In [1]:

    

import numpy as np
import pandas as pd


    

In [8]:

    

df = pd.read_csv('issue_19_data_1.csv')


    

In [9]:

    

df


    

    
Out[9]:







  

    

      

      
date
      
number
      
info
    
  
  

    

      
0
      
1890
      
328.0
      
prince de Galles futur Edouard VII
    
    

      
1
      
1900
      
6043.0
      
grand-duc Vladimir de Russie
    
    

      
2
      
NaN
      
33642.0
      
Theodore Roosevelt
    
    

      
3
      
1914
      
40362.0
      
Alphonse XII
    
    

      
4
      
1921
      
51327.0
      
Thomas Rockefeller
    
    

      
5
      
1921
      
53211.0
      
l'empereur Hirohito.
    
    

      
6
      
1929
      
112151.0
      
Franklin D. Roosevelt
    
    

      
7
      
1938
      
147844.0
      
le duc de Windsor
    
    

      
8
      
1948
      
185397.0
      
Princesse Elisabeth d'Angleterre
    
    

      
9
      
NaN
      
203728.0
      
Marlene Dietrich
    
    

      
10
      
NaN
      
248903.0
      
Jean Cocteau
    
    

      
11
      
NaN
      
253652.0
      
Charlie Chaplin
    
    

      
12
      
1950
      
285793.0
      

    
    

      
13
      
NaN
      
448212.0
      
Charlie Chaplin
    
    

      
14
      
1955
      
NaN
      
Charlie Chaplin
    
    

      
15
      
1973
      
NaN
      
Charlie Chaplin
    
    

      
16
      
1976-03-17
      
500000.0
      

    
    

      
17
      
1976
      
536814.0
      
Gainsbourg
    
    

      
18
      
1978
      
531147.0
      
Mick Jagger
    
    

      
19
      
1979
      
554711.0
      
Roman Polanski
    
    

      
20
      
NaN
      
662614.0
      
Coluche
    
    

      
21
      
NaN
      
821208.0
      
Catherine Deneuve
    
    

      
22
      
2000-02-xx
      
908683.0
      
Ronaldo
    
    

      
23
      
NaN
      
921785.0
      
Vladimir Poutine
    
    

      
24
      
NaN
      
954466.0
      
Woody Allen
    
    

      
25
      
2003-04-29
      
1000000.0
      

    
    

      
26
      
NaN
      
1042624.0
      
Barbara Carlotti.
    
    

      
27
      
NaN
      
1079006.0
      
Bill Gates
    
    

      
28
      
2010
      
1089170.0
      
Buzz
    
    

      
29
      
2012
      
1113000.0
      

    
    

      
30
      
NaN
      
NaN
      
Lionel Jospin
    
    

      
31
      
NaN
      
NaN
      
Lionel Jospin
    
    

      
32
      
NaN
      
NaN
      
Jacques Chirac
    
  

In [11]:

    

%matplotlib inline


    

In [13]:

    

df.plot('date' , 'number')


    

    
Out[13]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f485fd73a90>






    

In [25]:

    

import datetime

def convert_date(x):
    y = np.nan
    try:
        y = datetime.datetime.strptime(str(x), "%Y")
    except:
        pass
    return y


df['date'] = df['date'].apply(convert_date)

df_train = df.dropna()


    

In [26]:

    

df_train


    

    
Out[26]:







  

    

      

      
date
      
number
      
info
    
  
  

    

      
0
      
1890-01-01
      
328.0
      
prince de Galles futur Edouard VII
    
    

      
1
      
1900-01-01
      
6043.0
      
grand-duc Vladimir de Russie
    
    

      
3
      
1914-01-01
      
40362.0
      
Alphonse XII
    
    

      
4
      
1921-01-01
      
51327.0
      
Thomas Rockefeller
    
    

      
5
      
1921-01-01
      
53211.0
      
l'empereur Hirohito.
    
    

      
6
      
1929-01-01
      
112151.0
      
Franklin D. Roosevelt
    
    

      
7
      
1938-01-01
      
147844.0
      
le duc de Windsor
    
    

      
8
      
1948-01-01
      
185397.0
      
Princesse Elisabeth d'Angleterre
    
    

      
12
      
1950-01-01
      
285793.0
      

    
    

      
17
      
1976-01-01
      
536814.0
      
Gainsbourg
    
    

      
18
      
1978-01-01
      
531147.0
      
Mick Jagger
    
    

      
19
      
1979-01-01
      
554711.0
      
Roman Polanski
    
    

      
28
      
2010-01-01
      
1089170.0
      
Buzz
    
    

      
29
      
2012-01-01
      
1113000.0
      

    
  

In [27]:

    

import pyaf.ForecastEngine as autof
lEngine = autof.cForecastEngine()

lEngine.train(iInputDS = df_train, iTime = 'date', iSignal = 'number', iHorizon = 7);
lEngine.getModelInfo()


    

    




INFO:pyaf.std:START_TRAINING 'number'
INFO:pyaf.std:END_TRAINING_TIME_IN_SECONDS 'number' 2.8104207515716553
INFO:pyaf.std:TIME_DETAIL TimeVariable='date' TimeMin=1890-01-01T00:00:00.000000 TimeMax=2012-01-01T00:00:00.000000 TimeDelta=3427 days 14:46:09.230769 Estimation = (0 , 14) Validation = (0 , 14) Test = (0 , 14) Horizon=7
INFO:pyaf.std:SIGNAL_DETAIL SignalVariable='CumSum_number' Min=328.0 Max=4707298.0  Mean=1188070.07143 StdDev=1434737.29059
INFO:pyaf.std:BEST_TRANSOFORMATION_TYPE 'CumSum_'
INFO:pyaf.std:BEST_DECOMPOSITION  'CumSum_number_Lag1Trend_residue_zeroCycle_residue_AR(3)' [Lag1Trend + NoCycle + AR(3)]
INFO:pyaf.std:TREND_DETAIL 'CumSum_number_Lag1Trend' [Lag1Trend]
INFO:pyaf.std:CYCLE_DETAIL 'CumSum_number_Lag1Trend_residue_zeroCycle' [NoCycle]
INFO:pyaf.std:AUTOREG_DETAIL 'CumSum_number_Lag1Trend_residue_zeroCycle_residue_AR(3)' [AR(3)]
INFO:pyaf.std:MODEL_MAPE MAPE_Fit=0.2965 MAPE_Forecast=0.2965 MAPE_Test=0.2965
INFO:pyaf.std:MODEL_SMAPE SMAPE_Fit=0.4822 SMAPE_Forecast=0.4822 SMAPE_Test=0.4822
INFO:pyaf.std:MODEL_MASE MASE_Fit=0.5357 MASE_Forecast=0.5357 MASE_Test=0.5357
INFO:pyaf.std:MODEL_L1 L1_Fit=46318.1679123 L1_Forecast=46318.1679123 L1_Test=46318.1679123
INFO:pyaf.std:MODEL_L2 L2_Fit=70082.7714655 L2_Forecast=70082.7714655 L2_Test=70082.7714655
INFO:pyaf.std:MODEL_COMPLEXITY 67
INFO:pyaf.std:AR_MODEL_DETAIL_START
INFO:pyaf.std:AR_MODEL_COEFF 1 CumSum_number_Lag1Trend_residue_zeroCycle_residue_Lag3 1.83751069759
INFO:pyaf.std:AR_MODEL_COEFF 2 CumSum_number_Lag1Trend_residue_zeroCycle_residue_Lag1 0.225997870452
INFO:pyaf.std:AR_MODEL_COEFF 3 CumSum_number_Lag1Trend_residue_zeroCycle_residue_Lag2 -0.17684817679
INFO:pyaf.std:AR_MODEL_DETAIL_END

In [28]:

    

lEngine.standardPlots()


    

    




INFO:pyaf.std:START_PLOTTING
/home/antoine/dev/python/packages/pyaf/TS/Plots.py:31: UserWarning: 
This call to matplotlib.use() has no effect because the backend has already
been chosen; matplotlib.use() must be called *before* pylab, matplotlib.pyplot,
or matplotlib.backends is imported for the first time.

