .. ..$ lambda   : atomic [1:1] -0.376
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 4931 4994 4718 4656 3775 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5796 6030 6100 5968 6040 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 3958 4043 3941 3690 3638 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 9052 9654 10295 10738 11308 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 5253 4169 4734 2519 7788 6920 5391 6046 6159 3020 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4931 4994 4718 4656 3775 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.002551 -0.007577 0.000136 -0.028782 0.028562 ...
  ..- attr(*, "class")= chr "forecast"
 $ 15  :List of 10
  ..$ method   : chr "ARIMA(1,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:3] -0.977 0.623 -0.286
  .. .. ..- attr(*, "names")= chr [1:3] "ar1" "ma1" "ma2"
  .. ..$ sigma2   : num 2.3e-09
  .. ..$ var.coef : num [1:3, 1:3] 1.29e-04 -1.33e-04 5.75e-05 -1.33e-04 1.52e-03 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  .. .. .. ..$ : chr [1:3] "ar1" "ma1" "ma2"
  .. ..$ mask     : logi [1:3] TRUE TRUE TRUE
  .. ..$ loglik   : num 6995
  .. ..$ aic      : num -13982
  .. ..$ arma     : int [1:7] 1 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 1.70e-05 7.99e-06 1.33e-05 7.58e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999862884456626,  0.999881064326566, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.977
  .. .. ..$ theta: num [1:2] 0.623 -0.286
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 3.67e-06 -4.88e-06 -1.27e-06 1.00
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 3.18e-21 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.977 0 0 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 0.623 -0.286 0 0.623 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 6.23e-01 -2.86e-01 2.38e-21 6.23e-01 ...
  .. ..$ bic      : num -13963
  .. ..$ aicc     : num -13982
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 4701 5140 5174 5538 9049 7439 6777 6818 7621 5429 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 825 4728 4969 5158 5369 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 8528 9069 8539 9056 8550 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 5595 5451 4946 4894 4538 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 17922 26964 31215 60584 73868 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 4701 5140 5174 5538 9049 7439 6777 6818 7621 5429 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 825 4728 4969 5158 5369 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 1.70e-05 7.99e-06 1.33e-05 7.58e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 16  :List of 10
  ..$ method   : chr "ARIMA(2,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:3] 0.116 0.137 -0.986
  .. .. ..- attr(*, "names")= chr [1:3] "ar1" "ar2" "ma1"
  .. ..$ sigma2   : num 1.74e-06
  .. ..$ var.coef : num [1:3, 1:3] 1.32e-03 -1.16e-04 -4.81e-05 -1.16e-04 1.31e-03 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:3] "ar1" "ar2" "ma1"
  .. .. .. ..$ : chr [1:3] "ar1" "ar2" "ma1"
  .. ..$ mask     : logi [1:3] TRUE TRUE TRUE
  .. ..$ loglik   : num 4045
  .. ..$ aic      : num -8083
  .. ..$ arma     : int [1:7] 2 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 0.001698 -0.00091 -0.000314 -0.001979 0.003066 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.69809373366723,  1.69688016681599, 1.697139| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] 0.116 0.137
  .. .. ..$ theta: num -0.986
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 2.19e-06 -9.50e-04 1.70
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -8.25e-22 0.00 9.92e-12 ...
  .. .. ..$ T    : num [1:3, 1:3] 0.116 0.137 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.986 0 -0.986 0.972 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.86e-01 -1.88e-21 -9.86e-01 9.72e-01 ...
  .. ..$ bic      : num -8064
  .. ..$ aicc     : num -8083
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 6919 5650 5888 4346 10013 8370 7898 7017 7498 4559 ...
  .. ..$ lambda   : atomic [1:1] -0.586
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 5244 6562 6199 5812 5670 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 8380 8201 7978 7929 7894 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 6171 6046 5886 5855 5832 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 12170 11889 11551 11470 11411 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 6919 5650 5888 4346 10013 8370 7898 7017 7498 4559 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 5244 6562 6199 5812 5670 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.001698 -0.00091 -0.000314 -0.001979 0.003066 ...
  ..- attr(*, "class")= chr "forecast"
 $ 17  :List of 10
  ..$ method   : chr "ARIMA(5,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] -1.195 -0.826 -0.224 -0.021 -0.334 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.01
  .. ..$ var.coef : num [1:9, 1:9] 0.00417 0.00468 0.00209 -0.00183 -0.00201 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -1109
  .. ..$ aic      : num 2237
  .. ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:782] from 1 to 782: -0.1213 -0.3271 0.0186 -1.8547 1.7794 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(15.2056929036692,  14.9463586261433, 15.33500| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 782
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.195 -0.826 -0.224 -0.021 -0.334
  .. .. ..$ theta: num [1:4] 1.47 1.304 0.577 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 1.047 0.349 0.459 0.257 -0.241
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -1.195 -0.826 -0.224 -0.021 -0.334 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 1.47 1.304 0.577 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 1.47 1.304 0.577 0 ...
  .. ..$ bic      : num 2284
  .. ..$ aicc     : num 2238
  .. ..$ x        : Time-Series [1:782] from 1 to 782: 5593 5102 5853 2576 11279 9034 7450 7259 7711 3031 ...
  .. ..$ lambda   : atomic [1:1] 0.121
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:782] from 1 to 782: 5837 5728 5815 5127 6208 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 783 to 829: 4267 7424 5815 4807 6385 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 783 to 829: 2636 4654 3575 2919 3927 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 783 to 829: 6727 11549 9206 7693 10103 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:782] from 1 to 782: 5593 5102 5853 2576 11279 9034 7450 7259 7711 3031 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 5837 5728 5815 5127 6208 ...
  ..$ residuals: Time-Series [1:782] from 1 to 782: -0.1213 -0.3271 0.0186 -1.8547 1.7794 ...
  ..- attr(*, "class")= chr "forecast"
 $ 18  :List of 10
  ..$ method   : chr "ARIMA(2,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] -0.718 0.254 -0.105 -0.865
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. ..$ sigma2   : num 5.27e-06
  .. ..$ var.coef : num [1:4, 1:4] 0.001633 0.001417 -0.000497 0.000392 0.001417 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 3638
  .. ..$ aic      : num -7267
  .. ..$ arma     : int [1:7] 2 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:782] from 1 to 782: 1.87e-03 -8.37e-05 1.59e-03 -3.77e-03 4.17e-03 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.86527612263994,  1.86514947263116, 1.867119| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 781
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.718 0.254
  .. .. ..$ theta: num [1:2] -0.105 -0.865
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 0.00257 -0.00177 -0.00187 1.86879
  .. .. ..$ P    : num [1:4, 1:4] 0.00 -1.39e-17 0.00 -1.11e-16 -1.39e-17 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.718 0.254 0 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.105 -0.865 0 -0.105 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.05e-01 -8.65e-01 -8.48e-17 -1.05e-01 ...
  .. ..$ bic      : num -7243
  .. ..$ aicc     : num -7266
  .. ..$ x        : Time-Series [1:782] from 1 to 782: 5143 5083 6155 3688 7843 6653 6553 6903 6797 3768 ...
  .. ..$ lambda   : atomic [1:1] -0.53
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:782] from 1 to 782: 4357 5123 5268 5076 5095 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 783 to 829: 6566 7648 6214 7486 6214 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 783 to 829: 4922 5582 4661 5462 4655 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 783 to 829: 9226 11165 8725 10934 8742 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:782] from 1 to 782: 5143 5083 6155 3688 7843 6653 6553 6903 6797 3768 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 4357 5123 5268 5076 5095 ...
  ..$ residuals: Time-Series [1:782] from 1 to 782: 1.87e-03 -8.37e-05 1.59e-03 -3.77e-03 4.17e-03 ...
  ..- attr(*, "class")= chr "forecast"
 $ 19  :List of 10
  ..$ method   : chr "ARIMA(3,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:6] -0.586 -0.59 0.33 -0.237 0.106 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 1.19e-06
  .. ..$ var.coef : num [1:6, 1:6] 0.00292 0.00254 0.00151 -0.00222 0.0012 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 4204
  .. ..$ aic      : num -8395
  .. ..$ arma     : int [1:7] 3 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.001583 -0.001183 0.000332 -0.001291 0.002756 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.5827700877602,  1.58105283402581, 1.5823028| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] -0.586 -0.59 0.33
  .. .. ..$ theta: num [1:3] -0.237 0.106 -0.842
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] -6.83e-05 -1.26e-03 2.67e-04 -6.99e-04 1.58
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -2.41e-25 ...
  .. .. ..$ T    : num [1:5, 1:5] -0.586 -0.59 0.33 0 1 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.237 0.106 -0.842 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -2.37e-01 1.06e-01 -8.42e-01 6.11e-22 ...
  .. ..$ bic      : num -8362
  .. ..$ aicc     : num -8394
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 5763 4038 5189 3769 8978 7369 6149 6753 6725 3950 ...
  .. ..$ lambda   : atomic [1:1] -0.629
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 4141 5114 4835 4829 4557 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5982 7785 6631 5666 7409 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4424 5456 4773 4183 5194 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 8685 12314 10044 8248 11713 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 5763 4038 5189 3769 8978 7369 6149 6753 6725 3950 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4141 5114 4835 4829 4557 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.001583 -0.001183 0.000332 -0.001291 0.002756 ...
  ..- attr(*, "class")= chr "forecast"
 $ 20  :List of 10
  ..$ method   : chr "ARIMA(3,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] -1.904 -1.79 -0.865 1.146 0.188 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 839659
  .. ..$ var.coef : num [1:8, 1:8] 0.001769 0.002625 0.001312 -0.001436 -0.000217 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -5090
  .. ..$ aic      : num 10198
  .. ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:619] from 1 to 619: 4.69 101.95 -768.76 -1596.71 2079.53 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4691.01127378294,  4844.60915510654, 3740.950| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 618
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] -1.904 -1.79 -0.865
  .. .. ..$ theta: num [1:5] 1.146 0.188 -0.709 -1.079 -0.411
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] -1702 -4402 -4014 -2226 -780 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 0.00 -1.11e-16 -3.33e-16 -2.22e-16 ...
  .. .. ..$ T    : num [1:7, 1:7] -1.904 -1.79 -0.865 0 0 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 1.146 0.188 -0.709 -1.079 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 1.146 0.188 -0.709 -1.079 ...
  .. ..$ bic      : num 10238
  .. ..$ aicc     : num 10198
  .. ..$ x        : Time-Series [1:619] from 1 to 619: 7110 7356 5599 3642 9662 9065 7764 8175 6745 4527 ...
  .. ..$ lambda   : atomic [1:1] 0.947
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:619] from 1 to 619: 7102 7193 6820 6145 6315 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 620 to 666: 7713 9729 8037 8011 9213 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 620 to 666: 5839 7775 6099 6047 7217 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 620 to 666: 9612 11705 10001 10001 11233 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:619] from 1 to 619: 7110 7356 5599 3642 9662 9065 7764 8175 6745 4527 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:619] from 1 to 619: 7102 7193 6820 6145 6315 ...
  ..$ residuals: Time-Series [1:619] from 1 to 619: 4.69 101.95 -768.76 -1596.71 2079.53 ...
  ..- attr(*, "class")= chr "forecast"
 $ 21  :List of 10
  ..$ method   : chr "ARIMA(3,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:5] 1.356 -0.438 -0.189 -1.707 0.721
  .. .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 3.11e-09
  .. ..$ var.coef : num [1:5, 1:5] 0.0024 -0.00303 0.00143 -0.00127 0.0013 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 6709
  .. ..$ aic      : num -13406
  .. ..$ arma     : int [1:7] 3 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 1.69e-05 2.35e-05 2.05e-05 8.06e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99980382877924,  0.999824008187924, 0.99985| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 1.356 -0.438 -0.189
  .. .. ..$ theta: num [1:2] -1.707 0.721
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 3.81e-05 -1.02e-04 5.23e-05 1.00
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -2.51e-24 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 1.356 -0.438 -0.189 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -1.707 0.721 0 -1.707 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.71 7.21e-01 -6.04e-25 -1.71 ...
  .. ..$ bic      : num -13378
  .. ..$ aicc     : num -13406
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 3680 3975 4471 5034 9580 7288 6618 5569 5869 5329 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 787 3725 4046 4563 5407 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 6436 5320 4600 4282 4232 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 4409 3661 3240 3073 3044 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 11913 9727 7925 7063 6937 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 3680 3975 4471 5034 9580 7288 6618 5569 5869 5329 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 787 3725 4046 4563 5407 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 1.69e-05 2.35e-05 2.05e-05 8.06e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 22  :List of 10
  ..$ method   : chr "ARIMA(0,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] -0.864 -0.123
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  .. ..$ sigma2   : num 7.25e-09
  .. ..$ var.coef : num [1:2, 1:2] 0.00119 -0.00114 -0.00114 0.00117
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 4998
  .. ..$ aic      : num -9991
  .. ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:619] from 1 to 619: 1.04e-03 2.85e-05 2.49e-05 -1.36e-04 1.84e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.03597223920683,  1.03600928797097, 1.036022| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 618
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num [1:2] -0.864 -0.123
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 3.20e-05 -8.36e-05 -1.08e-05 1.04
  .. .. ..$ P    : num [1:4, 1:4] 0.0 0.0 0.0 -5.1e-22 0.0 ...
  .. .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.864 -0.123 0 -0.864 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.64e-01 -1.23e-01 -4.80e-21 -8.64e-01 ...
  .. ..$ bic      : num -9978
  .. ..$ aicc     : num -9991
  .. ..$ x        : Time-Series [1:619] from 1 to 619: 3514 3894 4053 2645 6507 5779 5254 4742 4750 2665 ...
  .. ..$ lambda   : atomic [1:1] -0.965
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:619] from 1 to 619: 922 3595 3768 3631 3441 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 620 to 666: 4671 4501 4501 4501 4501 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 620 to 666: 3382 3283 3283 3282 3282 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 620 to 666: 7486 7103 7104 7104 7104 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:619] from 1 to 619: 3514 3894 4053 2645 6507 5779 5254 4742 4750 2665 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:619] from 1 to 619: 922 3595 3768 3631 3441 ...
  ..$ residuals: Time-Series [1:619] from 1 to 619: 1.04e-03 2.85e-05 2.49e-05 -1.36e-04 1.84e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 23  :List of 10
  ..$ method   : chr "ARIMA(2,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:6] 1.6168 -0.8955 -1.3398 0.8052 -0.0758 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 2.03e-09
  .. ..$ var.coef : num [1:6, 1:6] 7.43e-04 -4.82e-04 -7.47e-04 6.46e-05 -2.03e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 6694
  .. ..$ aic      : num -13373
  .. ..$ arma     : int [1:7] 2 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -2.29e-05 -4.63e-06 -9.86e-07 -4.12e-05 1.08e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.01701226326749,  1.01702192395747, 1.017027| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] 1.617 -0.896
  .. .. ..$ theta: num [1:3] -1.3398 0.8052 -0.0758
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:4] 1 0 0 0
  .. .. ..$ a    : num [1:4] 6.67e-05 -9.59e-05 3.78e-05 -3.45e-06
  .. .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:4, 1:4] 1.617 -0.896 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -1.3398 0.8052 -0.0758 -1.3398 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1 -1.3398 0.8052 -0.0758 -1.3398 ...
  .. ..$ bic      : num -13340
  .. ..$ aicc     : num -13373
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4523 4701 4816 4174 9075 6998 5800 6023 6377 4314 ...
  .. ..$ lambda   : atomic [1:1] -0.983
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 4968 4791 4836 4904 4924 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5414 5067 4739 4570 4562 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4261 4012 3760 3633 3626 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 7408 6864 6397 6149 6142 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4523 4701 4816 4174 9075 6998 5800 6023 6377 4314 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4968 4791 4836 4904 4924 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -2.29e-05 -4.63e-06 -9.86e-07 -4.12e-05 1.08e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 24  :List of 10
  ..$ method   : chr "ARIMA(5,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] -0.04213 0.66475 0.00245 -0.17382 -0.37146 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.77e-09
  .. ..$ var.coef : num [1:8, 1:8] 0.004391 0.000518 -0.002629 0.000669 0.000458 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7254
  .. ..$ aic      : num -14490
  .. ..$ arma     : int [1:7] 5 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.72e-06 2.29e-05 -8.26e-06 4.81e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999930868955441,  0.999927565070031, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.04213 0.66475 0.00245 -0.17382 -0.37146
  .. .. ..$ theta: num [1:4] -0.629 -0.681 0.366 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 1.70e-05 -3.73e-05 -3.64e-07 4.68e-06 -3.38e-06 ...
  .. .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 0.00 -4.37e-18 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.04213 0.66475 0.00245 -0.17382 -0.37146 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.629 -0.681 0.366 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -0.629 -0.681 0.366 0 ...
  .. ..$ bic      : num -14448
  .. ..$ aicc     : num -14490
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 6907 6753 8419 6975 13453 10349 9474 9823 10333 7297 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 874 6832 7057 7401 8169 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 9221 10423 8547 8756 7813 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 6162 6552 5663 5699 5278 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 18314 25472 17420 18882 15037 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 6907 6753 8419 6975 13453 10349 9474 9823 10333 7297 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 874 6832 7057 7401 8169 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.72e-06 2.29e-05 -8.26e-06 4.81e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 25  :List of 10
  ..$ method   : chr "ARIMA(5,0,1) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] -0.355 0.406 0.249 -0.106 -0.343 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 32.4
  .. ..$ var.coef : num [1:7, 1:7] 0.00522 -0.000978 -0.000911 -0.000316 0.000048 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -2366
  .. ..$ aic      : num 4748
  .. ..$ arma     : int [1:7] 5 1 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:750] from 1 to 750: 2 -2.13 -2.75 -3.71 10.58 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(74.9757777635979,  71.2892705408686, 69.54317| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 750
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.355 0.406 0.249 -0.106 -0.343
  .. .. ..$ theta: num [1:4] 0.707 0 0 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 7.205 3.818 0.374 0.276 -0.265
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -0.355 0.406 0.249 -0.106 -0.343 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 0.707 0 0 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 0.707 0 0 0 ...
  .. ..$ bic      : num 4785
  .. ..$ aicc     : num 4748
  .. ..$ x        : Time-Series [1:750] from 1 to 750: 11944 10409 9729 8987 14513 14243 11539 11835 11194 9227 ...
  .. ..$ lambda   : atomic [1:1] 0.353
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:750] from 1 to 750: 11095 11278 10812 10394 9880 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 751 to 797: 11477 12165 11608 10905 10457 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 751 to 797: 8645 9059 8505 7839 7478 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 751 to 797: 14849 15889 15362 14656 14113 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:750] from 1 to 750: 11944 10409 9729 8987 14513 14243 11539 11835 11194 9227 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:750] from 1 to 750: 11095 11278 10812 10394 9880 ...
  ..$ residuals: Time-Series [1:750] from 1 to 750: 2 -2.13 -2.75 -3.71 10.58 ...
  ..- attr(*, "class")= chr "forecast"
 $ 26  :List of 10
  ..$ method   : chr "ARIMA(3,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 0.664 0.705 -0.889 -1.337 -0.229 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 4.27e-06
  .. ..$ var.coef : num [1:7, 1:7] 0.000784 -0.000129 -0.000308 -0.000861 0.000575 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 3721
  .. ..$ aic      : num -7426
  .. ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:782] from 1 to 782: 0.001853 -0.000384 0.000126 -0.00099 0.004526 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.8529654279375,  1.85246849479052, 1.8528002| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 781
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.664 0.705 -0.889
  .. .. ..$ theta: num [1:4] -1.337 -0.229 1.204 -0.629
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] -0.000078 -0.00171 0.000909 0.000547 -0.00046 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] 0.664 0.705 -0.889 0 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -1.337 -0.229 1.204 -0.629 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -1.337 -0.229 1.204 -0.629 ...
  .. ..$ bic      : num -7389
  .. ..$ aicc     : num -7426
  .. ..$ x        : Time-Series [1:782] from 1 to 782: 5950 5654 5849 5129 10108 7450 7124 6818 7223 5310 ...
  .. ..$ lambda   : atomic [1:1] -0.534
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:782] from 1 to 782: 4952 5881 5774 5656 5893 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 783 to 829: 6395 6181 5668 5861 5806 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 783 to 829: 4898 4696 4297 4401 4361 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 783 to 829: 8728 8533 7845 8220 8143 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:782] from 1 to 782: 5950 5654 5849 5129 10108 7450 7124 6818 7223 5310 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 4952 5881 5774 5656 5893 ...
  ..$ residuals: Time-Series [1:782] from 1 to 782: 0.001853 -0.000384 0.000126 -0.00099 0.004526 ...
  ..- attr(*, "class")= chr "forecast"
 $ 27  :List of 10
  ..$ method   : chr "ARIMA(0,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num -0.349
  .. .. ..- attr(*, "names")= chr "ma1"
  .. ..$ sigma2   : num 2.14e-09
  .. ..$ var.coef : num [1, 1] 0.00137
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr "ma1"
  .. .. .. ..$ : chr "ma1"
  .. ..$ mask     : logi TRUE
  .. ..$ loglik   : num 7021
  .. ..$ aic      : num -14038
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.04e-05 3.63e-06 -4.62e-06 5.98e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999960382550472,  0.999948967278473, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.349
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 2.17e-05 -7.65e-06 1.00
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -3.84e-21 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.349 0 -0.349 0.122 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.49e-01 -9.93e-22 -3.49e-01 1.22e-01 ...
  .. ..$ bic      : num -14029
  .. ..$ aicc     : num -14038
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 8674 7893 8361 7969 15594 11608 9803 10434 11571 8046 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 897 8602 8115 8274 8073 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 12001 12001 12001 12001 12001 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 7016 6495 6106 5796 5540 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 41444 78738 347193 NA NA ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 8674 7893 8361 7969 15594 11608 9803 10434 11571 8046 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 897 8602 8115 8274 8073 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.04e-05 3.63e-06 -4.62e-06 5.98e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 28  :List of 10
  ..$ method   : chr "ARIMA(0,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:3] -0.9534 0.0405 -0.0724
  .. .. ..- attr(*, "names")= chr [1:3] "ma1" "ma2" "ma3"
  .. ..$ sigma2   : num 0.0488
  .. ..$ var.coef : num [1:3, 1:3] 0.00158 -0.002443 0.000898 -0.002443 0.00595 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:3] "ma1" "ma2" "ma3"
  .. .. .. ..$ : chr [1:3] "ma1" "ma2" "ma3"
  .. ..$ mask     : logi [1:3] TRUE TRUE TRUE
  .. ..$ loglik   : num 69.3
  .. ..$ aic      : num -131
  .. ..$ arma     : int [1:7] 0 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:768] from 1 to 768: 0.00634 0.0249 0.03142 -0.4557 0.43434 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(6.33984707647235,  6.37431248336113, 6.393573| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 767
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num [1:3] -0.9534 0.0405 -0.0724
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] 0.08511 -0.24766 -0.00195 -0.01877 6.45993
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 3.71e-22 ...
  .. .. ..$ T    : num [1:5, 1:5] 0 0 0 0 1 1 0 0 0 0 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.9534 0.0405 -0.0724 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -9.53e-01 4.05e-02 -7.24e-02 7.98e-22 ...
  .. ..$ bic      : num -112
  .. ..$ aicc     : num -131
  .. ..$ x        : Time-Series [1:768] from 1 to 768: 4958 5287 5481 2070 10126 7892 6632 6179 6630 2401 ...
  .. ..$ lambda   : atomic [1:1] -0.0729
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:768] from 1 to 768: 4900 5047 5168 4696 4435 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 769 to 815: 4582 4566 4410 4410 4410 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 769 to 815: 2741 2730 2635 2635 2635 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 769 to 815: 7816 7792 7531 7532 7532 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:768] from 1 to 768: 4958 5287 5481 2070 10126 7892 6632 6179 6630 2401 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:768] from 1 to 768: 4900 5047 5168 4696 4435 ...
  ..$ residuals: Time-Series [1:768] from 1 to 768: 0.00634 0.0249 0.03142 -0.4557 0.43434 ...
  ..- attr(*, "class")= chr "forecast"
 $ 29  :List of 10
  ..$ method   : chr "ARIMA(3,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.736 0.681 -0.922 -1.258 -0.516 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 4.14e-08
  .. ..$ var.coef : num [1:8, 1:8] 0.000764 -0.000844 0.000288 -0.000803 0.001226 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 5532
  .. ..$ aic      : num -11047
  .. ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.29e-03 -1.62e-04 1.60e-04 6.31e-05 5.41e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.28758364070675,  1.28738322499306, 1.287617| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.736 0.681 -0.922
  .. .. ..$ theta: num [1:5] -1.258 -0.516 1.297 -0.269 -0.233
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 1.39e-04 -2.58e-04 -1.83e-05 1.62e-04 -2.29e-05 ...
  .. .. ..$ P    : num [1:7, 1:7] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:7, 1:7] 0.736 0.681 -0.922 0 0 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -1.258 -0.516 1.297 -0.269 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -1.258 -0.516 1.297 -0.269 ...
  .. ..$ bic      : num -11005
  .. ..$ aicc     : num -11046
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 5269 4554 5411 5564 10796 7235 5721 6590 7061 5518 ...
  .. ..$ lambda   : atomic [1:1] -0.776
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 2525 5118 4798 5294 6063 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 7897 7589 6877 7014 6760 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 6155 5817 5333 5413 5250 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 10757 10614 9442 9702 9262 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 5269 4554 5411 5564 10796 7235 5721 6590 7061 5518 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 2525 5118 4798 5294 6063 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.29e-03 -1.62e-04 1.60e-04 6.31e-05 5.41e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 30  :List of 10
  ..$ method   : chr "ARIMA(2,1,1) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:4] -0.487 -0.223 0.196 -0.005
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "drift"
  .. ..$ sigma2   : num 28.8
  .. ..$ var.coef : num [1:4, 1:4] 2.73e-02 6.21e-03 -2.71e-02 1.17e-05 6.21e-03 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "drift"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "drift"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num -2404
  .. ..$ aic      : num 4817
  .. ..$ arma     : int [1:7] 2 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 0.059 1.935 -4.065 1.443 11.616 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(59.009921726543,  61.0382149091668, 56.386506| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.487 -0.223
  .. .. ..$ theta: num 0.196
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] -0.449 -0.357 59.615
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -5.94e-22 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] -0.487 -0.223 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 0.196 0 0.196 0.0384 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 1.96e-01 -5.06e-23 1.96e-01 3.84e-02 ...
  .. ..$ xreg     : int [1:777, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num 4841
  .. ..$ aicc     : num 4817
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 5683 6219 5035 5643 9174 8705 5718 7957 6182 5131 ...
  .. ..$ lambda   : atomic [1:1] 0.358
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 5668 5707 6061 5282 5671 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 4743 4781 4768 4764 4767 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 3332 3085 2898 2691 2533 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 6489 6980 7272 7651 7979 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 5683 6219 5035 5643 9174 8705 5718 7957 6182 5131 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 5668 5707 6061 5282 5671 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.059 1.935 -4.065 1.443 11.616 ...
  ..- attr(*, "class")= chr "forecast"
 $ 31  :List of 10
  ..$ method   : chr "ARIMA(3,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.654 0.66 -0.839 -0.117 -0.627 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 7.49e-10
  .. ..$ var.coef : num [1:8, 1:8] 0.00214 -0.00078 -0.000508 -0.002186 -0.000673 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7128
  .. ..$ aic      : num -14238
  .. ..$ arma     : int [1:7] 3 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: -1.22e-05 1.00e-05 1.49e-05 -1.12e-05 4.46e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999880380177298,  0.999897786722261, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 784
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.654 0.66 -0.839
  .. .. ..$ theta: num [1:4] -0.117 -0.627 0.476 0.243
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 4.07e-05 -2.24e-05 -2.84e-05 1.54e-05 4.78e-06
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.654 0.66 -0.839 0 0 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.117 -0.627 0.476 0.243 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 -0.117 -0.627 0.476 0.243 ...
  .. ..$ bic      : num -14196
  .. ..$ aicc     : num -14237
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5122 5623 6140 5607 7857 6480 6335 6066 7314 5033 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 5464 5323 5624 5982 5819 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 5733 5637 5161 5362 5134 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 4774 4605 4242 4361 4198 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 7175 7266 6588 6961 6606 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5122 5623 6140 5607 7857 6480 6335 6066 7314 5033 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5464 5323 5624 5982 5819 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: -1.22e-05 1.00e-05 1.49e-05 -1.12e-05 4.46e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 32  :List of 10
  ..$ method   : chr "ARIMA(2,1,0) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:3] -6.37e-01 -2.38e-01 5.47e-06
  .. .. ..- attr(*, "names")= chr [1:3] "ar1" "ar2" "drift"
  .. ..$ sigma2   : num 5.28e-06
  .. ..$ var.coef : num [1:3, 1:3] 1.52e-03 7.82e-04 -1.35e-09 7.82e-04 1.52e-03 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:3] "ar1" "ar2" "drift"
  .. .. .. ..$ : chr [1:3] "ar1" "ar2" "drift"
  .. ..$ mask     : logi [1:3] TRUE TRUE TRUE
  .. ..$ loglik   : num 2889
  .. ..$ aic      : num -5770
  .. ..$ arma     : int [1:7] 2 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:621] from 1 to 621: 0.001596 -0.001753 -0.000145 -0.004319 0.005923 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.59601038446368,  1.59391037698159, 1.594849| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 620
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.637 -0.238
  .. .. ..$ theta: num 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 0.00044 -0.000194 1.595006
  .. .. ..$ P    : num [1:3, 1:3] 0.00 -1.10e-17 4.62e-17 -1.10e-17 -7.00e-35 ...
  .. .. ..$ T    : num [1:3, 1:3] -0.637 -0.238 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 0 0 0 0 0 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -2.61e-18 2.94e-17 -2.61e-18 0.00 ...
  .. ..$ xreg     : int [1:621, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num -5752
  .. ..$ aicc     : num -5770
  .. ..$ x        : Time-Series [1:621] from 1 to 621: 3668 2676 3058 1768 6573 5410 5277 4292 4414 1913 ...
  .. ..$ lambda   : atomic [1:1] -0.623
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:621] from 1 to 621: 2871 3466 3125 3018 2385 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 622 to 668: 5750 6015 6005 5961 6005 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 622 to 668: 3340 3348 3159 2968 2866 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 622 to 668: 13148 15284 17807 21023 24681 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:621] from 1 to 621: 3668 2676 3058 1768 6573 5410 5277 4292 4414 1913 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:621] from 1 to 621: 2871 3466 3125 3018 2385 ...
  ..$ residuals: Time-Series [1:621] from 1 to 621: 0.001596 -0.001753 -0.000145 -0.004319 0.005923 ...
  ..- attr(*, "class")= chr "forecast"
 $ 33  :List of 10
  ..$ method   : chr "ARIMA(5,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] 0.664 0.559 -0.113 -1.027 0.429 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 172
  .. ..$ var.coef : num [1:10, 1:10] 0.001491 0.000443 -0.000386 -0.002548 0.002628 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -3105
  .. ..$ aic      : num 6233
  .. ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 4.28 -6.383 3.484 -0.538 28.23 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(171.235467126574,  162.232264171273, 166.9284| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] 0.664 0.559 -0.113 -1.027 0.429
  .. .. ..$ theta: num [1:4] -0.132 -0.627 -0.236 0.881
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 22.48 -5.31 -17.52 -7.64 18.68
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.664 0.559 -0.113 -1.027 0.429 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.132 -0.627 -0.236 0.881 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 -0.132 -0.627 -0.236 0.881 ...
  .. ..$ bic      : num 6284
  .. ..$ aicc     : num 6233
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 8910 7987 8462 8293 11480 10678 7791 9322 8295 9339 ...
  .. ..$ lambda   : atomic [1:1] 0.488
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 8465 8636 8108 8348 8348 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 9346 8483 7948 7615 7603 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 7622 6643 6121 5818 5807 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 11250 10554 10021 9660 9648 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 8910 7987 8462 8293 11480 10678 7791 9322 8295 9339 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 8465 8636 8108 8348 8348 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 4.28 -6.383 3.484 -0.538 28.23 ...
  ..- attr(*, "class")= chr "forecast"
 $ 34  :List of 10
  ..$ method   : chr "ARIMA(0,1,1) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:2] -3.29e-01 4.43e-08
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "drift"
  .. ..$ sigma2   : num 1.74e-09
  .. ..$ var.coef : num [1:2, 1:2] 1.50e-03 8.17e-08 8.17e-08 1.28e-09
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "drift"
  .. .. .. ..$ : chr [1:2] "ma1" "drift"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 7311
  .. ..$ aic      : num -14617
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -1.57e-05 -4.61e-06 1.39e-05 4.93e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999946893992605,  0.999930088682986, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.329
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 2.87e-05 -8.94e-06 1.00
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 3.53e-21 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.329 0 -0.329 0.108 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.29e-01 8.75e-22 -3.29e-01 1.08e-01 ...
  .. ..$ xreg     : int [1:784, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num -14603
  .. ..$ aicc     : num -14617
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 7766 6870 6885 7707 11768 8576 8224 7667 8123 7045 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 886 7699 7110 6960 7447 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 10140 10144 10149 10154 10158 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 6580 6142 5812 5547 5327 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 22087 29119 39996 59832 108897 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 7766 6870 6885 7707 11768 8576 8224 7667 8123 7045 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 886 7699 7110 6960 7447 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -1.57e-05 -4.61e-06 1.39e-05 4.93e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 35  :List of 10
  ..$ method   : chr "ARIMA(1,1,0)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num -0.37
  .. .. ..- attr(*, "names")= chr "ar1"
  .. ..$ sigma2   : num 2.03e-09
  .. ..$ var.coef : num [1, 1] 0.00111
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr "ar1"
  .. .. .. ..$ : chr "ar1"
  .. ..$ mask     : logi TRUE
  .. ..$ loglik   : num 7074
  .. ..$ aic      : num -14143
  .. ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.31e-05 1.70e-05 1.30e-05 7.39e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999922246098883,  0.99990770812858, 0.99993| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.37
  .. .. ..$ theta: num(0) 
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:2] 1 1
  .. .. ..$ a    : num [1:2] 9.63e-06 1.00
  .. .. ..$ P    : num [1:2, 1:2] 0.00 -6.23e-21 -6.23e-21 6.23e-21
  .. .. ..$ T    : num [1:2, 1:2] -0.37 1 0 1
  .. .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:2, 1:2] 1.00 -2.30e-21 -2.30e-21 6.23e-21
  .. ..$ bic      : num -14134
  .. ..$ aicc     : num -14143
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 6519 5955 6868 7097 14536 11508 10066 9909 9946 7284 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 867 6459 6152 6499 7011 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 11887 12076 12005 12031 12022 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 7051 6622 6076 5737 5442 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 37829 68391 496564 NA NA ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 6519 5955 6868 7097 14536 11508 10066 9909 9946 7284 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 867 6459 6152 6499 7011 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.31e-05 1.70e-05 1.30e-05 7.39e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 36  :List of 10
  ..$ method   : chr "ARIMA(3,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 0.413 0.735 -0.579 -0.819 -0.778 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 3.2e-05
  .. ..$ var.coef : num [1:7, 1:7] 0.006877 0.000568 -0.003342 -0.007109 0.00381 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 2335
  .. ..$ aic      : num -4653
  .. ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00291 -0.0105 -0.00226 0.00216 0.01133 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.90699738038605,  2.89487345709204, 2.894533| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.413 0.735 -0.579
  .. .. ..$ theta: num [1:4] -0.8185 -0.7782 0.6997 -0.0773
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.001774 -0.007329 -0.001108 0.003741 -0.000463 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] 0.413 0.735 -0.579 0 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.8185 -0.7782 0.6997 -0.0773 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -0.8185 -0.7782 0.6997 -0.0773 ...
  .. ..$ bic      : num -4618
  .. ..$ aicc     : num -4653
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 9333 7407 7361 7806 10329 8902 9645 8494 8956 8545 ...
  .. ..$ lambda   : atomic [1:1] -0.327
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 8816 9039 7675 7499 8260 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 10797 10250 9612 9648 9495 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 9321 8669 8088 8110 7988 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 12600 12238 11542 11597 11402 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 9333 7407 7361 7806 10329 8902 9645 8494 8956 8545 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 8816 9039 7675 7499 8260 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00291 -0.0105 -0.00226 0.00216 0.01133 ...
  ..- attr(*, "class")= chr "forecast"
 $ 37  :List of 10
  ..$ method   : chr "ARIMA(5,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] 1.0434 0.0155 -0.1624 -0.5294 0.2092 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.268
  .. ..$ var.coef : num [1:10, 1:10] 0.00781 -0.01119 0.00195 0.00533 -0.00197 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -590
  .. ..$ aic      : num 1201
  .. ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.1294 -0.0335 0.0924 0.5916 -0.1065 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(15.0165212979815,  14.9118294896086, 14.96645| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 780
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] 1.0434 0.0155 -0.1624 -0.5294 0.2092
  .. .. ..$ theta: num [1:4] -0.428 -0.341 -0.14 0.686
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 0.7336 -0.5555 -0.3923 -0.0795 0.3652
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] 1.0434 0.0155 -0.1624 -0.5294 0.2092 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.428 -0.341 -0.14 0.686 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 -0.428 -0.341 -0.14 0.686 ...
  .. ..$ bic      : num 1252
  .. ..$ aicc     : num 1201
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 7369 7081 7230 8922 7795 7143 6760 7900 7967 8828 ...
  .. ..$ lambda   : atomic [1:1] 0.109
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 7015 7172 6980 7140 8114 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 7469 6479 5991 5817 5917 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 5785 4774 4353 4222 4293 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 9576 8707 8156 7928 8069 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 7369 7081 7230 8922 7795 7143 6760 7900 7967 8828 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 7015 7172 6980 7140 8114 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.1294 -0.0335 0.0924 0.5916 -0.1065 ...
  ..- attr(*, "class")= chr "forecast"
 $ 38  :List of 10
  ..$ method   : chr "ARIMA(3,0,2) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:6] 2.161 -1.738 0.437 -1.585 0.821 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 0.000105
  .. ..$ var.coef : num [1:6, 1:6] 0.00317 -0.00518 0.00276 -0.00192 0.00141 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 2465
  .. ..$ aic      : num -4917
  .. ..$ arma     : int [1:7] 3 2 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -0.00816 -0.00979 -0.0034 0.00473 0.02306 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.72457039291493,  2.71795170391307, 2.720684| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 2.161 -1.738 0.437
  .. .. ..$ theta: num [1:2] -1.585 0.821
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:3] 1 0 0
  .. .. ..$ a    : num [1:3] 0.013 -0.0241 0.011
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 0.00 0.00 4.44e-16 ...
  .. .. ..$ T    : num [1:3, 1:3] 2.161 -1.738 0.437 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -1.585 0.821 -1.585 2.513 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1 -1.585 0.821 -1.585 2.513 ...
  .. ..$ bic      : num -4884
  .. ..$ aicc     : num -4917
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4506 3995 4196 5233 9738 6773 6224 6155 5890 5347 ...
  .. ..$ lambda   : atomic [1:1] -0.347
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 5265 4782 4466 4777 5839 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 6122 5309 4839 4658 4734 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4724 3998 3638 3508 3560 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 8139 7270 6642 6380 6497 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4506 3995 4196 5233 9738 6773 6224 6155 5890 5347 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 5265 4782 4466 4777 5839 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.00816 -0.00979 -0.0034 0.00473 0.02306 ...
  ..- attr(*, "class")= chr "forecast"
 $ 39  :List of 10
  ..$ method   : chr "ARIMA(1,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] 0.254 -0.989
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  .. ..$ sigma2   : num 1.26e-08
  .. ..$ var.coef : num [1:2, 1:2] 1.24e-03 -3.09e-05 -3.09e-05 2.76e-05
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 6017
  .. ..$ aic      : num -12028
  .. ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.03e-03 -4.39e-05 -1.07e-05 -1.65e-04 2.72e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.03465933671525,  1.03460354872205, 1.034611| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num 0.254
  .. .. ..$ theta: num -0.989
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 7.34e-05 -1.16e-04 1.03
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 8.85e-17 0.00 5.02e-10 ...
  .. .. ..$ T    : num [1:3, 1:3] 0.254 0 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.989 0 -0.989 0.978 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.89e-01 3.27e-17 -9.89e-01 9.78e-01 ...
  .. ..$ bic      : num -12014
  .. ..$ aicc     : num -12028
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4144 3527 3604 2435 9136 5510 4154 5120 4766 2398 ...
  .. ..$ lambda   : atomic [1:1] -0.966
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 956 3996 3712 3517 3193 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5198 4741 4637 4611 4605 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 3324 3091 3043 3031 3028 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 11625 9953 9545 9443 9419 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4144 3527 3604 2435 9136 5510 4154 5120 4766 2398 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 956 3996 3712 3517 3193 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.03e-03 -4.39e-05 -1.07e-05 -1.65e-04 2.72e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 40  :List of 10
  ..$ method   : chr "ARIMA(3,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:5] -0.193 0.525 -0.115 -0.178 -0.77
  .. .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 5.58e+10
  .. ..$ var.coef : num [1:5, 1:5] 4.17e-03 -1.85e-05 -1.09e-03 -3.06e-03 2.17e-03 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num -10687
  .. ..$ aic      : num 21386
  .. ..$ arma     : int [1:7] 3 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:776] from 1 to 776: 724 -35936 -51034 265100 419849 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(724164.557066078,  683292.278005351, 636276.8| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 775
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] -0.193 0.525 -0.115
  .. .. ..$ theta: num [1:2] -0.178 -0.77
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 76412 -87973 -122599 862235
  .. .. ..$ P    : num [1:4, 1:4] 0.00 2.78e-17 0.00 5.57e-17 2.78e-17 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.193 0.525 -0.115 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.178 -0.77 0 -0.178 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.78e-01 -7.70e-01 1.98e-17 -1.78e-01 ...
  .. ..$ bic      : num 21413
  .. ..$ aicc     : num 21386
  .. ..$ x        : Time-Series [1:776] from 1 to 776: 4672 4511 4321 5479 6735 5524 4498 5685 4882 4867 ...
  .. ..$ lambda   : atomic [1:1] 1.66
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:776] from 1 to 776: 4669 4653 4527 4489 5354 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 777 to 823: 5095 4861 4666 4622 4554 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 777 to 823: 3884 3342 2958 2878 2763 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 777 to 823: 6140 6114 6032 6007 5964 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:776] from 1 to 776: 4672 4511 4321 5479 6735 5524 4498 5685 4882 4867 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:776] from 1 to 776: 4669 4653 4527 4489 5354 ...
  ..$ residuals: Time-Series [1:776] from 1 to 776: 724 -35936 -51034 265100 419849 ...
  ..- attr(*, "class")= chr "forecast"
 $ 41  :List of 10
  ..$ method   : chr "ARIMA(1,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] 0.521 -0.976
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  .. ..$ sigma2   : num 2.25e-06
  .. ..$ var.coef : num [1:2, 1:2] 1.29e-03 -7.98e-05 -7.98e-05 5.66e-05
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 3158
  .. ..$ aic      : num -6310
  .. ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00176 -0.000488 0.000532 -0.001111 0.001414 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.7604658935845,  1.75991220806412, 1.7606294| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num 0.521
  .. .. ..$ theta: num -0.976
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 0.000669 -0.000969 1.763244
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 2.14e-21 0.00 3.33e-15 ...
  .. .. ..$ T    : num [1:3, 1:3] 0.521 0 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.976 0 -0.976 0.953 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.76e-01 5.11e-22 -9.76e-01 9.53e-01 ...
  .. ..$ bic      : num -6297
  .. ..$ aicc     : num -6310
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 4461 4194 4545 3940 4839 4860 4128 4303 4044 4219 ...
  .. ..$ lambda   : atomic [1:1] -0.563
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 3692 4428 4281 4449 4122 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 6353 6079 5943 5874 5839 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 4959 4626 4497 4438 4410 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 8473 8395 8274 8195 8151 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 4461 4194 4545 3940 4839 4860 4128 4303 4044 4219 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 3692 4428 4281 4449 4122 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00176 -0.000488 0.000532 -0.001111 0.001414 ...
  ..- attr(*, "class")= chr "forecast"
 $ 42  :List of 10
  ..$ method   : chr "ARIMA(3,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.707 0.702 -0.928 -1.32 -0.373 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 1.61e-09
  .. ..$ var.coef : num [1:8, 1:8] 0.000586 -0.000146 -0.000216 -0.000617 0.000348 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7410
  .. ..$ aic      : num -14802
  .. ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.35e-05 1.30e-05 -6.32e-07 4.76e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99995001860758,  0.99993124553275, 0.999954| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.707 0.702 -0.928
  .. .. ..$ theta: num [1:5] -1.32 -0.373 1.256 -0.353 -0.188
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 8.44e-06 -2.73e-05 1.76e-05 -2.56e-06 -1.93e-06 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 -2.22e-16 -1.67e-16 2.22e-16 -1.11e-16 ...
  .. .. ..$ T    : num [1:7, 1:7] 0.707 0.702 -0.928 0 0 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -1.32 -0.373 1.256 -0.353 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -1.32 -0.373 1.256 -0.353 ...
  .. ..$ bic      : num -14760
  .. ..$ aicc     : num -14802
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 7959 6925 8273 7587 14737 12216 10569 10298 10841 7648 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 889 7638 7472 7624 8660 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 9521 10352 8622 9441 8325 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 6391 6589 5779 6126 5624 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 18655 24125 16964 20569 16012 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 7959 6925 8273 7587 14737 12216 10569 10298 10841 7648 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 889 7638 7472 7624 8660 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.35e-05 1.30e-05 -6.32e-07 4.76e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 43  :List of 10
  ..$ method   : chr "ARIMA(2,0,2) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:5] 1.674 -0.941 -1.535 0.828 2.651
  .. .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 0.000124
  .. ..$ var.coef : num [1:5, 1:5] 8.67e-04 -6.07e-04 -1.19e-03 4.92e-04 -1.14e-07 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 2399
  .. ..$ aic      : num -4787
  .. ..$ arma     : int [1:7] 2 2 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -0.001308 -0.004115 0.000679 -0.008731 0.024988 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.64973842926548,  2.64649194153076, 2.650717| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] 1.674 -0.941
  .. .. ..$ theta: num [1:2] -1.535 0.828
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:3] 1 0 0
  .. .. ..$ a    : num [1:3] 0.00913 -0.01388 0.00509
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 0.00 0.00 2.66e-15 ...
  .. .. ..$ T    : num [1:3, 1:3] 1.674 -0.941 0 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -1.535 0.828 -1.535 2.356 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1 -1.535 0.828 -1.535 2.356 ...
  .. ..$ bic      : num -4759
  .. ..$ aicc     : num -4787
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 6243 5790 6389 5167 12218 8600 7918 8132 8246 5308 ...
  .. ..$ lambda   : atomic [1:1] -0.361
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 6439 6372 6287 6303 6296 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 6678 6284 5984 5832 5847 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4827 4559 4355 4254 4263 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 9647 9034 8567 8329 8353 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 6243 5790 6389 5167 12218 8600 7918 8132 8246 5308 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6439 6372 6287 6303 6296 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.001308 -0.004115 0.000679 -0.008731 0.024988 ...
  ..- attr(*, "class")= chr "forecast"
 $ 44  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.525 0.256 0.581 0.127 -0.607 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 3.14e-09
  .. ..$ var.coef : num [1:10, 1:10] 0.001882 0.002089 0.000882 -0.000658 -0.000917 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 6764
  .. ..$ aic      : num -13505
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -2.66e-05 6.53e-06 -2.51e-05 1.06e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999861287801532,  0.999816037499558, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.525 0.256 0.581 0.127 -0.607
  .. .. ..$ theta: num [1:5] -0.1399 -0.6784 -0.6743 0.0232 0.5578
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 4.39e-05 -1.03e-04 3.66e-05 -1.65e-05 -2.51e-06 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 -6.94e-18 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.525 0.256 0.581 0.127 -0.607 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.1399 -0.6784 -0.6743 0.0232 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.1399 -0.6784 -0.6743 0.0232 ...
  .. ..$ bic      : num -13454
  .. ..$ aicc     : num -13505
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 4666 3853 4407 3652 9818 6149 6284 5397 6699 3195 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 824 4292 4284 4020 4808 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 3623 6173 4079 4123 4441 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 2875 4207 3094 3119 3294 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 4897 11591 5984 6080 6813 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 4666 3853 4407 3652 9818 6149 6284 5397 6699 3195 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 824 4292 4284 4020 4808 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -2.66e-05 6.53e-06 -2.51e-05 1.06e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 45  :List of 10
  ..$ method   : chr "ARIMA(3,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 2.125 -1.679 0.402 -1.522 0.716 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 4.09
  .. ..$ var.coef : num [1:7, 1:7] 0.00998 -0.01658 0.00905 -0.00973 0.01257 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -1651
  .. ..$ aic      : num 3318
  .. ..$ arma     : int [1:7] 3 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -1.605 -0.55 0.548 0.7 1.795 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(33.4709980204569,  33.7068725783257, 35.11697| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 2.125 -1.679 0.402
  .. .. ..$ theta: num [1:3] -1.522 0.716 0.09
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:4] 1 0 0 0
  .. .. ..$ a    : num [1:4] 2.096 -3.814 1.636 0.109
  .. .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:4, 1:4] 2.125 -1.679 0.402 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -1.522 0.716 0.09 -1.522 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1 -1.522 0.716 0.09 -1.522 ...
  .. ..$ bic      : num 3355
  .. ..$ aicc     : num 3318
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4270 4368 4988 5566 6616 5518 5235 5955 5868 5455 ...
  .. ..$ lambda   : atomic [1:1] 0.28
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 4969 4603 4740 5225 5657 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5542 4984 4664 4554 4637 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4358 3725 3427 3330 3396 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 6942 6524 6193 6072 6176 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4270 4368 4988 5566 6616 5518 5235 5955 5868 5455 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 4969 4603 4740 5225 5657 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -1.605 -0.55 0.548 0.7 1.795 ...
  ..- attr(*, "class")= chr "forecast"
 $ 46  :List of 10
  ..$ method   : chr "ARIMA(4,0,2) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 2.1663 -1.7123 0.3741 0.0384 -1.6138 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.34e-09
  .. ..$ var.coef : num [1:7, 1:7] 0.003253 -0.005572 0.00328 -0.000178 -0.001652 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 5473
  .. ..$ aic      : num -10930
  .. ..$ arma     : int [1:7] 4 2 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: -3.09e-05 -5.39e-06 -1.68e-05 1.39e-05 6.14e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999826578144851,  0.999836181905615, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 622
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] 2.1663 -1.7123 0.3741 0.0384
  .. .. ..$ theta: num [1:3] -1.614 0.847 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:4] 1 0 0 0
  .. .. ..$ a    : num [1:4] 7.11e-05 -1.39e-04 6.94e-05 2.32e-06
  .. .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:4, 1:4] 2.1663 -1.7123 0.3741 0.0384 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -1.614 0.847 0 -1.614 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1 -1.614 0.847 0 -1.614 ...
  .. ..$ bic      : num -10895
  .. ..$ aicc     : num -10930
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 4016 4177 4125 4848 7788 5793 5501 5503 5985 4857 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 4585 4273 4431 4542 5269 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 5347 4511 4141 4073 4247 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 4275 3633 3364 3314 3428 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 7139 5950 5387 5284 5580 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 4016 4177 4125 4848 7788 5793 5501 5503 5985 4857 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 4585 4273 4431 4542 5269 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: -3.09e-05 -5.39e-06 -1.68e-05 1.39e-05 6.14e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 47  :List of 10
  ..$ method   : chr "ARIMA(2,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] -0.4613 0.5046 -0.0864 -0.8942
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. ..$ sigma2   : num 4.78e-09
  .. ..$ var.coef : num [1:4, 1:4] 0.001195 0.000963 -0.000321 0.000262 0.000963 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ma1" "ma2"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 6539
  .. ..$ aic      : num -13069
  .. ..$ arma     : int [1:7] 2 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.09e-03 -1.28e-05 -3.70e-05 -8.83e-06 1.31e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.08503141131099,  1.08501475430077, 1.084979| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] -0.461 0.505
  .. .. ..$ theta: num [1:2] -0.0864 -0.8942
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 5.13e-05 -2.90e-05 -3.50e-05 1.09
  .. .. ..$ P    : num [1:4, 1:4] 0.00 -1.39e-17 0.00 -1.29e-16 -1.39e-17 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.461 0.505 0 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.0864 -0.8942 0 -0.0864 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.64e-02 -8.94e-01 -7.05e-17 -8.64e-02 ...
  .. ..$ bic      : num -13045
  .. ..$ aicc     : num -13069
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 6538 6199 5580 5673 9881 8729 9057 7493 7409 5021 ...
  .. ..$ lambda   : atomic [1:1] -0.921
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 1351 6457 6230 5821 6022 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 7546 8000 7059 7683 6950 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 5652 5760 5190 5522 5115 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 11202 12840 10860 12379 10670 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 6538 6199 5580 5673 9881 8729 9057 7493 7409 5021 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 1351 6457 6230 5821 6022 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.09e-03 -1.28e-05 -3.70e-05 -8.83e-06 1.31e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 48  :List of 10
  ..$ method   : chr "ARIMA(4,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] -1.4399 -0.9305 0.0325 0.471 0.7411 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.00202
  .. ..$ var.coef : num [1:8, 1:8] 0.0023 0.00384 0.00352 0.00143 -0.0016 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 1321
  .. ..$ aic      : num -2623
  .. ..$ arma     : int [1:7] 4 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 0.00439 -0.00403 0.00528 -0.0347 0.10403 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.38747211180177,  4.38154588494194, 4.391271| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] -1.4399 -0.9305 0.0325 0.471
  .. .. ..$ theta: num [1:4] 0.7411 -0.0842 -0.8202 -0.6943
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.03867 -0.01492 0.01338 -0.00474 -0.01135 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] -1.4399 -0.9305 0.0325 0.471 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 0.7411 -0.0842 -0.8202 -0.6943 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 0.7411 -0.0842 -0.8202 -0.6943 ...
  .. ..$ bic      : num -2581
  .. ..$ aicc     : num -2623
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 4091 3989 4158 3418 6718 5460 4393 4657 4648 3831 ...
  .. ..$ lambda   : atomic [1:1] -0.175
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 4015 4058 4065 3953 4220 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 2896 4015 3237 3308 3443 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 2308 3126 2520 2566 2662 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 3667 5217 4205 4317 4507 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 4091 3989 4158 3418 6718 5460 4393 4657 4648 3831 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 4015 4058 4065 3953 4220 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.00439 -0.00403 0.00528 -0.0347 0.10403 ...
  ..- attr(*, "class")= chr "forecast"
 $ 49  :List of 10
  ..$ method   : chr "ARIMA(1,1,0) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:2] -0.170606 0.000018
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "drift"
  .. ..$ sigma2   : num 2.19e-05
  .. ..$ var.coef : num [1:2, 1:2] 1.25e-03 -4.55e-09 -4.55e-09 2.18e-08
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "drift"
  .. .. .. ..$ : chr [1:2] "ar1" "drift"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 3063
  .. ..$ aic      : num -6120
  .. ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 0.00233 -0.0066 0.00249 0.00395 0.01 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.33029819523373,  2.32361437548974, 2.327269| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.171
  .. .. ..$ theta: num(0) 
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:2] 1 1
  .. .. ..$ a    : num [1:2] 0.00294 2.32678
  .. .. ..$ P    : num [1:2, 1:2] 0.00 -8.81e-21 -8.81e-21 8.81e-21
  .. .. ..$ T    : num [1:2, 1:2] -0.171 1 0 1
  .. .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:2, 1:2] 1.00 -1.50e-21 -1.50e-21 8.81e-21
  .. ..$ xreg     : int [1:777, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num -6106
  .. ..$ aicc     : num -6120
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 5866 4622 5250 5937 8731 7290 6532 6399 7062 6127 ...
  .. ..$ lambda   : atomic [1:1] -0.418
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 5384 5848 4809 5138 5816 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 10077 10127 10128 10138 10146 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 7720 7198 6764 6429 6150 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 13601 15080 16465 17801 19125 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 5866 4622 5250 5937 8731 7290 6532 6399 7062 6127 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 5384 5848 4809 5138 5816 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.00233 -0.0066 0.00249 0.00395 0.01 ...
  ..- attr(*, "class")= chr "forecast"
 $ 50  :List of 10
  ..$ method   : chr "ARIMA(0,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] -0.1307 -0.0502
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  .. ..$ sigma2   : num 0.00438
  .. ..$ var.coef : num [1:2, 1:2] 0.001405 0.000364 0.000364 0.001791
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 1010
  .. ..$ aic      : num -2014
  .. ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00472 -0.03346 0.02655 0.04518 0.10729 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.72296932495699,  4.68918552235314, 4.719910| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num [1:2] -0.1307 -0.0502
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 0.02004 -0.00365 -0.00109 4.81776
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -4.25e-21 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.1307 -0.0502 0 -0.1307 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.31e-01 -5.02e-02 -3.17e-22 -1.31e-01 ...
  .. ..$ bic      : num -2000
  .. ..$ aicc     : num -2014
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 3804 3388 3764 4380 6298 4734 3615 4176 4608 4395 ...
  .. ..$ lambda   : atomic [1:1] -0.151
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 3742 3800 3436 3741 4270 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 5653 5630 5630 5630 5630 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4170 3775 3527 3327 3159 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 7775 8616 9311 9968 10603 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 3804 3388 3764 4380 6298 4734 3615 4176 4608 4395 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 3742 3800 3436 3741 4270 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00472 -0.03346 0.02655 0.04518 0.10729 ...
  ..- attr(*, "class")= chr "forecast"
 $ 51  :List of 10
  ..$ method   : chr "ARIMA(3,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] 0.679 -0.1899 -0.0934 -0.9795
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ sigma2   : num 1.68e-07
  .. ..$ var.coef : num [1:4, 1:4] 0.001693 -0.001121 0.000505 -0.000113 -0.001121 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 3969
  .. ..$ aic      : num -7929
  .. ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 1.45e-03 -2.89e-04 7.38e-04 5.01e-05 5.03e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.44736492544213,  1.44702864613274, 1.447894| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.679 -0.1899 -0.0934
  .. .. ..$ theta: num [1:2] -0.98 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 2.03e-04 -3.84e-04 -1.81e-05 1.45
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 2.28e-20 -2.44e-19 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 0.679 -0.1899 -0.0934 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.98 0 0 -0.98 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.80e-01 0.00 -1.38e-20 -9.80e-01 ...
  .. ..$ bic      : num -7907
  .. ..$ aicc     : num -7929
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 5152 4585 6323 6605 8125 6233 4729 6503 7322 6079 ...
  .. ..$ lambda   : atomic [1:1] -0.689
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 3297 5065 4787 6466 6458 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 8100 7282 6887 6830 6926 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 6383 5573 5281 5244 5302 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 10775 10111 9534 9436 9614 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 5152 4585 6323 6605 8125 6233 4729 6503 7322 6079 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 3297 5065 4787 6466 6458 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 1.45e-03 -2.89e-04 7.38e-04 5.01e-05 5.03e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 52  :List of 10
  ..$ method   : chr "ARIMA(3,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 2.154 -1.73 0.428 -2.612 2.479 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 1.06e-07
  .. ..$ var.coef : num [1:7, 1:7] 0.0156 -0.0265 0.0149 -0.0159 0.0383 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 4116
  .. ..$ aic      : num -8215
  .. ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 1.39e-03 -7.97e-05 3.64e-05 4.24e-05 4.19e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.39264283129069,  1.39254729369268, 1.392602| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 2.154 -1.73 0.428
  .. .. ..$ theta: num [1:4] -2.611922 2.478928 -0.859129 0.000149
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 2.23e-04 -8.15e-04 8.79e-04 -3.12e-04 5.40e-08 ...
  .. .. ..$ P    : num [1:6, 1:6] 1.11e-16 -8.88e-16 4.44e-16 -2.22e-16 2.71e-20 ...
  .. .. ..$ T    : num [1:6, 1:6] 2.154 -1.73 0.428 0 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -2.611922 2.478928 -0.859129 0.000149 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -2.611922 2.478928 -0.859129 0.000149 ...
  .. ..$ bic      : num -8180
  .. ..$ aicc     : num -8215
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 7176 6796 7011 7211 9928 8195 7530 7311 8929 8003 ...
  .. ..$ lambda   : atomic [1:1] -0.717
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 3792 7111 6868 7036 7520 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 6604 5865 5513 5453 5645 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 5344 4705 4431 4383 4514 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 8477 7621 7143 7066 7370 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 7176 6796 7011 7211 9928 8195 7530 7311 8929 8003 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 3792 7111 6868 7036 7520 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 1.39e-03 -7.97e-05 3.64e-05 4.24e-05 4.19e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 53  :List of 10
  ..$ method   : chr "ARIMA(5,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] -1.342 -0.777 0.148 0.5 -0.044 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.00322
  .. ..$ var.coef : num [1:9, 1:9] 0.00333 0.00375 0.00135 -0.00183 -0.00215 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 1140
  .. ..$ aic      : num -2259
  .. ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 0.0127 -0.0148 -0.0163 -0.092 0.1247 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.68671096931498,  4.65611696982447, 4.652481| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 784
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.342 -0.777 0.148 0.5 -0.044
  .. .. ..$ theta: num [1:4] 1.708 1.593 0.733 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 0.10059 0.08453 0.08447 0.04389 -0.00331
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -1.342 -0.777 0.148 0.5 -0.044 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 1.708 1.593 0.733 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 1.708 1.593 0.733 0 ...
  .. ..$ bic      : num -2213
  .. ..$ aicc     : num -2259
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5367 4767 4701 3298 8330 5576 5241 5640 5283 3510 ...
  .. ..$ lambda   : atomic [1:1] -0.159
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 5107 5047 5006 4644 5040 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 4161 6761 5019 4736 5125 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 3184 4975 3696 3487 3755 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 5502 9334 6922 6535 7107 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5367 4767 4701 3298 8330 5576 5241 5640 5283 3510 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5107 5047 5006 4644 5040 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.0127 -0.0148 -0.0163 -0.092 0.1247 ...
  ..- attr(*, "class")= chr "forecast"
 $ 54  :List of 10
  ..$ method   : chr "ARIMA(5,0,2) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] -0.482 -0.236 0.347 -0.111 -0.189 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.00688
  .. ..$ var.coef : num [1:8, 1:8] 0.003212 0.000247 0.000219 -0.000537 -0.000334 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 844
  .. ..$ aic      : num -1670
  .. ..$ arma     : int [1:7] 5 2 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:785] from 1 to 785: -0.0321 -0.0307 0.0329 0.0376 0.0301 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(5.69706275003294,  5.68348963765527, 5.742385| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 785
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.482 -0.236 0.347 -0.111 -0.189
  .. .. ..$ theta: num [1:4] 1.08 0.844 0 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 0.1288 0.1127 0.0843 -0.0244 -0.0188
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -0.482 -0.236 0.347 -0.111 -0.189 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 1.08 0.844 0 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 1.08 0.844 0 0 ...
  .. ..$ bic      : num -1628
  .. ..$ aicc     : num -1670
  .. ..$ x        : Time-Series [1:785] from 1 to 785: 6868 6631 7730 8628 9019 7571 7556 7181 7831 9073 ...
  .. ..$ lambda   : atomic [1:1] -0.108
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:785] from 1 to 785: 7468 7181 7094 7811 8325 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 786 to 832: 8699 8225 7493 7230 7434 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 786 to 832: 6585 5962 5386 5202 5344 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 786 to 832: 11590 11477 10551 10170 10469 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:785] from 1 to 785: 6868 6631 7730 8628 9019 7571 7556 7181 7831 9073 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:785] from 1 to 785: 7468 7181 7094 7811 8325 ...
  ..$ residuals: Time-Series [1:785] from 1 to 785: -0.0321 -0.0307 0.0329 0.0376 0.0301 ...
  ..- attr(*, "class")= chr "forecast"
 $ 55  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.517 0.267 0.633 0.185 -0.539 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.00542
  .. ..$ var.coef : num [1:10, 1:10] 0.002444 0.002235 0.000923 -0.001113 -0.000883 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 930
  .. ..$ aic      : num -1838
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00478 -0.02186 0.01778 -0.04486 0.12347 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.78360766389403,  4.75111864424898, 4.790174| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.517 0.267 0.633 0.185 -0.539
  .. .. ..$ theta: num [1:5] -0.1947 -0.6593 -0.6698 0.0419 0.589
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 0.0227 -0.1146 0.0298 0.0055 -0.0166 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 6.94e-18 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.517 0.267 0.633 0.185 -0.539 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.1947 -0.6593 -0.6698 0.0419 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.1947 -0.6593 -0.6698 0.0419 ...
  .. ..$ bic      : num -1787
  .. ..$ aicc     : num -1838
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 4516 4031 4622 3583 7164 6212 6439 6454 5619 3652 ...
  .. ..$ lambda   : atomic [1:1] -0.15
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 4441 4350 4341 4182 4563 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 3885 5559 4388 3936 4611 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 2828 3925 3103 2797 3249 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 5423 8025 6325 5640 6672 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 4516 4031 4622 3583 7164 6212 6439 6454 5619 3652 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 4441 4350 4341 4182 4563 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00478 -0.02186 0.01778 -0.04486 0.12347 ...
  ..- attr(*, "class")= chr "forecast"
 $ 56  :List of 10
  ..$ method   : chr "ARIMA(1,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] 0.197 -0.459 -0.263 -0.23
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. ..$ sigma2   : num 2.23
  .. ..$ var.coef : num [1:4, 1:4] 0.02321 -0.02283 0.00938 0.01158 -0.02283 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num -1419
  .. ..$ aic      : num 2847
  .. ..$ arma     : int [1:7] 1 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:781] from 1 to 781: 0.0305 1.2525 -0.6342 0.4916 3.1316 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(30.4936873444812,  31.8976962991993, 31.10854| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 780
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num 0.197
  .. .. ..$ theta: num [1:3] -0.459 -0.263 -0.23
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] 1.365 -0.905 -0.368 -0.334 34.297
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -5.82e-21 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.197 0 0 0 1 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.459 -0.263 -0.23 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -4.59e-01 -2.63e-01 -2.30e-01 -9.39e-22 ...
  .. ..$ bic      : num 2871
  .. ..$ aicc     : num 2848
  .. ..$ x        : Time-Series [1:781] from 1 to 781: 5715 6710 6136 6384 8954 8523 6931 6999 7030 7210 ...
  .. ..$ lambda   : atomic [1:1] 0.248
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:781] from 1 to 781: 5695 5817 6594 6035 6369 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 782 to 828: 9390 8922 8527 8451 8436 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 782 to 828: 7670 6905 6481 6410 6395 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 782 to 828: 11386 11353 11025 10946 10932 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:781] from 1 to 781: 5715 6710 6136 6384 8954 8523 6931 6999 7030 7210 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 5695 5817 6594 6035 6369 ...
  ..$ residuals: Time-Series [1:781] from 1 to 781: 0.0305 1.2525 -0.6342 0.4916 3.1316 ...
  ..- attr(*, "class")= chr "forecast"
 $ 57  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.4035 0.3358 0.5964 0.0486 -0.5948 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.05e-07
  .. ..$ var.coef : num [1:10, 1:10] 0.003849 0.002297 0.0002 -0.002776 -0.000866 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 5095
  .. ..$ aic      : num -10168
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:769] from 1 to 769: 1.40e-03 -6.54e-05 -7.61e-06 -2.75e-04 6.86e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.39506976731438,  1.39497537299736, 1.395006| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 768
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.4035 0.3358 0.5964 0.0486 -0.5948
  .. .. ..$ theta: num [1:5] -0.1943 -0.6187 -0.5508 0.0842 0.3966
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 2.17e-04 -5.60e-04 1.06e-04 -8.30e-05 -2.46e-05 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 -1.39e-17 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.4035 0.3358 0.5964 0.0486 -0.5948 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.1943 -0.6187 -0.5508 0.0842 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.1943 -0.6187 -0.5508 0.0842 ...
  .. ..$ bic      : num -10117
  .. ..$ aicc     : num -10168
  .. ..$ x        : Time-Series [1:769] from 1 to 769: 10719 9988 10222 8112 19314 14203 11842 12947 12230 7309 ...
  .. ..$ lambda   : atomic [1:1] -0.716
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:769] from 1 to 769: 4841 10485 10280 9756 10241 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 770 to 816: 7419 9887 7839 7330 8145 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 770 to 816: 5923 7390 6028 5676 6192 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 770 to 816: 9707 14287 10837 10028 11459 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:769] from 1 to 769: 10719 9988 10222 8112 19314 14203 11842 12947 12230 7309 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:769] from 1 to 769: 4841 10485 10280 9756 10241 ...
  ..$ residuals: Time-Series [1:769] from 1 to 769: 1.40e-03 -6.54e-05 -7.61e-06 -2.75e-04 6.86e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 58  :List of 10
  ..$ method   : chr "ARIMA(2,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:5] 1.682 -0.945 -2.334 1.974 -0.623
  .. .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 2.43e-09
  .. ..$ var.coef : num [1:5, 1:5] 0.000376 -0.000348 -0.000682 0.001235 -0.000543 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 5630
  .. ..$ aic      : num -11249
  .. ..$ arma     : int [1:7] 2 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:623] from 1 to 623: 1.00e-03 -2.06e-05 1.28e-05 1.41e-05 8.90e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.99984352041338,  0.999816843813967, 0.99983| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 622
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] 1.682 -0.945
  .. .. ..$ theta: num [1:3] -2.334 1.974 -0.623
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] 2.05e-06 -3.28e-05 3.73e-05 -1.36e-05 1.00
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -1.14e-17 ...
  .. .. ..$ T    : num [1:5, 1:5] 1.682 -0.945 0 0 1 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -2.334 1.974 -0.623 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -2.33 1.97 -6.23e-01 -4.43e-18 ...
  .. ..$ bic      : num -11222
  .. ..$ aicc     : num -11249
  .. ..$ x        : Time-Series [1:623] from 1 to 623: 4309 3865 4239 4452 8439 6704 5385 5833 5863 4585 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:623] from 1 to 623: 812 4199 4021 4189 4820 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 624 to 670: 6854 6251 5900 5806 5958 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 624 to 670: 4785 4410 4191 4131 4207 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 624 to 670: 12072 10732 9959 9764 10202 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:623] from 1 to 623: 4309 3865 4239 4452 8439 6704 5385 5833 5863 4585 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:623] from 1 to 623: 812 4199 4021 4189 4820 ...
  ..$ residuals: Time-Series [1:623] from 1 to 623: 1.00e-03 -2.06e-05 1.28e-05 1.41e-05 8.90e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 59  :List of 10
  ..$ method   : chr "ARIMA(5,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] -1.2585 -0.923 -0.2913 -0.0302 -0.3048 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 44.5
  .. ..$ var.coef : num [1:9, 1:9] 0.00532 0.00604 0.00282 -0.00222 -0.00259 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -2590
  .. ..$ aic      : num 5200
  .. ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:782] from 1 to 782: -0.339 -1.9752 0.0961 -12.3348 9.494 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(57.1483602396751,  55.2025019258398, 57.74530| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 782
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.2585 -0.923 -0.2913 -0.0302 -0.3048
  .. .. ..$ theta: num [1:4] 1.41 1.262 0.541 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 6.947 1.683 3.812 2.985 -0.345
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -1.2585 -0.923 -0.2913 -0.0302 -0.3048 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 1.41 1.262 0.541 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 1.41 1.262 0.541 0 ...
  .. ..$ bic      : num 5247
  .. ..$ aicc     : num 5200
  .. ..$ x        : Time-Series [1:782] from 1 to 782: 5177 4722 5322 2384 8744 6252 6991 5798 5963 2273 ...
  .. ..$ lambda   : atomic [1:1] 0.359
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:782] from 1 to 782: 5259 5184 5298 4660 5907 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 783 to 829: 3730 6954 5171 4411 5622 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 783 to 829: 2291 4721 3333 2760 3659 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 783 to 829: 5646 9769 7557 6588 8155 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:782] from 1 to 782: 5177 4722 5322 2384 8744 6252 6991 5798 5963 2273 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 5259 5184 5298 4660 5907 ...
  ..$ residuals: Time-Series [1:782] from 1 to 782: -0.339 -1.9752 0.0961 -12.3348 9.494 ...
  ..- attr(*, "class")= chr "forecast"
 $ 60  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.645 0.0718 0.5087 0.1867 -0.5071 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.000103
  .. ..$ var.coef : num [1:10, 1:10] 0.003802 0.004805 0.002939 -0.000551 -0.001618 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 2473
  .. ..$ aic      : num -4924
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0026 -0.00446 -0.00131 -0.0182 0.02265 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.60341003648283,  2.59661552104264, 2.598151| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.645 0.0718 0.5087 0.1867 -0.5071
  .. .. ..$ theta: num [1:5] -0.0471 -0.5965 -0.7541 -0.0729 0.5424
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] -0.00151 -0.01694 0.00521 0.00229 -0.00017 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 -6.94e-18 0.00 0.00 0.00 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.645 0.0718 0.5087 0.1867 -0.5071 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.0471 -0.5965 -0.7541 -0.0729 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.0471 -0.5965 -0.7541 -0.0729 ...
  .. ..$ bic      : num -4873
  .. ..$ aicc     : num -4923
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 6759 5697 5916 3505 10344 8969 7225 7500 6717 3870 ...
  .. ..$ lambda   : atomic [1:1] -0.369
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 6322 6366 6112 5222 5602 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 6302 9598 7337 7087 8616 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 4619 6596 5173 5017 5945 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 8953 14839 10961 10530 13247 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 6759 5697 5916 3505 10344 8969 7225 7500 6717 3870 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 6322 6366 6112 5222 5602 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0026 -0.00446 -0.00131 -0.0182 0.02265 ...
  ..- attr(*, "class")= chr "forecast"
 $ 61  :List of 10
  ..$ method   : chr "ARIMA(3,1,2) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:6] -0.394 0.46 -0.052 -0.112 -0.865 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 1.75
  .. ..$ var.coef : num [1:6, 1:6] 0.005318 -0.000748 -0.00179 -0.004107 0.004012 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num -1316
  .. ..$ aic      : num 2646
  .. ..$ arma     : int [1:7] 3 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 0.0248 -1.4893 0.0386 0.5759 1.5933 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(24.7590071063863,  23.012668657777, 23.564689| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] -0.394 0.46 -0.052
  .. .. ..$ theta: num [1:2] -0.112 -0.865
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] -0.368 -0.802 0.524 24.512
  .. .. ..$ P    : num [1:4, 1:4] 0.00 1.39e-17 0.00 1.48e-16 1.39e-17 ...
  .. .. ..$ T    : num [1:4, 1:4] -0.394 0.46 -0.052 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.112 -0.865 0 -0.112 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -1.12e-01 -8.65e-01 6.95e-17 -1.12e-01 ...
  .. ..$ xreg     : int [1:777, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num 2679
  .. ..$ aicc     : num 2646
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 4233 3221 3518 3923 5127 3982 3727 4144 4125 4115 ...
  .. ..$ lambda   : atomic [1:1] 0.226
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 4217 4070 3497 3586 4042 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 5071 5543 5142 5547 5179 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 3934 4196 3837 4157 3859 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 6447 7201 6766 7271 6824 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 4233 3221 3518 3923 5127 3982 3727 4144 4125 4115 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 4217 4070 3497 3586 4042 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 0.0248 -1.4893 0.0386 0.5759 1.5933 ...
  ..- attr(*, "class")= chr "forecast"
 $ 62  :List of 10
  ..$ method   : chr "ARIMA(1,1,0) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:2] -0.49 0.0297
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "drift"
  .. ..$ sigma2   : num 1414
  .. ..$ var.coef : num [1:2, 1:2] 9.75e-04 -6.40e-06 -6.40e-06 8.17e-01
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "drift"
  .. .. .. ..$ : chr [1:2] "ar1" "drift"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num -3925
  .. ..$ aic      : num 7856
  .. ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.202 -18.102 -7.295 -41.727 90.204 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(201.71438392195,  180.978807919199, 183.88765| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.49
  .. .. ..$ theta: num(0) 
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:2] 1 1
  .. .. ..$ a    : num [1:2] 4.94 190.03
  .. .. ..$ P    : num [1:2, 1:2] 0.0 -3.5e-21 -3.5e-21 3.5e-21
  .. .. ..$ T    : num [1:2, 1:2] -0.49 1 0 1
  .. .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:2, 1:2] 1.00 -1.72e-21 -1.72e-21 3.50e-21
  .. ..$ xreg     : int [1:779, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num 7870
  .. ..$ aicc     : num 7856
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 6484 5303 5462 3332 9812 8443 6253 6760 6806 3690 ...
  .. ..$ lambda   : atomic [1:1] 0.534
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 6472 6328 5870 5386 4317 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 7343 7420 7385 7405 7398 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4596 4360 3807 3511 3186 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 10679 11221 12036 12607 13199 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 6484 5303 5462 3332 9812 8443 6253 6760 6806 3690 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6472 6328 5870 5386 4317 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.202 -18.102 -7.295 -41.727 90.204 ...
  ..- attr(*, "class")= chr "forecast"
 $ 63  :List of 10
  ..$ method   : chr "ARIMA(3,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:6] 0.491 0.737 -0.611 -0.74 -0.87 ...
  .. .. ..- attr(*, "names")= chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 6.98e-07
  .. ..$ var.coef : num [1:6, 1:6] 0.003681 -0.000734 -0.000999 -0.003516 0.002225 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:6] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:6] TRUE TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 4442
  .. ..$ aic      : num -8870
  .. ..$ arma     : int [1:7] 3 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 0.001613 -0.00019 0.000643 0.00051 0.001048 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.61326670314274,  1.61305056728001, 1.613784| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.491 0.737 -0.611
  .. .. ..$ theta: num [1:3] -0.74 -0.87 0.622
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] 0.000712 -0.000992 -0.000786 0.000681 1.615919
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -2.27e-18 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.491 0.737 -0.611 0 1 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.74 -0.87 0.622 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -7.40e-01 -8.70e-01 6.22e-01 -9.65e-19 ...
  .. ..$ bic      : num -8837
  .. ..$ aicc     : num -8869
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5052 4849 5598 6332 8353 6412 6356 6734 7612 6279 ...
  .. ..$ lambda   : atomic [1:1] -0.617
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 3804 5027 4933 5679 6481 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 9499 8127 7163 6705 6463 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 7191 5945 5246 4952 4804 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 13296 11978 10533 9734 9297 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5052 4849 5598 6332 8353 6412 6356 6734 7612 6279 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 3804 5027 4933 5679 6481 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.001613 -0.00019 0.000643 0.00051 0.001048 ...
  ..- attr(*, "class")= chr "forecast"
 $ 64  :List of 10
  ..$ method   : chr "ARIMA(1,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] 0.399 -0.742 -0.107 -0.132
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. ..$ sigma2   : num 2.11e-06
  .. ..$ var.coef : num [1:4, 1:4] 0.00787 -0.00751 0.00368 0.00357 -0.00751 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. .. .. ..$ : chr [1:4] "ar1" "ma1" "ma2" "ma3"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 3982
  .. ..$ aic      : num -7954
  .. ..$ arma     : int [1:7] 1 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.88e-03 -4.70e-04 5.18e-04 -1.58e-05 2.66e-03 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.88385966547805,  1.88333604197829, 1.883981| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num 0.399
  .. .. ..$ theta: num [1:3] -0.742 -0.107 -0.132
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] 1.15e-04 -5.39e-04 -2.25e-04 -7.82e-05 1.89
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 -7.23e-21 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.399 0 0 0 1 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.742 -0.107 -0.132 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -7.42e-01 -1.07e-01 -1.32e-01 -1.41e-21 ...
  .. ..$ bic      : num -7931
  .. ..$ aicc     : num -7954
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 7610 7190 7713 7667 10824 8735 8092 9395 8922 8473 ...
  .. ..$ lambda   : atomic [1:1] -0.526
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 6251 7565 7289 7680 7836 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 12338 11632 11247 11099 11040 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 9637 8756 8379 8261 8218 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 16393 16243 15935 15746 15662 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 7610 7190 7713 7667 10824 8735 8092 9395 8922 8473 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6251 7565 7289 7680 7836 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.88e-03 -4.70e-04 5.18e-04 -1.58e-05 2.66e-03 ...
  ..- attr(*, "class")= chr "forecast"
 $ 65  :List of 10
  ..$ method   : chr "ARIMA(5,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] -0.5791 0.2108 0.2543 -0.0383 -0.3906 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.00422
  .. ..$ var.coef : num [1:7, 1:7] 0.00289 0.000658 -0.000253 -0.000445 -0.000683 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 1026
  .. ..$ aic      : num -2036
  .. ..$ arma     : int [1:7] 5 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0043 -0.02617 0.00505 -0.13038 0.11511 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.30241131761118,  4.2630712674577, 4.2894974| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.5791 0.2108 0.2543 -0.0383 -0.3906
  .. .. ..$ theta: num [1:4] -0.245 -0.737 0 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.01448 -0.09888 -0.00712 0.01576 -0.01724 ...
  .. .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 3.01e-19 3.07e-18 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.5791 0.2108 0.2543 -0.0383 -0.3906 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.245 -0.737 0 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1.00 -2.45e-01 -7.37e-01 2.53e-18 0.00 ...
  .. ..$ bic      : num -1998
  .. ..$ aicc     : num -2035
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 4738 3949 4460 2217 6614 6777 4716 4987 5976 2747 ...
  .. ..$ lambda   : atomic [1:1] -0.183
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 4643 4455 4357 3890 3825 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 4258 5605 4701 4455 4715 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 2937 3774 3195 3009 3168 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 6342 8585 7125 6798 7239 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 4738 3949 4460 2217 6614 6777 4716 4987 5976 2747 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 4643 4455 4357 3890 3825 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0043 -0.02617 0.00505 -0.13038 0.11511 ...
  ..- attr(*, "class")= chr "forecast"
 $ 66  :List of 10
  ..$ method   : chr "ARIMA(0,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num -0.256
  .. .. ..- attr(*, "names")= chr "ma1"
  .. ..$ sigma2   : num 3.82e-08
  .. ..$ var.coef : num [1, 1] 0.00187
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr "ma1"
  .. .. .. ..$ : chr "ma1"
  .. ..$ mask     : logi TRUE
  .. ..$ loglik   : num 5548
  .. ..$ aic      : num -11093
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 1.28e-03 2.72e-05 2.48e-04 8.75e-05 2.39e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.28435703222091,  1.28438477326799, 1.284626| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.256
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 0.000173 -0.000043 1.284743
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 -3.04e-21 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.2562 0 -0.2562 0.0657 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -2.56e-01 -6.20e-22 -2.56e-01 6.57e-02 ...
  .. ..$ bic      : num -11083
  .. ..$ aicc     : num -11093
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 4993 5099 6221 6358 7867 6431 5659 6281 7734 5643 ...
  .. ..$ lambda   : atomic [1:1] -0.778
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 2431 4995 5075 5887 6231 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 7923 7923 7923 7923 7923 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 6203 5879 5631 5429 5257 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 10722 11695 12632 13568 14522 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 4993 5099 6221 6358 7867 6431 5659 6281 7734 5643 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 2431 4995 5075 5887 6231 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.28e-03 2.72e-05 2.48e-04 8.75e-05 2.39e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 67  :List of 10
  ..$ method   : chr "ARIMA(0,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] -0.786 -0.2
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  .. ..$ sigma2   : num 2.54e-09
  .. ..$ var.coef : num [1:2, 1:2] 0.00093 -0.000889 -0.000889 0.000925
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 6852
  .. ..$ aic      : num -13697
  .. ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 -2.05e-05 -4.27e-06 -3.82e-05 7.00e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999952146194639,  0.999925134042107, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num [1:2] -0.786 -0.2
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 1.33e-06 -3.16e-05 -6.43e-06 1.00
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 -1.95e-21 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.786 -0.2 0 -0.786 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -7.86e-01 -2.00e-01 -9.35e-22 -7.86e-01 ...
  .. ..$ bic      : num -13683
  .. ..$ aicc     : num -13697
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 8096 6644 6859 5456 12363 9451 8946 7888 8085 5115 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 891 7690 7066 6889 6629 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 8183 7775 7775 7775 7775 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 5354 5137 5136 5136 5136 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 17359 15983 15985 15986 15988 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 8096 6644 6859 5456 12363 9451 8946 7888 8085 5115 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 891 7690 7066 6889 6629 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 -2.05e-05 -4.27e-06 -3.82e-05 7.00e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 68  :List of 10
  ..$ method   : chr "ARIMA(1,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] 0.518 -0.987
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  .. ..$ sigma2   : num 2.04e-09
  .. ..$ var.coef : num [1:2, 1:2] 1.13e-03 -1.31e-04 -1.31e-04 9.28e-05
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 7119
  .. ..$ aic      : num -14231
  .. ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.01e-03 -2.21e-05 -2.66e-05 1.81e-05 2.99e-06 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.00542379989032,  1.00539824648144, 1.005374| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num 0.518
  .. .. ..$ theta: num -0.987
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 4.12e-05 -4.16e-05 1.01
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 6.23e-23 0.00 3.99e-11 ...
  .. .. ..$ T    : num [1:3, 1:3] 0.518 0 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.987 0 -0.987 0.975 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.87e-01 2.81e-21 -9.87e-01 9.75e-01 ...
  .. ..$ bic      : num -14217
  .. ..$ aicc     : num -14231
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 7669 6463 5645 6782 6912 6379 6083 5957 6347 6376 ...
  .. ..$ lambda   : atomic [1:1] -0.994
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 913 7482 6588 6073 6778 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 9202 8427 8075 7904 7818 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 6108 5524 5314 5222 5179 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 18593 17698 16753 16195 15895 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 7669 6463 5645 6782 6912 6379 6083 5957 6347 6376 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 913 7482 6588 6073 6778 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.01e-03 -2.21e-05 -2.66e-05 1.81e-05 2.99e-06 ...
  ..- attr(*, "class")= chr "forecast"
 $ 69  :List of 10
  ..$ method   : chr "ARIMA(2,0,2) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:5] 1.587 -0.847 -1.31 0.729 7.213
  .. .. ..- attr(*, "names")= chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ sigma2   : num 0.0123
  .. ..$ var.coef : num [1:5, 1:5] 1.53e-03 -1.24e-03 -1.45e-03 3.95e-04 -9.63e-07 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. .. .. ..$ : chr [1:5] "ar1" "ar2" "ma1" "ma2" ...
  .. ..$ mask     : logi [1:5] TRUE TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 610
  .. ..$ aic      : num -1208
  .. ..$ arma     : int [1:7] 2 2 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:781] from 1 to 781: 0.03794 0.02843 0.00884 -0.12335 0.24799 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(7.25948267164239,  7.26500041514854, 7.250731| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 781
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:2] 1.587 -0.847
  .. .. ..$ theta: num [1:2] -1.31 0.729
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:3] 1 0 0
  .. .. ..$ a    : num [1:3] 0.121 -0.1472 0.0477
  .. .. ..$ P    : num [1:3, 1:3] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:3, 1:3] 1.587 -0.847 0 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -1.31 0.729 -1.31 1.716 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1 -1.31 0.729 -1.31 1.716 ...
  .. ..$ bic      : num -1180
  .. ..$ aicc     : num -1208
  .. ..$ x        : Time-Series [1:781] from 1 to 781: 9903 9993 9762 7715 13265 11677 10233 9000 10349 7665 ...
  .. ..$ lambda   : atomic [1:1] -0.0537
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:781] from 1 to 781: 9307 9538 9622 9429 8817 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 782 to 828: 9886 9437 9010 8708 8578 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 782 to 828: 7840 7424 7013 6727 6609 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 782 to 828: 12503 12034 11616 11313 11174 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:781] from 1 to 781: 9903 9993 9762 7715 13265 11677 10233 9000 10349 7665 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 9307 9538 9622 9429 8817 ...
  ..$ residuals: Time-Series [1:781] from 1 to 781: 0.03794 0.02843 0.00884 -0.12335 0.24799 ...
  ..- attr(*, "class")= chr "forecast"
 $ 70  :List of 10
  ..$ method   : chr "ARIMA(5,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] 0.692 0.433 -0.764 0.198 -0.16 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 8.19e-10
  .. ..$ var.coef : num [1:9, 1:9] 0.004479 -0.00208 -0.003444 0.002255 0.000859 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7075
  .. ..$ aic      : num -14130
  .. ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:782] from 1 to 782: -1.54e-06 -1.95e-05 1.41e-06 1.94e-06 5.86e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999913379341035,  0.99989277567704, 0.99990| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 782
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] 0.692 0.433 -0.764 0.198 -0.16
  .. .. ..$ theta: num [1:4] -0.304 -0.402 0.622 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 4.42e-05 -2.47e-05 -2.13e-05 1.46e-05 -5.72e-06
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.692 0.433 -0.764 0.198 -0.16 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.304 -0.402 0.622 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 -0.304 -0.402 0.622 0 ...
  .. ..$ bic      : num -14084
  .. ..$ aicc     : num -14130
  .. ..$ x        : Time-Series [1:782] from 1 to 782: 6163 5469 5912 6020 10059 7520 6778 6022 6776 5928 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:782] from 1 to 782: 6222 6120 5863 5951 6331 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 783 to 829: 6477 6315 5695 5830 5493 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 783 to 829: 5234 5059 4621 4690 4458 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 783 to 829: 8492 8399 7419 7703 7156 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:782] from 1 to 782: 6163 5469 5912 6020 10059 7520 6778 6022 6776 5928 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:782] from 1 to 782: 6222 6120 5863 5951 6331 ...
  ..$ residuals: Time-Series [1:782] from 1 to 782: -1.54e-06 -1.95e-05 1.41e-06 1.94e-06 5.86e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 71  :List of 10
  ..$ method   : chr "ARIMA(5,0,5) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:11] -0.352 0.399 0.48 -0.164 -0.837 ...
  .. .. ..- attr(*, "names")= chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 5.65e-10
  .. ..$ var.coef : num [1:11, 1:11] 1.06e-03 7.29e-04 -2.99e-06 -4.53e-04 -4.48e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:11] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7193
  .. ..$ aic      : num -14362
  .. ..$ arma     : int [1:7] 5 5 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -1.78e-05 -8.43e-06 1.41e-07 -1.11e-05 4.27e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999933626180052,  0.999937646986079, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.352 0.399 0.48 -0.164 -0.837
  .. .. ..$ theta: num [1:5] 0.653 0.0101 -0.2821 0.0207 0.4682
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. .. ..$ a    : num [1:6] 3.22e-05 -3.00e-06 -4.99e-06 -1.72e-05 -2.11e-05 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.352 0.399 0.48 -0.164 -0.837 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 0.653 0.0101 -0.2821 0.0207 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 0.653 0.0101 -0.2821 0.0207 ...
  .. ..$ bic      : num -14306
  .. ..$ aicc     : num -14362
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 7041 7246 7737 7263 13634 10289 9952 9819 11501 7841 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 8051 7717 7729 7901 8618 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 7514 9444 7650 7010 7587 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 6116 7263 6104 5670 6040 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 9743 13495 10244 9181 10199 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 7041 7246 7737 7263 13634 10289 9952 9819 11501 7841 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 8051 7717 7729 7901 8618 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -1.78e-05 -8.43e-06 1.41e-07 -1.11e-05 4.27e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 72  :List of 10
  ..$ method   : chr "ARIMA(5,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.7522 -0.0545 0.3312 0.1291 -0.4784 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 7.29e-09
  .. ..$ var.coef : num [1:10, 1:10] 0.004157 0.005719 0.003476 0.000356 -0.001338 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 4956
  .. ..$ aic      : num -9891
  .. ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:623] from 1 to 623: -1.61e-05 -1.36e-04 -3.53e-05 -2.24e-04 1.33e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999793314703828,  0.999648306194832, 0.9997| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 623
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.7522 -0.0545 0.3312 0.1291 -0.4784
  .. .. ..$ theta: num [1:4] 0.933 0.3 -0.262 -0.486
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 7.24e-05 -5.12e-05 -2.48e-05 -4.19e-05 -5.60e-05
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -0.7522 -0.0545 0.3312 0.1291 -0.4784 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 0.933 0.3 -0.262 -0.486 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 0.933 0.3 -0.262 -0.486 ...
  .. ..$ bic      : num -9842
  .. ..$ aicc     : num -9890
  .. ..$ x        : Time-Series [1:623] from 1 to 623: 3543 2341 3198 1831 8386 5765 5079 4258 4311 2075 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:623] from 1 to 623: 3757 3430 3605 3106 3973 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 624 to 670: 2715 4714 3194 3233 3898 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 624 to 670: 2093 3094 2354 2375 2684 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 624 to 670: 3860 9898 4967 5062 7117 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:623] from 1 to 623: 3543 2341 3198 1831 8386 5765 5079 4258 4311 2075 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:623] from 1 to 623: 3757 3430 3605 3106 3973 ...
  ..$ residuals: Time-Series [1:623] from 1 to 623: -1.61e-05 -1.36e-04 -3.53e-05 -2.24e-04 1.33e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 73  :List of 10
  ..$ method   : chr "ARIMA(0,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] -0.874 -0.103
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "ma2"
  .. ..$ sigma2   : num 2830
  .. ..$ var.coef : num [1:2, 1:2] 0.00132 -0.00127 -0.00127 0.00144
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. .. .. ..$ : chr [1:2] "ma1" "ma2"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num -4223
  .. ..$ aic      : num 8452
  .. ..$ arma     : int [1:7] 0 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 0.254 6.281 4.558 -59.451 109.202 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(254.149025733295,  262.513746846693, 264.2668| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num [1:2] -0.874 -0.103
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 37.64 -46.08 -5.27 306.61
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 0.00 5.84e-23 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 0 0 0 1 1 0 0 0 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.874 -0.103 0 -0.874 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -8.74e-01 -1.03e-01 2.60e-23 -8.74e-01 ...
  .. ..$ bic      : num 8466
  .. ..$ aicc     : num 8452
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 3692 3890 3932 2373 6399 5342 4519 5197 4387 2297 ...
  .. ..$ lambda   : atomic [1:1] 0.616
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 3686 3741 3823 3657 3551 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 4778 4642 4642 4642 4642 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 3143 3016 3016 3015 3015 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 6663 6525 6525 6526 6527 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 3692 3890 3932 2373 6399 5342 4519 5197 4387 2297 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 3686 3741 3823 3657 3551 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 0.254 6.281 4.558 -59.451 109.202 ...
  ..- attr(*, "class")= chr "forecast"
 $ 74  :List of 10
  ..$ method   : chr "ARIMA(4,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] 0.153 1.015 -0.512 -0.476 0.153 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.16e-09
  .. ..$ var.coef : num [1:9, 1:9] 0.0314 -0.0201 -0.0215 0.0262 -0.0289 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 6886
  .. ..$ aic      : num -13752
  .. ..$ arma     : int [1:7] 4 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:776] from 1 to 776: 2.12e-05 -2.86e-05 -2.03e-05 -2.57e-05 8.10e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999930806001656,  0.999884888835551, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] 0.153 1.015 -0.512 -0.476
  .. .. ..$ theta: num [1:4] 0.153 -0.849 0.334 0.506
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 3.74e-05 5.04e-06 -2.11e-05 -5.99e-06 2.24e-06
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.153 1.015 -0.512 -0.476 0 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 0.153 -0.849 0.334 0.506 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 0.153 -0.849 0.334 0.506 ...
  .. ..$ bic      : num -13705
  .. ..$ aicc     : num -13752
  .. ..$ x        : Time-Series [1:776] from 1 to 776: 6904 5243 5090 4692 9415 8134 5800 7331 6461 5312 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:776] from 1 to 776: 6022 6168 5675 5335 5344 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 777 to 823: 6265 6585 5503 5734 5073 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 777 to 823: 4921 5064 4381 4515 4090 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 777 to 823: 8620 9412 7398 7857 6678 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:776] from 1 to 776: 6904 5243 5090 4692 9415 8134 5800 7331 6461 5312 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:776] from 1 to 776: 6022 6168 5675 5335 5344 ...
  ..$ residuals: Time-Series [1:776] from 1 to 776: 2.12e-05 -2.86e-05 -2.03e-05 -2.57e-05 8.10e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 75  :List of 10
  ..$ method   : chr "ARIMA(0,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num -0.392
  .. .. ..- attr(*, "names")= chr "ma1"
  .. ..$ sigma2   : num 2.14e-09
  .. ..$ var.coef : num [1, 1] 0.00198
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr "ma1"
  .. .. .. ..$ : chr "ma1"
  .. ..$ mask     : logi TRUE
  .. ..$ loglik   : num 7062
  .. ..$ aic      : num -14120
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -1.63e-05 1.29e-05 -7.98e-06 3.49e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999904516468369,  0.999886584516886, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 783
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.392
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] -1.90e-06 -7.79e-07 1.00
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 7.87e-22 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.392 0 -0.392 0.154 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.92e-01 2.22e-22 -3.92e-01 1.54e-01 ...
  .. ..$ bic      : num -14111
  .. ..$ aicc     : num -14120
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5844 5290 5882 5464 6898 5843 5054 5258 5680 4827 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 854 5790 5466 5713 5559 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 7401 7401 7401 7401 7401 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 5146 4892 4690 4523 4380 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 13173 15191 17533 20351 23862 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5844 5290 5882 5464 6898 5843 5054 5258 5680 4827 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 854 5790 5466 5713 5559 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: 1.00e-03 -1.63e-05 1.29e-05 -7.98e-06 3.49e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 76  :List of 10
  ..$ method   : chr "ARIMA(1,1,0)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num -0.352
  .. .. ..- attr(*, "names")= chr "ar1"
  .. ..$ sigma2   : num 2.07e-09
  .. ..$ var.coef : num [1, 1] 0.00141
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr "ar1"
  .. .. .. ..$ : chr "ar1"
  .. ..$ mask     : logi TRUE
  .. ..$ loglik   : num 5802
  .. ..$ aic      : num -11601
  .. ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:623] from 1 to 623: 1.00e-03 -3.02e-05 9.26e-07 -1.84e-05 5.55e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999974022035681,  0.999941338316296, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 622
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.352
  .. .. ..$ theta: num(0) 
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:2] 1 1
  .. .. ..$ a    : num [1:2] 1.52e-05 1.00
  .. .. ..$ P    : num [1:2, 1:2] 0.00 -3.48e-17 -3.48e-17 3.48e-17
  .. .. ..$ T    : num [1:2, 1:2] -0.352 1 0 1
  .. .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:2, 1:2] 1.00 -1.22e-17 -1.22e-17 3.48e-17
  .. ..$ bic      : num -11592
  .. ..$ aicc     : num -11601
  .. ..$ x        : Time-Series [1:623] from 1 to 623: 9837 7445 8203 6914 12311 8321 9005 8112 9093 7813 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:623] from 1 to 623: 908 9604 8141 7919 7318 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 624 to 670: 12056 12336 12236 12271 12259 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 624 to 670: 7079 6642 6078 5729 5427 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 624 to 670: 40588 86390 NA NA NA ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:623] from 1 to 623: 9837 7445 8203 6914 12311 8321 9005 8112 9093 7813 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:623] from 1 to 623: 908 9604 8141 7919 7318 ...
  ..$ residuals: Time-Series [1:623] from 1 to 623: 1.00e-03 -3.02e-05 9.26e-07 -1.84e-05 5.55e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 77  :List of 10
  ..$ method   : chr "ARIMA(3,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.728 0.647 -0.884 -1.165 -0.599 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 5.18e-06
  .. ..$ var.coef : num [1:8, 1:8] 0.00279 -0.00365 0.00158 -0.00286 0.00485 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 3642
  .. ..$ aic      : num -7267
  .. ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:781] from 1 to 781: 0.002007 -0.002473 0.001839 0.000255 0.00476 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.00707241487974,  2.00410210912823, 2.006665| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 1
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 780
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.728 0.647 -0.884
  .. .. ..$ theta: num [1:5] -1.165 -0.599 1.217 -0.175 -0.265
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 0.002691 -0.004619 -0.000871 0.003845 -0.000609 ...
  .. .. ..$ P    : num [1:7, 1:7] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:7, 1:7] 0.728 0.647 -0.884 0 0 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -1.165 -0.599 1.217 -0.175 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -1.165 -0.599 1.217 -0.175 ...
  .. ..$ bic      : num -7225
  .. ..$ aicc     : num -7266
  .. ..$ x        : Time-Series [1:781] from 1 to 781: 6573 5316 6376 6461 10350 7535 7781 6968 6881 7130 ...
  .. ..$ lambda   : atomic [1:1] -0.492
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:781] from 1 to 781: 5681 6333 5587 6340 6903 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 782 to 828: 8162 7478 6895 7058 6936 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 782 to 828: 6480 5810 5368 5470 5384 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 782 to 828: 10589 9974 9174 9446 9263 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:781] from 1 to 781: 6573 5316 6376 6461 10350 7535 7781 6968 6881 7130 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:781] from 1 to 781: 5681 6333 5587 6340 6903 ...
  ..$ residuals: Time-Series [1:781] from 1 to 781: 0.002007 -0.002473 0.001839 0.000255 0.00476 ...
  ..- attr(*, "class")= chr "forecast"
 $ 78  :List of 10
  ..$ method   : chr "ARIMA(3,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 0.7068 0.7225 -0.9293 -1.5178 -0.0806 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 0.00322
  .. ..$ var.coef : num [1:7, 1:7] 4.78e-04 -8.68e-05 -2.70e-04 -6.31e-04 5.89e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 1132
  .. ..$ aic      : num -2248
  .. ..$ arma     : int [1:7] 3 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.004268 -0.004545 0.000441 -0.036931 0.119175 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(4.26834467732629,  4.26195595497084, 4.265844| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.707 0.722 -0.929
  .. .. ..$ theta: num [1:4] -1.5178 -0.0806 1.3259 -0.7034
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.0807 -0.1616 0.0325 0.0793 -0.0432 ...
  .. .. ..$ P    : num [1:6, 1:6] 0.00 -2.22e-16 -2.78e-17 2.22e-16 -1.11e-16 ...
  .. .. ..$ T    : num [1:6, 1:6] 0.707 0.722 -0.929 0 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -1.5178 -0.0806 1.3259 -0.7034 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -1.5178 -0.0806 1.3259 -0.7034 ...
  .. ..$ bic      : num -2210
  .. ..$ aicc     : num -2247
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 3075 2994 3043 2521 5181 3712 3556 3583 3860 2797 ...
  .. ..$ lambda   : atomic [1:1] -0.178
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 3021 3051 3037 2933 3072 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 3574 3846 2988 3309 2784 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 2637 2811 2193 2411 2044 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 4931 5361 4145 4629 3862 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 3075 2994 3043 2521 5181 3712 3556 3583 3860 2797 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 3021 3051 3037 2933 3072 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.004268 -0.004545 0.000441 -0.036931 0.119175 ...
  ..- attr(*, "class")= chr "forecast"
 $ 79  :List of 10
  ..$ method   : chr "ARIMA(0,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num -0.504
  .. .. ..- attr(*, "names")= chr "ma1"
  .. ..$ sigma2   : num 3.66e-09
  .. ..$ var.coef : num [1, 1] 0.00177
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr "ma1"
  .. .. .. ..$ : chr "ma1"
  .. ..$ mask     : logi TRUE
  .. ..$ loglik   : num 6605
  .. ..$ aic      : num -13205
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 -3.70e-05 -4.94e-06 -4.53e-05 1.39e-04 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999868440704389,  0.999826453999085, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 776
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.504
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 1.71e-05 -6.40e-06 1.00
  .. .. ..$ P    : num [1:3, 1:3] 0.0 0.0 -3.4e-22 0.0 0.0 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.504 0 -0.504 0.254 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -5.04e-01 -1.14e-22 -5.04e-01 2.54e-01 ...
  .. ..$ bic      : num -13196
  .. ..$ aicc     : num -13205
  .. ..$ x        : Time-Series [1:777] from 1 to 777: 4827 4014 4210 3563 8444 6286 5261 4996 5329 3494 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:777] from 1 to 777: 829 4715 4299 4248 3879 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 778 to 824: 6837 6837 6837 6837 6837 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 778 to 824: 4469 4296 4151 4025 3915 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 778 to 824: 14546 16740 19388 22691 26971 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:777] from 1 to 777: 4827 4014 4210 3563 8444 6286 5261 4996 5329 3494 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:777] from 1 to 777: 829 4715 4299 4248 3879 ...
  ..$ residuals: Time-Series [1:777] from 1 to 777: 1.00e-03 -3.70e-05 -4.94e-06 -4.53e-05 1.39e-04 ...
  ..- attr(*, "class")= chr "forecast"
 $ 80  :List of 10
  ..$ method   : chr "ARIMA(0,1,0)"
  ..$ model    :List of 19
  .. ..$ coef     : num(0) 
  .. ..$ sigma2   : num 1015
  .. ..$ var.coef : num(0) 
  .. ..$ mask     : logi(0) 
  .. ..$ loglik   : num -3797
  .. ..$ aic      : num 7596
  .. ..$ arma     : int [1:7] 0 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.227 6.791 13.942 36.646 52.043 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(227.169301856619,  233.960064688439, 247.9016| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : num 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num(0) 
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:2] 1 1
  .. .. ..$ a    : num [1:2] 16.2 299.6
  .. .. ..$ P    : num [1:2, 1:2] 0.00 -7.42e-23 -7.42e-23 7.42e-23
  .. .. ..$ T    : num [1:2, 1:2] 0 1 0 1
  .. .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:2, 1:2] 1.00 0.00 0.00 7.42e-23
  .. ..$ bic      : num 7600
  .. ..$ aicc     : num 7596
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 5495 5787 6407 8166 10977 8213 7002 7530 7822 7249 ...
  .. ..$ lambda   : atomic [1:1] 0.565
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 5485 5495 5787 6407 8166 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 9810 9810 9810 9810 9810 9810 9810 9810 9810 9810 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 7688 6875 6279 5794 5382 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 12154 13188 14007 14713 15348 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 5495 5787 6407 8166 10977 8213 7002 7530 7822 7249 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 5485 5495 5787 6407 8166 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.227 6.791 13.942 36.646 52.043 ...
  ..- attr(*, "class")= chr "forecast"
 $ 81  :List of 10
  ..$ method   : chr "ARIMA(4,1,4)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.4338 -0.0515 -0.8945 0.4525 -0.8841 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.0527
  .. ..$ var.coef : num [1:8, 1:8] 0.004696 0.000123 0.000468 0.002773 -0.003417 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 35.1
  .. ..$ aic      : num -52.2
  .. ..$ arma     : int [1:7] 4 4 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 0.0111 -0.4713 0.2042 -0.0311 0.329 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(11.1453648294304,  10.550199077084, 10.853326| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] 0.4338 -0.0515 -0.8945 0.4525
  .. .. ..$ theta: num [1:4] -0.884 -0.116 0.853 -0.82
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.358 -0.214 -0.104 0.177 -0.192 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] 0.4338 -0.0515 -0.8945 0.4525 0 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.884 -0.116 0.853 -0.82 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 -0.884 -0.116 0.853 -0.82 ...
  .. ..$ bic      : num -12.3
  .. ..$ aicc     : num -51.9
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 7181 4874 5943 6311 8546 6574 6743 5781 6984 7537 ...
  .. ..$ lambda   : atomic [1:1] 0.0494
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 7130 6629 5201 6439 6917 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 8940 8134 7131 6864 7277 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 7404 6552 5719 5503 5837 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 10776 10075 8870 8541 9049 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 7181 4874 5943 6311 8546 6574 6743 5781 6984 7537 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 7130 6629 5201 6439 6917 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.0111 -0.4713 0.2042 -0.0311 0.329 ...
  ..- attr(*, "class")= chr "forecast"
 $ 82  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.633 0.148 0.563 0.236 -0.483 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 9.34e-06
  .. ..$ var.coef : num [1:10, 1:10] 0.00362 0.00447 0.00226 -0.00067 -0.00157 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 3404
  .. ..$ aic      : num -6785
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00201 0.000135 -0.000255 -0.003316 0.006186 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.00983698152278,  2.01003915527628, 2.009601| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.633 0.148 0.563 0.236 -0.483
  .. .. ..$ theta: num [1:5] -0.0555 -0.6688 -0.6462 -0.128 0.5122
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 0.001428 -0.00475 0.001657 0.000183 -0.000916 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 -2.08e-17 0.00 0.00 -2.78e-17 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.633 0.148 0.563 0.236 -0.483 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.0555 -0.6688 -0.6462 -0.128 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.0555 -0.6688 -0.6462 -0.128 ...
  .. ..$ bic      : num -6734
  .. ..$ aicc     : num -6785
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 8047 8184 7892 5799 14645 11770 10794 10918 10660 5289 ...
  .. ..$ lambda   : atomic [1:1] -0.492
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 6853 8092 8061 7442 8082 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 7006 11263 8338 7761 8921 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 5277 7802 6011 5647 6347 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 9740 17633 12319 11314 13429 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 8047 8184 7892 5799 14645 11770 10794 10918 10660 5289 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 6853 8092 8061 7442 8082 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00201 0.000135 -0.000255 -0.003316 0.006186 ...
  ..- attr(*, "class")= chr "forecast"
 $ 83  :List of 10
  ..$ method   : chr "ARIMA(3,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 0.651 0.703 -0.9 -0.488 -0.581 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 5.07e-05
  .. ..$ var.coef : num [1:7, 1:7] 1.13e-03 -4.74e-05 -5.58e-04 -1.38e-03 -2.36e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 2750
  .. ..$ aic      : num -5483
  .. ..$ arma     : int [1:7] 3 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00276 -0.00766 -0.00412 -0.00944 0.01687 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.39061348506058,  2.3797959313861, 2.3822892| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.651 0.703 -0.9
  .. .. ..$ theta: num [1:3] -0.488 -0.581 0.737
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:4] 1 0 0 0
  .. .. ..$ a    : num [1:4] 0.001069 -0.003106 0.000788 -0.002881
  .. .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:4, 1:4] 0.651 0.703 -0.9 0 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.488 -0.581 0.737 -0.488 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1 -0.488 -0.581 0.737 -0.488 ...
  .. ..$ bic      : num -5446
  .. ..$ aicc     : num -5483
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4102 3060 3264 2649 5746 4773 4631 4298 4776 2954 ...
  .. ..$ lambda   : atomic [1:1] -0.404
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 3794 3752 3645 3363 3480 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 3513 3749 3231 3603 3293 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 2777 2938 2552 2815 2592 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 4554 4914 4193 4742 4291 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4102 3060 3264 2649 5746 4773 4631 4298 4776 2954 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 3794 3752 3645 3363 3480 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00276 -0.00766 -0.00412 -0.00944 0.01687 ...
  ..- attr(*, "class")= chr "forecast"
 $ 84  :List of 10
  ..$ method   : chr "ARIMA(4,1,3)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] 0.219 0.95 -0.449 -0.22 -0.774 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.48e-09
  .. ..$ var.coef : num [1:7, 1:7] 0.00496 -0.0011 -0.00257 0.00215 -0.00377 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7625
  .. ..$ aic      : num -15235
  .. ..$ arma     : int [1:7] 4 3 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.46e-05 1.39e-06 -3.39e-06 3.51e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999997010866548,  0.999978044671405, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] 0.219 0.95 -0.449 -0.22
  .. .. ..$ theta: num [1:3] -0.774 -0.869 0.679
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:5] 1 0 0 0 1
  .. .. ..$ a    : num [1:5] 1.05e-05 -1.48e-05 -2.83e-06 5.74e-06 1.00
  .. .. ..$ P    : num [1:5, 1:5] 0.00 0.00 0.00 0.00 4.88e-17 ...
  .. .. ..$ T    : num [1:5, 1:5] 0.219 0.95 -0.449 -0.22 1 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 -0.774 -0.869 0.679 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1.00 -7.74e-01 -8.69e-01 6.79e-01 4.02e-17 ...
  .. ..$ bic      : num -15198
  .. ..$ aicc     : num -15235
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 12709 10242 11274 10274 19582 15019 12951 12981 13462 10406 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 928 12044 11101 10645 11610 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 12593 13325 11773 12556 11482 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 7774 7756 7023 7283 6908 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 33129 47249 36372 45473 33980 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 12709 10242 11274 10274 19582 15019 12951 12981 13462 10406 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 928 12044 11101 10645 11610 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.46e-05 1.39e-06 -3.39e-06 3.51e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 85  :List of 10
  ..$ method   : chr "ARIMA(1,1,0) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:2] -4.75e-01 8.74e-08
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "drift"
  .. ..$ sigma2   : num 2.91e-09
  .. ..$ var.coef : num [1:2, 1:2] 8.25e-04 1.97e-08 1.97e-08 1.06e-09
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "drift"
  .. .. .. ..$ : chr [1:2] "ar1" "drift"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 8127
  .. ..$ aic      : num -16249
  .. ..$ arma     : int [1:7] 1 0 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:942] from 1 to 942: 1.00e-03 6.40e-05 8.33e-06 -9.10e-06 1.56e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999838622895527,  0.999910864529877, 0.9998| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 941
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num -0.475
  .. .. ..$ theta: num(0) 
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:2] 1 1
  .. .. ..$ a    : num [1:2] 1.07e-05 1.00
  .. .. ..$ P    : num [1:2, 1:2] 0.00 2.28e-22 2.28e-22 -2.28e-22
  .. .. ..$ T    : num [1:2, 1:2] -0.475 1 0 1
  .. .. ..$ V    : num [1:2, 1:2] 1 0 0 0
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:2, 1:2] 1.00 1.08e-22 1.08e-22 -2.28e-22
  .. ..$ xreg     : int [1:942, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num -16234
  .. ..$ aicc     : num -16249
  .. ..$ x        : Time-Series [1:942] from 1 to 942: 4220 6069 5246 5339 5774 10509 8990 7300 6523 7434 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:942] from 1 to 942: 809 4371 5026 5611 5298 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 943 to 989: 7499 7643 7581 7618 7608 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 943 to 989: 4939 4787 4432 4255 4069 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 943 to 989: 15565 18938 26177 36287 58238 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:942] from 1 to 942: 4220 6069 5246 5339 5774 10509 8990 7300 6523 7434 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:942] from 1 to 942: 809 4371 5026 5611 5298 ...
  ..$ residuals: Time-Series [1:942] from 1 to 942: 1.00e-03 6.40e-05 8.33e-06 -9.10e-06 1.56e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 86  :List of 10
  ..$ method   : chr "ARIMA(4,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 0.8 0.616 -0.996 0.108 -0.492 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.449
  .. ..$ var.coef : num [1:8, 1:8] 0.00487 -0.00321 -0.00282 0.0033 -0.00348 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -789
  .. ..$ aic      : num 1595
  .. ..$ arma     : int [1:7] 4 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:778] from 1 to 778: -0.158 -0.676 -0.348 -0.426 1.449 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(14.763201085347,  14.1243961643442, 14.218456| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:4] 0.8 0.616 -0.996 0.108
  .. .. ..$ theta: num [1:3] -0.492 -0.6 0.734
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:4] 1 0 0 0
  .. .. ..$ a    : num [1:4] 0.605 -0.37 -0.342 0.19
  .. .. ..$ P    : num [1:4, 1:4] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:4, 1:4] 0.8 0.616 -0.996 0.108 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.492 -0.6 0.734 -0.492 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1 -0.492 -0.6 0.734 -0.492 ...
  .. ..$ bic      : num 1637
  .. ..$ aicc     : num 1596
  .. ..$ x        : Time-Series [1:778] from 1 to 778: 4230 3371 3487 3289 6623 5631 4334 4739 4530 3505 ...
  .. ..$ lambda   : atomic [1:1] 0.126
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:778] from 1 to 778: 4469 4285 3947 3831 4038 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 779 to 825: 4710 4723 4156 4268 3943 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 779 to 825: 3481 3442 2982 3058 2813 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 779 to 825: 6303 6403 5716 5879 5451 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:778] from 1 to 778: 4230 3371 3487 3289 6623 5631 4334 4739 4530 3505 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:778] from 1 to 778: 4469 4285 3947 3831 4038 ...
  ..$ residuals: Time-Series [1:778] from 1 to 778: -0.158 -0.676 -0.348 -0.426 1.449 ...
  ..- attr(*, "class")= chr "forecast"
 $ 87  :List of 10
  ..$ method   : chr "ARIMA(5,0,5) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:11] -1.093 -1.123 -1.029 -0.919 -0.868 ...
  .. .. ..- attr(*, "names")= chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 369
  .. ..$ var.coef : num [1:11, 1:11] 7.58e-04 8.43e-04 5.66e-04 4.25e-05 -1.92e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:11] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:11] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -3426
  .. ..$ aic      : num 6875
  .. ..$ arma     : int [1:7] 5 5 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:784] from 1 to 784: -1.33 -8.65 -16.83 -40.84 41.89 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(161.031172769098,  151.772957508451, 141.7001| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 784
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.093 -1.123 -1.029 -0.919 -0.868
  .. .. ..$ theta: num [1:5] 1.171 1.353 1.191 0.857 0.624
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 0
  .. .. ..$ a    : num [1:6] 8.98 -8.74 10.17 14.77 13.22 ...
  .. .. ..$ P    : num [1:6, 1:6] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:6, 1:6] -1.093 -1.123 -1.029 -0.919 -0.868 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 1.171 1.353 1.191 0.857 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1 1.171 1.353 1.191 0.857 ...
  .. ..$ bic      : num 6931
  .. ..$ aicc     : num 6876
  .. ..$ x        : Time-Series [1:784] from 1 to 784: 5636 5028 4405 2810 10252 7522 6396 5820 7238 2772 ...
  .. ..$ lambda   : atomic [1:1] 0.512
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:784] from 1 to 784: 5726 5595 5469 5106 6808 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 785 to 831: 4555 7221 6035 5528 5622 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 785 to 831: 3178 5460 4417 3978 4028 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 785 to 831: 6172 9220 7898 7325 7475 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:784] from 1 to 784: 5636 5028 4405 2810 10252 7522 6396 5820 7238 2772 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:784] from 1 to 784: 5726 5595 5469 5106 6808 ...
  ..$ residuals: Time-Series [1:784] from 1 to 784: -1.33 -8.65 -16.83 -40.84 41.89 ...
  ..- attr(*, "class")= chr "forecast"
 $ 88  :List of 10
  ..$ method   : chr "ARIMA(5,0,3) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:9] -1.167 -0.871 -0.415 -0.223 -0.422 ...
  .. .. ..- attr(*, "names")= chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 13
  .. ..$ var.coef : num [1:9, 1:9] 0.00413 0.00473 0.00245 -0.00131 -0.00162 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:9] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:9] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -2104
  .. ..$ aic      : num 4228
  .. ..$ arma     : int [1:7] 5 3 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: -0.4358 -0.0383 -0.7076 -7.4163 4.7063 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(31.5511490949698,  32.0376944001306, 31.23059| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 780
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -1.167 -0.871 -0.415 -0.223 -0.422
  .. .. ..$ theta: num [1:4] 1.316 1.104 0.514 0
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 3.2958 0.0958 1.5581 0.3959 -1.4386
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -1.167 -0.871 -0.415 -0.223 -0.422 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 1.316 1.104 0.514 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 1.316 1.104 0.514 0 ...
  .. ..$ bic      : num 4275
  .. ..$ aicc     : num 4229
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 5289 5576 5106 1870 10051 8485 7137 6776 6704 2003 ...
  .. ..$ lambda   : atomic [1:1] 0.258
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 5546 5599 5516 4775 6329 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 3652 7688 4861 4594 6478 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 2003 4690 2770 2588 3795 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 6142 11918 7941 7573 10364 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 5289 5576 5106 1870 10051 8485 7137 6776 6704 2003 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 5546 5599 5516 4775 6329 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: -0.4358 -0.0383 -0.7076 -7.4163 4.7063 ...
  ..- attr(*, "class")= chr "forecast"
 $ 89  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.763 0.0157 0.4817 0.2821 -0.368 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.000427
  .. ..$ var.coef : num [1:10, 1:10] 0.010805 0.015157 0.00938 0.000724 -0.003631 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 1530
  .. ..$ aic      : num -3039
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00351 -0.01958 -0.01064 -0.04987 0.0557 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(3.50724306786307,  3.47614236237408, 3.480223| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.763 0.0157 0.4817 0.2821 -0.368
  .. .. ..$ theta: num [1:5] -0.0816 -0.6129 -0.5793 -0.1609 0.4612
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 0.01324 -0.02662 0.00432 -0.00251 -0.00329 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 -2.78e-17 0.00 0.00 -2.78e-17 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.763 0.0157 0.4817 0.2821 -0.368 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.0816 -0.6129 -0.5793 -0.1609 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.0816 -0.6129 -0.5793 -0.1609 ...
  .. ..$ bic      : num -2990
  .. ..$ aicc     : num -3038
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 6635 5002 5185 3225 8960 7443 7057 5772 6393 3470 ...
  .. ..$ lambda   : atomic [1:1] -0.255
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 6420 5962 5703 4868 5279 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 5196 7008 5735 5719 6096 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 4138 5469 4509 4496 4766 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 6617 9132 7410 7391 7927 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 6635 5002 5185 3225 8960 7443 7057 5772 6393 3470 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 6420 5962 5703 4868 5279 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00351 -0.01958 -0.01064 -0.04987 0.0557 ...
  ..- attr(*, "class")= chr "forecast"
 $ 90  :List of 10
  ..$ method   : chr "ARIMA(0,1,1) with drift"
  ..$ model    :List of 20
  .. ..$ coef     : Named num [1:2] -0.379732 0.000966
  .. .. ..- attr(*, "names")= chr [1:2] "ma1" "drift"
  .. ..$ sigma2   : num 0.304
  .. ..$ var.coef : num [1:2, 1:2] 1.45e-03 8.93e-07 8.93e-07 1.50e-04
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ma1" "drift"
  .. .. .. ..$ : chr [1:2] "ma1" "drift"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num -639
  .. ..$ aic      : num 1284
  .. ..$ arma     : int [1:7] 0 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:778] from 1 to 778: 0.0149 -0.4846 -0.1225 0.1083 1.1161 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(14.9434068409552,  14.4260525746627, 14.47539| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 777
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num(0) 
  .. .. ..$ theta: num -0.38
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 0.672 -0.27 14.379
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 3.41e-22 0.00 0.00 ...
  .. .. ..$ T    : num [1:3, 1:3] 0 0 1 1 0 0 0 0 1
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.38 0 -0.38 0.144 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -3.80e-01 9.38e-23 -3.80e-01 1.44e-01 ...
  .. ..$ xreg     : int [1:778, 1] 1 2 3 4 5 6 7 8 9 10 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : NULL
  .. .. .. ..$ : chr "drift"
  .. ..$ bic      : num 1298
  .. ..$ aicc     : num 1284
  .. ..$ x        : Time-Series [1:778] from 1 to 778: 8256 6727 6861 7299 11084 8981 7087 7574 7970 7100 ...
  .. ..$ lambda   : atomic [1:1] 0.104
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:778] from 1 to 778: 8208 8151 7204 6991 7184 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 779 to 825: 10377 10380 10384 10388 10392 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 779 to 825: 7888 7512 7199 6928 6689 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 779 to 825: 13546 14194 14780 15323 15836 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:778] from 1 to 778: 8256 6727 6861 7299 11084 8981 7087 7574 7970 7100 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:778] from 1 to 778: 8208 8151 7204 6991 7184 ...
  ..$ residuals: Time-Series [1:778] from 1 to 778: 0.0149 -0.4846 -0.1225 0.1083 1.1161 ...
  ..- attr(*, "class")= chr "forecast"
 $ 91  :List of 10
  ..$ method   : chr "ARIMA(3,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] 0.518 0.115 -0.1 -0.963
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ sigma2   : num 2.86e-05
  .. ..$ var.coef : num [1:4, 1:4] 1.36e-03 -6.05e-04 -7.08e-06 -9.80e-05 -6.05e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 2964
  .. ..$ aic      : num -5917
  .. ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:778] from 1 to 778: 0.002294 -0.005218 -0.00047 0.000104 0.012972 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.29420793601765,  2.28833887849549, 2.289443| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 777
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.518 0.115 -0.1
  .. .. ..$ theta: num [1:2] -0.963 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 5.21e-05 -3.36e-03 -1.42e-04 2.30
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 5.35e-19 -5.33e-18 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 0.518 0.115 -0.1 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.963 0 0 -0.963 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.63e-01 0.00 -1.52e-18 -9.63e-01 ...
  .. ..$ bic      : num -5894
  .. ..$ aicc     : num -5917
  .. ..$ x        : Time-Series [1:778] from 1 to 778: 5087 4125 4285 4324 7652 6758 5861 5239 5835 4395 ...
  .. ..$ lambda   : atomic [1:1] -0.424
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:778] from 1 to 778: 4676 4965 4356 4308 4570 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 779 to 825: 5404 5037 4792 4692 4646 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 779 to 825: 4213 3827 3595 3512 3475 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 779 to 825: 7139 6875 6649 6529 6473 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:778] from 1 to 778: 5087 4125 4285 4324 7652 6758 5861 5239 5835 4395 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:778] from 1 to 778: 4676 4965 4356 4308 4570 ...
  ..$ residuals: Time-Series [1:778] from 1 to 778: 0.002294 -0.005218 -0.00047 0.000104 0.012972 ...
  ..- attr(*, "class")= chr "forecast"
 $ 92  :List of 10
  ..$ method   : chr "ARIMA(3,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] 0.6337 0.0613 -0.1795 -0.9898
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ sigma2   : num 3.79e-05
  .. ..$ var.coef : num [1:4, 1:4] 1.25e-03 -7.96e-04 7.85e-05 -1.19e-05 -7.96e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 2857
  .. ..$ aic      : num -5703
  .. ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00232 0.000126 0.004644 -0.00021 0.016559 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(2.32030679340155,  2.32044846446879, 2.325608| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.6337 0.0613 -0.1795
  .. .. ..$ theta: num [1:2] -0.99 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 0.005029 -0.006135 0.000155 2.33378
  .. .. ..$ P    : num [1:4, 1:4] 0.0 0.0 -1.6e-17 8.9e-17 0.0 ...
  .. .. ..$ T    : num [1:4, 1:4] 0.6337 0.0613 -0.1795 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.99 0 0 -0.99 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.90e-01 0.00 1.87e-17 -9.90e-01 ...
  .. ..$ bic      : num -5680
  .. ..$ aicc     : num -5703
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 4129 4148 4934 4759 9685 6620 6452 5888 5545 5437 ...
  .. ..$ lambda   : atomic [1:1] -0.418
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 3835 4131 4218 4794 4985 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 7267 6865 6352 6157 6068 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 5365 4843 4417 4288 4234 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 10287 10331 9747 9432 9271 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 4129 4148 4934 4759 9685 6620 6452 5888 5545 5437 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 3835 4131 4218 4794 4985 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.00232 0.000126 0.004644 -0.00021 0.016559 ...
  ..- attr(*, "class")= chr "forecast"
 $ 93  :List of 10
  ..$ method   : chr "ARIMA(5,0,4) with non-zero mean"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.74179 0.00143 0.49848 0.27327 -0.40618 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 0.273
  .. ..$ var.coef : num [1:10, 1:10] 0.005388 0.007553 0.004994 0.000256 -0.00193 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -596
  .. ..$ aic      : num 1213
  .. ..$ arma     : int [1:7] 5 4 0 0 1 0 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: -0.0369 0.0967 0.1488 -0.8491 0.7388 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(11.6910435472495,  11.8514868755181, 11.90358| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.74179 0.00143 0.49848 0.27327 -0.40618
  .. .. ..$ theta: num [1:4] 0.88 0.278 -0.349 -0.465
  .. .. ..$ Delta: num(0) 
  .. .. ..$ Z    : num [1:5] 1 0 0 0 0
  .. .. ..$ a    : num [1:5] 0.26346 -0.40855 0.00507 0.09567 0.00859
  .. .. ..$ P    : num [1:5, 1:5] 0 0 0 0 0 ...
  .. .. ..$ T    : num [1:5, 1:5] -0.74179 0.00143 0.49848 0.27327 -0.40618 ...
  .. .. ..$ V    : num [1:5, 1:5] 1 0.88 0.278 -0.349 -0.465 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:5, 1:5] 1 0.88 0.278 -0.349 -0.465 ...
  .. ..$ bic      : num 1264
  .. ..$ aicc     : num 1213
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 5520 6036 6213 3207 9394 7385 6712 6605 8189 3565 ...
  .. ..$ lambda   : atomic [1:1] 0.0676
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 5635 5720 5720 5204 6274 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 4024 7270 5319 5237 5837 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 2732 4995 3604 3547 3951 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 5867 10482 7773 7656 8538 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 5520 6036 6213 3207 9394 7385 6712 6605 8189 3565 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 5635 5720 5720 5204 6274 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: -0.0369 0.0967 0.1488 -0.8491 0.7388 ...
  ..- attr(*, "class")= chr "forecast"
 $ 94  :List of 10
  ..$ method   : chr "ARIMA(5,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] -0.17 0.398 0.175 -0.12 -0.446 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 2.14e-09
  .. ..$ var.coef : num [1:7, 1:7] 6.35e-03 -1.97e-03 -1.42e-03 5.72e-04 4.01e-05 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 7024
  .. ..$ aic      : num -14033
  .. ..$ arma     : int [1:7] 5 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.59e-06 -8.80e-07 -2.24e-05 8.59e-05 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(0.999904252363291,  0.999901444445018, 0.9999| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.17 0.398 0.175 -0.12 -0.446
  .. .. ..$ theta: num [1:4] -0.452 -0.532 0 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 6.12e-06 -4.10e-05 9.25e-06 7.36e-06 -1.79e-06 ...
  .. .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 -1.53e-17 -5.71e-17 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.17 0.398 0.175 -0.12 -0.446 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.452 -0.532 0 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1.00 -4.52e-01 -5.32e-01 -3.55e-17 0.00 ...
  .. ..$ bic      : num -13996
  .. ..$ aicc     : num -14033
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 5835 5741 5737 4966 11748 9091 7425 7423 7299 5653 ...
  .. ..$ lambda   : atomic [1:1] -1
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 854 5794 5766 5587 5850 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 6193 7010 6487 6470 6515 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4531 4854 4529 4479 4499 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 9784 12610 11428 11646 11803 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 5835 5741 5737 4966 11748 9091 7425 7423 7299 5653 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 854 5794 5766 5587 5850 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 1.00e-03 -1.59e-06 -8.80e-07 -2.24e-05 8.59e-05 ...
  ..- attr(*, "class")= chr "forecast"
 $ 95  :List of 10
  ..$ method   : chr "ARIMA(1,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:2] 0.169 -0.99
  .. .. ..- attr(*, "names")= chr [1:2] "ar1" "ma1"
  .. ..$ sigma2   : num 0.000387
  .. ..$ var.coef : num [1:2, 1:2] 1.28e-03 -3.06e-05 -3.06e-05 2.94e-05
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. .. .. ..$ : chr [1:2] "ar1" "ma1"
  .. ..$ mask     : logi [1:2] TRUE TRUE
  .. ..$ loglik   : num 1954
  .. ..$ aic      : num -3903
  .. ..$ arma     : int [1:7] 1 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00302 -0.00856 -0.00224 -0.02439 0.03868 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(3.0207732058344,  3.00963071725562, 3.0116060| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num 0.169
  .. .. ..$ theta: num -0.99
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:3] 1 0 1
  .. .. ..$ a    : num [1:3] 0.00709 -0.01321 3.01878
  .. .. ..$ P    : num [1:3, 1:3] 0.00 0.00 1.86e-22 0.00 1.64e-09 ...
  .. .. ..$ T    : num [1:3, 1:3] 0.169 0 1 1 0 ...
  .. .. ..$ V    : num [1:3, 1:3] 1 -0.99 0 -0.99 0.979 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:3, 1:3] 1.00 -9.90e-01 3.26e-20 -9.90e-01 9.79e-01 ...
  .. ..$ bic      : num -3889
  .. ..$ aicc     : num -3902
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 7770 6522 6723 4644 11985 10371 9232 8809 7882 4119 ...
  .. ..$ lambda   : atomic [1:1] -0.311
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 7403 7455 6961 6620 6286 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 6962 6746 6711 6705 6704 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 4803 4644 4621 4617 4617 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 10592 10292 10234 10224 10223 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 7770 6522 6723 4644 11985 10371 9232 8809 7882 4119 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 7403 7455 6961 6620 6286 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.00302 -0.00856 -0.00224 -0.02439 0.03868 ...
  ..- attr(*, "class")= chr "forecast"
 $ 96  :List of 10
  ..$ method   : chr "ARIMA(5,1,2)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:7] -0.668 -0.0101 -0.0851 -0.2105 -0.3709 ...
  .. .. ..- attr(*, "names")= chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 8.7
  .. ..$ var.coef : num [1:7, 1:7] 2.28e-03 6.96e-04 3.19e-06 2.32e-04 -3.04e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:7] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:7] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num -1947
  .. ..$ aic      : num 3910
  .. ..$ arma     : int [1:7] 5 2 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0241 0.1296 -0.0963 -4.776 6.208 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(24.1147558790783,  24.3091468425947, 24.09073| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.668 -0.0101 -0.0851 -0.2105 -0.3709
  .. .. ..$ theta: num [1:4] -0.228 -0.75 0 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:6] 1 0 0 0 0 1
  .. .. ..$ a    : num [1:6] 0.0693 -4.415 -0.4669 0.6331 0.3586 ...
  .. .. ..$ P    : num [1:6, 1:6] 0.00 0.00 0.00 1.47e-18 2.58e-18 ...
  .. .. ..$ T    : num [1:6, 1:6] -0.668 -0.0101 -0.0851 -0.2105 -0.3709 ...
  .. .. ..$ V    : num [1:6, 1:6] 1 -0.228 -0.75 0 0 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:6, 1:6] 1.00 -2.28e-01 -7.50e-01 2.31e-18 0.00 ...
  .. ..$ bic      : num 3947
  .. ..$ aicc     : num 3910
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 3999 4122 3984 1384 8978 7028 6511 6255 5667 1461 ...
  .. ..$ lambda   : atomic [1:1] 0.224
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 3984 4040 4044 3267 3673 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 3235 4798 4115 5066 4913 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 1661 2606 2182 2770 2647 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 5780 8208 7170 8622 8458 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 3999 4122 3984 1384 8978 7028 6511 6255 5667 1461 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 3984 4040 4044 3267 3673 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.0241 0.1296 -0.0963 -4.776 6.208 ...
  ..- attr(*, "class")= chr "forecast"
 $ 97  :List of 10
  ..$ method   : chr "ARIMA(5,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:10] -0.587 0.209 0.626 0.24 -0.5 ...
  .. .. ..- attr(*, "names")= chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ sigma2   : num 1.39e-06
  .. ..$ var.coef : num [1:10, 1:10] 0.00282 0.00308 0.00136 -0.00112 -0.00131 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. .. .. ..$ : chr [1:10] "ar1" "ar2" "ar3" "ar4" ...
  .. ..$ mask     : logi [1:10] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 4150
  .. ..$ aic      : num -8278
  .. ..$ arma     : int [1:7] 5 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:780] from 1 to 780: 0.001628 0.000137 -0.000023 -0.001811 0.002444 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.62796224586026,  1.62818049618764, 1.628034| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 779
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:5] -0.587 0.209 0.626 0.24 -0.5
  .. .. ..$ theta: num [1:5] -0.176 -0.665 -0.635 -0.026 0.571
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 3.50e-04 -1.74e-03 4.43e-04 3.64e-05 -1.54e-04 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 0.00 0.00 0.00 3.47e-17 ...
  .. .. ..$ T    : num [1:7, 1:7] -0.587 0.209 0.626 0.24 -0.5 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -0.176 -0.665 -0.635 -0.026 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -0.176 -0.665 -0.635 -0.026 ...
  .. ..$ bic      : num -8227
  .. ..$ aicc     : num -8278
  .. ..$ x        : Time-Series [1:780] from 1 to 780: 5735 5992 5818 3863 10668 7737 6864 8052 7540 4087 ...
  .. ..$ lambda   : atomic [1:1] -0.611
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:780] from 1 to 780: 4272 5829 5845 5263 5924 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 781 to 827: 5477 7812 6092 5755 6685 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 781 to 827: 4189 5586 4520 4308 4872 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 781 to 827: 7551 11917 8780 8185 9899 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:780] from 1 to 780: 5735 5992 5818 3863 10668 7737 6864 8052 7540 4087 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:780] from 1 to 780: 4272 5829 5845 5263 5924 ...
  ..$ residuals: Time-Series [1:780] from 1 to 780: 0.001628 0.000137 -0.000023 -0.001811 0.002444 ...
  ..- attr(*, "class")= chr "forecast"
 $ 98  :List of 10
  ..$ method   : chr "ARIMA(3,1,1)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:4] 0.6387 0.0289 -0.1421 -0.9847
  .. .. ..- attr(*, "names")= chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ sigma2   : num 4.77e-07
  .. ..$ var.coef : num [1:4, 1:4] 1.28e-03 -8.07e-04 1.01e-04 -2.78e-05 -8.07e-04 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. .. .. ..$ : chr [1:4] "ar1" "ar2" "ar3" "ma1"
  .. ..$ mask     : logi [1:4] TRUE TRUE TRUE TRUE
  .. ..$ loglik   : num 4561
  .. ..$ aic      : num -9112
  .. ..$ arma     : int [1:7] 3 1 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:779] from 1 to 779: 0.001521 0.00042 0.000467 0.000541 0.001559 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(1.52079486056249,  1.5212644776116, 1.5217140| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 778
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 0.6387 0.0289 -0.1421
  .. .. ..$ theta: num [1:2] -0.985 0
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:4] 1 0 0 1
  .. .. ..$ a    : num [1:4] 2.87e-04 -4.61e-04 -7.96e-05 1.52
  .. .. ..$ P    : num [1:4, 1:4] 0.00 0.00 -1.01e-18 7.08e-18 0.00 ...
  .. .. ..$ T    : num [1:4, 1:4] 0.6387 0.0289 -0.1421 1 1 ...
  .. .. ..$ V    : num [1:4, 1:4] 1 -0.985 0 0 -0.985 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:4, 1:4] 1.00 -9.85e-01 0.00 1.34e-18 -9.85e-01 ...
  .. ..$ bic      : num -9089
  .. ..$ aicc     : num -9112
  .. ..$ x        : Time-Series [1:779] from 1 to 779: 3169 3483 3835 4299 6406 4649 4002 4569 4659 3975 ...
  .. ..$ lambda   : atomic [1:1] -0.654
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:779] from 1 to 779: 2416 3200 3470 3799 4214 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 780 to 826: 6419 5955 5609 5453 5401 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 780 to 826: 4989 4484 4189 4081 4048 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 780 to 826: 8684 8441 8047 7798 7707 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:779] from 1 to 779: 3169 3483 3835 4299 6406 4649 4002 4569 4659 3975 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:779] from 1 to 779: 2416 3200 3470 3799 4214 ...
  ..$ residuals: Time-Series [1:779] from 1 to 779: 0.001521 0.00042 0.000467 0.000541 0.001559 ...
  ..- attr(*, "class")= chr "forecast"
 $ 99  :List of 10
  ..$ method   : chr "ARIMA(3,1,5)"
  ..$ model    :List of 19
  .. ..$ coef     : Named num [1:8] 1.594 -0.77 -0.118 -2.04 1.217 ...
  .. .. ..- attr(*, "names")= chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ sigma2   : num 0.000169
  .. ..$ var.coef : num [1:8, 1:8] 0.0998 -0.1701 0.0965 -0.098 0.2127 ...
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. .. .. ..$ : chr [1:8] "ar1" "ar2" "ar3" "ma1" ...
  .. ..$ mask     : logi [1:8] TRUE TRUE TRUE TRUE TRUE TRUE ...
  .. ..$ loglik   : num 1817
  .. ..$ aic      : num -3617
  .. ..$ arma     : int [1:7] 3 5 0 0 1 1 0
  .. ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00304 -0.01839 0.0081 0.00458 0.02809 ...
  .. ..$ call     : language auto.arima(y = y.xts, lambda = BoxCox.lambda(y.xts), x = list(x = c(3.0442983265908,  3.02198374025874, 3.0336253| __truncated__ ...
  .. ..$ series   : chr "y.xts"
  .. ..$ code     : int 0
  .. ..$ n.cond   : int 0
  .. ..$ nobs     : int 621
  .. ..$ model    :List of 10
  .. .. ..$ phi  : num [1:3] 1.594 -0.77 -0.118
  .. .. ..$ theta: num [1:5] -2.04048 1.2171 -0.00674 -0.00614 -0.14685
  .. .. ..$ Delta: num 1
  .. .. ..$ Z    : num [1:7] 1 0 0 0 0 0 1
  .. .. ..$ a    : num [1:7] 0.005906 -0.021547 0.015775 -0.001044 0.000576 ...
  .. .. ..$ P    : num [1:7, 1:7] 0.00 -4.44e-16 2.22e-16 -8.67e-19 -7.81e-18 ...
  .. .. ..$ T    : num [1:7, 1:7] 1.594 -0.77 -0.118 0 0 ...
  .. .. ..$ V    : num [1:7, 1:7] 1 -2.04048 1.2171 -0.00674 -0.00614 ...
  .. .. ..$ h    : num 0
  .. .. ..$ Pn   : num [1:7, 1:7] 1 -2.04048 1.2171 -0.00674 -0.00614 ...
  .. ..$ bic      : num -3577
  .. ..$ aicc     : num -3616
  .. ..$ x        : Time-Series [1:622] from 1 to 622: 4367 3333 3827 4100 6514 5534 3781 4467 4157 4101 ...
  .. ..$ lambda   : atomic [1:1] -0.302
  .. .. ..- attr(*, "biasadj")= logi FALSE
  .. ..$ fitted   : Time-Series [1:622] from 1 to 622: 4203 4158 3474 3876 4465 ...
  .. ..- attr(*, "class")= chr [1:2] "ARIMA" "Arima"
  ..$ level    : num [1:2] 80 95
  ..$ mean     : Time-Series [1:47] from 623 to 669: 5550 4981 4648 4633 4826 ...
  ..$ lower    : Time-Series [1:47, 1:2] from 623 to 669: 4459 3913 3643 3630 3770 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ upper    : Time-Series [1:47, 1:2] from 623 to 669: 7016 6461 6046 6030 6303 ...
  .. ..- attr(*, "dimnames")=List of 2
  .. .. ..$ : NULL
  .. .. ..$ : chr [1:2] "80%" "95%"
  ..$ x        : Time-Series [1:622] from 1 to 622: 4367 3333 3827 4100 6514 5534 3781 4467 4157 4101 ...
  ..$ series   : chr "y.xts"
  ..$ fitted   : Time-Series [1:622] from 1 to 622: 4203 4158 3474 3876 4465 ...
  ..$ residuals: Time-Series [1:622] from 1 to 622: 0.00304 -0.01839 0.0081 0.00458 0.02809 ...
  ..- attr(*, "class")= chr "forecast"
  [list output truncated]



In [24]:

    
# Ejemplo pronóstico con tienda 2
plot(fcast.arima[[2]])

Predicción con $tslm$

Aplicamos nuestro modelo usando los nuevos datos de series temporales, en nuestro caso el test dataset



In [218]:

    
# Funcion para pronosticar con nuevos datos en base a los modelos TSLM por tienda

tslm_forecast = function(x, y){
  index <- x$Store[1]
  fitt <- y[[index]]
  #if(nlevels(x$StateHoliday)>1) {
  return(data.frame(forecast(fitt, newdata = data.frame(DayOfWeek = x$DayOfWeek, 
                                                        StateHoliday = x$StateHoliday, 
                                                        SchoolHoliday = x$SchoolHoliday,
                                                        Promo = x$Promo,
                                                        Promo2 = x$Promo2)
                            )
                   )
        )
  #} else {
  #return(data.frame(forecast(fitt, newdata = data.frame(DayOfWeek = x$DayOfWeek, 
  #                                                      SchoolHoliday = x$SchoolHoliday,
  #                                                      Promo = x$Promo,
  #                                                      Promo2 = x$Promo2)
  #                          )
  #                 )
  #      )  
  #}
}



In [220]:

    
system.time(
    predictions <- ddply(test, .(Store), tslm_forecast, out.tslm)
)



In [ ]:

    
str(predictions)



In [ ]:

    
predictions$Point.Forecast <- ifelse(predictions$Point.Forecast < 0, 0, 
                                     predictions$Point.Forecast)

Avg_Sales <- train[,.(AS = mean(Sales,na.rm=T)),.(Store,DayOfWeek)]
test <- merge(test,Avg_Sales, by = c("Store","DayOfWeek"))
test <- test[order(Store,Date)]
test[,FPPredictions:=Open * predictions$Point.Forecast]
test[,FPredictions:=ifelse(is.na(predictions$Point.Forecast),AS,predictions$Point.Forecast)]

results <- data.frame(Id=test$Id, Sales=test$FPredictions)
results <- results[order(results$Id),]

ANEXO

Tasa de Cambio Diaria DOP/USD Entidades Financieras BCRD



In [4]:

    
# Tasa de Cambio Diaria DOP/USD Entidades Financieras BCRD

# Web download ####
url <- "https://www.bancentral.gov.do/tasas_cambio/TASA_ENTIDADES_FINANCIERAS.xls?s=1525718479909"
destfile <- "TASA_ENTIDADES_FINANCIERAS.xls"
curl::curl_download(url, destfile)

# Archivos crudos ####
raw.diaria <- read_excel(destfile, sheet = "Diaria", 
                  col_names = TRUE, skip = 1) %>% 
  select_all(tolower)

# Limpieza y Transformaciones ####

# cat(unique(raw.diaria$mes), sep = '", "')

mes <- data.frame(
       mes = c("Ene", "Feb", "Mar", "Abr", "May", "Jun", "Jul", 
               "Ago", "Sep", "Sept", "Oct", "Nov", "Dic"),
       mm = c("01", "02", "03", "04", "05", "06", "07", "08", 
              "09", "09", "10", "11", "12"),
       stringsAsFactors = FALSE
         )

etl.diaria <- raw.diaria %>%
  left_join(mes, by = "mes") %>% 
  mutate(tdate = as.Date(paste0(año, "-", mm, "-", día))) %>% 
  mutate(diff = venta - compra,
         spread = 100 * (diff / venta)) %>% 
  filter(is.na(tdate)==FALSE)

dates <- etl.diaria$tdate

xts.compra <- xts(etl.diaria$compra, order.by = dates)
xts.venta <- xts(etl.diaria$venta, order.by = dates)
xts.diff <- xts(etl.diaria$diff, order.by = dates)
xts.spread <- xts(etl.diaria$spread, order.by = dates)

print("Fin")









    



[1] "Fin"

Gráficos Tasa de Cambio Diaria DOP/USD Entidades Financieras BCRD



In [6]:

    
xts.all <- cbind(xts.venta, xts.compra, xts.diff, xts.spread)
names(xts.all) <- c("Venta", "Compra", "Diferencia", "Spread")

ts_plot(xts.venta, 
        title = "Tasa de Venta (DOP$ / USD$)",
        Xtitle = "Fuente: Banco Central de la República Dominicana", 
        Ytitle = "",
        slider = TRUE,
        col = "blue"
       )

ts_plot(xts.spread, 
        title = "Spread (DOP$ / USD$)",
        Xtitle = "Fuente: Cálculo a partir de datos del Banco Central de la República Dominicana", 
        Ytitle = "%",
        slider = TRUE,
        type = "single",
        col = "red"
       )



In [ ]:

Store	DayOfWeek	Date	Sales	Customers	Open	StateHoliday	SchoolHoliday	StoreType	Assortment	CompetitionDistance	CompetitionOpenSinceMonth	CompetitionOpenSinceYear	Promo2SinceWeek	Promo2SinceYear
1	2	2013-01-01	0	0	0	a	1	c	a	1270	9	2008	NA	NA
1	3	2013-01-02	5530	668	1	0	1	c	a	1270	9	2008	NA	NA
1	4	2013-01-03	4327	578	1	0	1	c	a	1270	9	2008	NA	NA
1	5	2013-01-04	4486	619	1	0	1	c	a	1270	9	2008	NA	NA
1	6	2013-01-05	4997	635	1	0	1	c	a	1270	9	2008	NA	NA
1	7	2013-01-06	0	0	0	0	1	c	a	1270	9	2008	NA	NA

Store	Id	DayOfWeek	Date	Open	Promo	SchoolHoliday	StoreType	Assortment	CompetitionDistance	CompetitionOpenSinceMonth	CompetitionOpenSinceYear	Promo2SinceWeek	Promo2SinceYear
1	40233	6	2015-08-01	1	0	1	c	a	1270	9	2008	NA	NA
1	39377	7	2015-08-02	0	0	1	c	a	1270	9	2008	NA	NA
1	38521	1	2015-08-03	1	1	1	c	a	1270	9	2008	NA	NA
1	37665	2	2015-08-04	1	1	1	c	a	1270	9	2008	NA	NA
1	36809	3	2015-08-05	1	1	1	c	a	1270	9	2008	NA	NA
1	35953	4	2015-08-06	1	1	1	c	a	1270	9	2008	NA	NA

Date	Sales
2013-01-01	97235
2013-01-02	6949829
2013-01-03	6347820
2013-01-04	6638954
2013-01-05	5951593
2013-01-06	143904

StoreType	Sales	Customers
a	3165334859	363541431
b	159231395	31465616
c	783221426	92129705
d	1765392943	156904995

StoreType	Sales	Customers	SalesPerCustomer	CompetitionDistance	CompetitionOpen	PromoOpen
a	6925.698	795.4224	8.846296	5222.894	7115.514	12918.54
b	10233.380	2022.2118	5.133427	1072.573	11364.495	17199.37
c	6933.126	815.5381	8.626227	3514.147	6745.419	12158.68
d	6822.300	606.3539	11.277862	6959.561	9028.527	10421.96

StoreType	Store	Year	WeekOfYear	Sales
a	2	2013	1	15407
a	2	2013	2	32914
a	2	2013	3	21081
a	2	2013	4	29973
a	2	2013	5	23297
a	2	2013	6	31996

Assortment	Sales	Customers	SalesPerCustomer	CompetitionDistance	CompetitionOpen	PromoOpen
a	6621.523	748.0010	9.130807	4385.694	6359.424	12212.71
b	8642.504	2067.5502	4.163726	1189.447	15965.434	13727.96
c	7300.844	752.2026	10.018030	6749.628	9116.896	12003.78