時系列モデルを統合して予測精度を向上させる

pip install --upgrade scalecast
 conda install tensorflow
 conda install shap
 conda install -c conda-forge cmdstanpy
 pip install prophet

import pandas as pd
 import numpy as np
 from scalecast.Forecaster import Forecaster
 from scalecast.util import metrics
 import matplotlib.pyplot as plt
 import seaborn as sns
 
 def read_data(idx = 'H1', cis = True, metrics = ['smape']):
 info = pd.read_csv(
 'M4-info.csv',
 index_col=0,
 parse_dates=['StartingDate'],
 dayfirst=True,
)
 train = pd.read_csv(
 f'Hourly-train.csv',
 index_col=0,
).loc[idx]
 test = pd.read_csv(
 f'Hourly-test.csv',
 index_col=0,
).loc[idx]
 y = train.values
 sd = info.loc[idx,'StartingDate']
 fcst_horizon = info.loc[idx,'Horizon']
 cd = pd.date_range(
 start = sd,
 freq = 'H',
 periods = len(y),
)
 f = Forecaster(
 y = y, # observed values
 current_dates = cd, # current dates
 future_dates = fcst_horizon, # forecast length
 test_length = fcst_horizon, # test-set length
 cis = cis, # whether to evaluate intervals for each model
 metrics = metrics, # what metrics to evaluate
)
 
 return f, test.values
 
 f, test_set = read_data()
 f # display the Forecaster object

f.set_estimator('naive')
 f.manual_forecast(seasonal=True)

f.set_estimator('arima')
 f.manual_forecast(
order = (5,1,4),
seasonal_order = (1,1,1,24),
call_me = 'manual_arima',
 )

f.set_estimator('rnn')
 f.manual_forecast(
 lags = 48,
 layers_struct=[
('LSTM',{'units':100,'activation':'tanh'}),
('LSTM',{'units':100,'activation':'tanh'}),
('LSTM',{'units':100,'activation':'tanh'}),
],
 optimizer = 'Adam',
 epochs = 15,
 plot_loss = True,
 validation_split=0.2,
 call_me = 'rnn_tanh_activation',
 )
 
 f.manual_forecast(
 lags = 48,
 layers_struct=[
('LSTM',{'units':100,'activation':'relu'}),
('LSTM',{'units':100,'activation':'relu'}),
('LSTM',{'units':100,'activation':'relu'}),
],
 optimizer = 'Adam',
 epochs = 15,
 plot_loss = True,
 validation_split=0.2,
 call_me = 'rnn_relu_activation',
 )

f.set_estimator('prophet')
 f.manual_forecast()

results = f.export(determine_best_by='TestSetSMAPE')
 ms = results['model_summaries']
 ms[
[
 'ModelNickname',
 'TestSetLength',
 'TestSetSMAPE',
 'InSampleSMAPE',
]
 ]

f.plot(order_by="TestSetSMAPE",ci=True)
 plt.show()

f.add_signals(
 f.history.keys(), # add signals from all previously evaluated models
 )
 f.add_ar_terms(48)
 f.set_estimator('catboost')

f.manual_forecast(
 Xvars='all',
 call_me='catboost_all_reg',
 verbose = False,
 )
 f.manual_forecast(
 Xvars=[x for x in f.get_regressor_names() if x.startswith('AR')],
 call_me = 'catboost_lags_only',
 verbose = False,
 )
 f.manual_forecast(
 Xvars=[x for x in f.get_regressor_names() if not x.startswith('AR')],
 call_me = 'catboost_signals_only',
 verbose = False,
 )

test_results = pd.DataFrame(index = f.history.keys(),columns = ['smape','mase'])
 for k, v in f.history.items():
 test_results.loc[k,['smape','mase']] = [
 metrics.smape(test_set,v['Forecast']),
 metrics.mase(test_set,v['Forecast'],m=24,obs=f.y),
]
 
 test_results.sort_values('smape')

fig, ax = plt.subplots(figsize=(12,6))
 f.plot(
 models = ['catboost_all_reg','catboost_signals_only'],
 ci=True,
 ax = ax
 )
 sns.lineplot(
 x = f.future_dates,
 y = test_set,
 ax = ax,
 label = 'held out actuals',
 color = 'darkblue',
 alpha = .75,
 )
 plt.show()

f.export_feature_importance('catboost_all_reg')