The backend was *originally* set to 'module://ipykernel.pylab.backend_inline' by the following code:
  File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/home/antoine/.local/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
    app.start()
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelapp.py", line 477, in start
    ioloop.IOLoop.instance().start()
  File "/home/antoine/.local/lib/python3.6/site-packages/zmq/eventloop/ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "/home/antoine/.local/lib/python3.6/site-packages/tornado/ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "/home/antoine/.local/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/home/antoine/.local/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "/home/antoine/.local/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "/home/antoine/.local/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "/home/antoine/.local/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
    handler(stream, idents, msg)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/usr/lib/python3/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/usr/lib/python3/dist-packages/IPython/core/interactiveshell.py", line 2828, in run_ast_nodes
    if self.run_code(code, result):
  File "/usr/lib/python3/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-11-e63dad7f4786>", line 1, in <module>
    get_ipython().magic('matplotlib inline')
  File "/usr/lib/python3/dist-packages/IPython/core/interactiveshell.py", line 2160, in magic
    return self.run_line_magic(magic_name, magic_arg_s)
  File "/usr/lib/python3/dist-packages/IPython/core/interactiveshell.py", line 2081, in run_line_magic
    result = fn(*args,**kwargs)
  File "<decorator-gen-105>", line 2, in matplotlib
  File "/usr/lib/python3/dist-packages/IPython/core/magic.py", line 188, in <lambda>
    call = lambda f, *a, **k: f(*a, **k)
  File "/usr/lib/python3/dist-packages/IPython/core/magics/pylab.py", line 100, in matplotlib
    gui, backend = self.shell.enable_matplotlib(args.gui)
  File "/usr/lib/python3/dist-packages/IPython/core/interactiveshell.py", line 2950, in enable_matplotlib
    pt.activate_matplotlib(backend)
  File "/usr/lib/python3/dist-packages/IPython/core/pylabtools.py", line 309, in activate_matplotlib
    matplotlib.pyplot.switch_backend(backend)
  File "/home/antoine/.local/lib/python3.6/site-packages/matplotlib/pyplot.py", line 229, in switch_backend
    matplotlib.use(newbackend, warn=False, force=True)
  File "/home/antoine/.local/lib/python3.6/site-packages/matplotlib/__init__.py", line 1305, in use
    reload(sys.modules['matplotlib.backends'])
  File "/usr/lib/python3.6/importlib/__init__.py", line 166, in reload
    _bootstrap._exec(spec, module)
  File "/home/antoine/.local/lib/python3.6/site-packages/matplotlib/backends/__init__.py", line 14, in <module>
    line for line in traceback.format_stack()


  matplotlib.use('Agg')
/home/antoine/.local/lib/python3.6/site-packages/pandas/plotting/_core.py:1714: UserWarning: Pandas doesn't allow columns to be created via a new attribute name - see https://pandas.pydata.org/pandas-docs/stable/indexing.html#attribute-access
  series.name = label






    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-28-f0a4d8ebc9c6> in <module>()
----> 1 lEngine.standardPlots()

/home/antoine/dev/python/packages/pyaf/ForecastEngine.py in standardPlots(self, name, format)
     46 
     47     def standardPlots(self , name = None, format = 'png'):
---> 48         self.mSignalDecomposition.standardPlots(name, format);
     49 
     50     def getPlotsAsDict(self):

/home/antoine/dev/python/packages/pyaf/TS/SignalDecomposition.py in standardPlots(self, name, format)
    623         logger.info("START_PLOTTING")
    624         start_time = time.time()
--> 625         self.mBestModel.standardPlots(name, format);
    626         lPlotTime = time.time() - start_time;
    627         logger.info("END_PLOTTING_TIME_IN_SECONDS " + str(lPlotTime))

/home/antoine/dev/python/packages/pyaf/TS/TimeSeriesModel.py in standardPlots(self, name, format)
    309                                         lForecastColumn + '_Upper_Bound',
    310                                         name = name,
--> 311                                         format= format);
    312         #lOutput.plot()
    313 

/home/antoine/dev/python/packages/pyaf/TS/Plots.py in prediction_interval_plot(df, time, signal, estimator, lower, upper, name, format, max_length)
    100     # last value of the signal
    101     lLastSignalPos = df1[signal].dropna().tail(1).index;
--> 102     lEstimtorValue = df1[estimator][lLastSignalPos];
    103     df1.loc[lLastSignalPos , lower] = lEstimtorValue;
    104     df1.loc[lLastSignalPos , upper] = lEstimtorValue;

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/series.py in __getitem__(self, key)
    662             key = check_bool_indexer(self.index, key)
    663 
--> 664         return self._get_with(key)
    665 
    666     def _get_with(self, key):

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/series.py in _get_with(self, key)
    705                         return self.loc[key]
    706 
--> 707                     return self.reindex(key)
    708                 except Exception:
    709                     # [slice(0, 5, None)] will break if you convert to ndarray,

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/series.py in reindex(self, index, **kwargs)
   2638     @Appender(generic._shared_docs['reindex'] % _shared_doc_kwargs)
   2639     def reindex(self, index=None, **kwargs):
-> 2640         return super(Series, self).reindex(index=index, **kwargs)
   2641 
   2642     @Appender(generic._shared_docs['fillna'] % _shared_doc_kwargs)

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/generic.py in reindex(self, *args, **kwargs)
   3021         # perform the reindex on the axes
   3022         return self._reindex_axes(axes, level, limit, tolerance, method,
-> 3023                                   fill_value, copy).__finalize__(self)
   3024 
   3025     def _reindex_axes(self, axes, level, limit, tolerance, method, fill_value,

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/generic.py in _reindex_axes(self, axes, level, limit, tolerance, method, fill_value, copy)
   3039             obj = obj._reindex_with_indexers({axis: [new_index, indexer]},
   3040                                              fill_value=fill_value,
-> 3041                                              copy=copy, allow_dups=False)
   3042 
   3043         return obj

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/generic.py in _reindex_with_indexers(self, reindexers, fill_value, copy, allow_dups)
   3143                                                 fill_value=fill_value,
   3144                                                 allow_dups=allow_dups,
-> 3145                                                 copy=copy)
   3146 
   3147         if copy and new_data is self._data:

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/internals.py in reindex_indexer(self, new_axis, indexer, axis, fill_value, allow_dups, copy)
   4132         # some axes don't allow reindexing with dups
   4133         if not allow_dups:
-> 4134             self.axes[axis]._can_reindex(indexer)
   4135 
   4136         if axis >= self.ndim:

/home/antoine/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py in _can_reindex(self, indexer)
   2939         # trying to reindex on an axis with duplicates
   2940         if not self.is_unique and len(indexer):
-> 2941             raise ValueError("cannot reindex from a duplicate axis")
   2942 
   2943     def reindex(self, target, method=None, level=None, limit=None,

ValueError: cannot reindex from a duplicate axis





    













    













    













    













    

In [32]:

    

df_forecast = lEngine.forecast(iInputDS = df_train, iHorizon = 7)
print(df_forecast.columns)
df_forecast[['date', 'number_Forecast', 'number_Forecast_Lower_Bound', 'number_Forecast_Upper_Bound']].tail(7)


    

    




INFO:pyaf.std:START_FORECASTING
INFO:pyaf.std:END_FORECAST_TIME_IN_SECONDS 0.20051145553588867






    




Index(['CumSum_number', 'date', 'number', 'row_number', 'date_Normalized',
       'CumSum_number_Lag1Trend', 'CumSum_number_Lag1Trend_residue',
       'CumSum_number_Lag1Trend_residue_zeroCycle',
       'CumSum_number_Lag1Trend_residue_zeroCycle_residue',
       'CumSum_number_Lag1Trend_residue_zeroCycle_residue_AR(3)',
       'CumSum_number_Lag1Trend_residue_zeroCycle_residue_AR(3)_residue',
       'CumSum_number_Trend', 'CumSum_number_Trend_residue',
       'CumSum_number_Cycle', 'CumSum_number_Cycle_residue',
       'CumSum_number_AR', 'CumSum_number_AR_residue',
       'CumSum_number_TransformedForecast', 'number_Forecast',
       'CumSum_number_TransformedResidue', 'number_Residue',
       'number_Forecast_Lower_Bound', 'number_Forecast_Upper_Bound'],
      dtype='object')






    
Out[32]:







  

    

      

      
date
      
number_Forecast
      
number_Forecast_Lower_Bound
      
number_Forecast_Upper_Bound
    
  
  

    

      
14
      
2021-05-20 14:46:09.230769216
      
1.067167e+06
      
9.298043e+05
      
1.204529e+06
    
    

      
15
      
2030-10-08 05:32:18.461538432
      
2.034668e+06
      
1.634727e+06
      
2.434609e+06
    
    

      
16
      
2040-02-25 20:18:27.692307648
      
2.305215e+06
      
1.951239e+06
      
2.659191e+06
    
    

      
17
      
2049-07-15 11:04:36.923076864
      
2.111037e+06
      
1.613392e+06
      
2.608682e+06
    
    

      
18
      
2058-12-03 01:50:46.153846080
      
3.797103e+06
      
1.929540e+06
      
5.664665e+06
    
    

      
19
      
2068-04-21 16:36:55.384615296
      
4.709622e+06
      
1.929136e+06
      
7.490109e+06
    
    

      
20
      
2077-09-09 07:23:04.615384512
      
4.260869e+06
      
1.424380e+06
      
7.097359e+06
    
  

In [ ]: