Datasets

In [1]:

    

df <- read.csv('desemprego.csv')


    

In [2]:

    

str(df)


    

    




'data.frame':	121 obs. of  2 variables:
 $ Periodo   : num  2007 2007 2007 2007 2007 ...
 $ Desemprego: num  10.4 10.5 10 10 9.3 9.3 9.1 9.6 9.8 9.8 ...

In [3]:

    

summary(df)


    

    






    Periodo       Desemprego   
 Min.   :2007   Min.   : 6.90  
 1st Qu.:2010   1st Qu.: 8.50  
 Median :2012   Median : 9.40  
 Mean   :2012   Mean   :10.01  
 3rd Qu.:2015   3rd Qu.:10.70  
 Max.   :2017   Max.   :15.90  

In [4]:

    

head(df)


    

    






Periodo
Desemprego

	
2007.08
10.4   
	
2007.09
10.5   
	
2007.10
10.0   
	
2007.11
10.0   
	
2007.12
 9.3   
	
2008.01
 9.3   

In [5]:

    

tail(df)


    

    






Periodo
Desemprego

	
116
2017.03
15.2   
	
117
2017.04
15.5   
	
118
2017.05
15.9   
	
119
2017.06
15.6   
	
120
2017.07
15.1   
	
121
2017.08
14.5   

In [7]:

    

df2 <- read.csv('dataset-nao-convencional.csv',dec = ',', sep = ";")


    

In [11]:

    

str(df2)


    

    




'data.frame':	29 obs. of  3 variables:
 $ Nome   : Factor w/ 29 levels "Antônia","Antônio",..: 12 4 8 14 23 22 18 13 21 9 ...
 $ Pesos  : int  74 61 61 68 70 73 67 67 65 57 ...
 $ Alturas: num  1.73 1.61 1.61 1.67 1.69 1.75 1.67 1.67 1.63 1.57 ...

In [8]:

    

head(df2)


    

    






Nome
Pesos
Alturas

	
Fulano  
74      
1.73    
	
Beltrano
61      
1.61    
	
Cicrano 
61      
1.61    
	
João    
68      
1.67    
	
Pedro   
70      
1.69    
	
Paulo   
73      
1.75    

In [9]:

    

df3 <- read.csv('dataset-nao-convencional.csv',dec = ',', sep = ";", 
      colClasses= c('character','integer','numeric'))


    

In [10]:

    

str(df3)


    

    




'data.frame':	29 obs. of  3 variables:
 $ Nome   : chr  "Fulano" "Beltrano" "Cicrano" "João" ...
 $ Pesos  : int  74 61 61 68 70 73 67 67 65 57 ...
 $ Alturas: num  1.73 1.61 1.61 1.67 1.69 1.75 1.67 1.67 1.63 1.57 ...

In [12]:

    

df4 <- read.csv('datas.csv',colClasses=c('Date','integer', 'numeric'))


    

In [13]:

    

print(as.numeric(format(df4$Nascimento, "%m")))


    

    




[1] 3 1 5 1 2

In [14]:

    

df6 <- read.csv('datas-horas.csv', colClasses = c('character', 'numeric', 'numeric'))
str(df6)


    

    




'data.frame':	3 obs. of  3 variables:
 $ Nascimento: chr  "5-3-2005 17:35:00" "1-5-2005 12:10:05" "10-6-2005 23:01:12"
 $ Pesos     : num  5 3.5 4.1
 $ Alturas   : num  0.5 0.48 0.51

In [15]:

    

df6$Nascimento <- strptime(df6$Nascimento,format='%d-%m-%Y %H:%M:%S')
str(df6)


    

    




'data.frame':	3 obs. of  3 variables:
 $ Nascimento: POSIXlt, format: "2005-03-05 17:35:00" "2005-05-01 12:10:05" ...
 $ Pesos     : num  5 3.5 4.1
 $ Alturas   : num  0.5 0.48 0.51

In [16]:

    

valores <- c(1.0,5.2,,6.7,3.2,4.1)


    

    




Error in c(1, 5.2, , 6.7, 3.2, 4.1): argumento 3 está vazio
Traceback:

In [18]:

    

valores <- c(1.0,5.2,NA,6.7,3.2,4.1)
valores


    

    






	
1
	
5.2
	
NA
	
6.7
	
3.2
	
4.1

In [20]:

    

valores <- c(1.0,5.2,NaN,6.7,3.2,4.1)
valores
mean(valores)


    

    






	
1
	
5.2
	
NaN
	
6.7
	
3.2
	
4.1








    





NaN

In [21]:

    

valores <- c(1.0,5.2,NULL,6.7,3.2,4.1)
valores
mean(valores)
length(valores)


    

    






	
1
	
5.2
	
6.7
	
3.2
	
4.1








    





4.04






    





5

In [23]:

    

valores <- c(1.0,5.2,NA,6.7,3.2,4.1)
is.na(valores)
is.na(valores[3])


    

    






	
FALSE
	
FALSE
	
TRUE
	
FALSE
	
FALSE
	
FALSE








    





TRUE

In [24]:

    

valores <- c(1.0,5.2,NaN,6.7,3.2,4.1)
is.na(valores)


    

    






	
FALSE
	
FALSE
	
TRUE
	
FALSE
	
FALSE
	
FALSE

In [26]:

    

# Inf é numérico! 

valores <- c(1.0,5.2,Inf,6.7,3.2,4.1)
is.na(valores)
is.infinite(valores)


    

    






	
FALSE
	
FALSE
	
FALSE
	
FALSE
	
FALSE
	
FALSE








    






	
FALSE
	
FALSE
	
TRUE
	
FALSE
	
FALSE
	
FALSE

In [27]:

    

valores <- c(1.0,5.2,NULL,6.7,3.2,4.1)
is.na(valores)


    

    






	
FALSE
	
FALSE
	
FALSE
	
FALSE
	
FALSE

In [28]:

    

library(tidyr)


    

In [29]:

    

library(dplyr)


    

    




Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

In [ ]: