Exogenous features

%load_ext autoreload
%autoreload 2

import lightgbm as lgb
import pandas as pd
from mlforecast import MLForecast
from mlforecast.lag_transforms import ExpandingMean, RollingMean
from mlforecast.utils import generate_daily_series, generate_prices_for_series

series = generate_daily_series(
    100, equal_ends=True, n_static_features=2
).rename(columns={'static_1': 'product_id'})
series.head()

prices_catalog = generate_prices_for_series(series)
prices_catalog.head()

series_with_prices = series.merge(prices_catalog, how='left')
series_with_prices.head()

fcst = MLForecast(
    models=lgb.LGBMRegressor(n_jobs=1, random_state=0, verbosity=-1),
    freq='D',
    lags=[7],
    lag_transforms={
        1: [ExpandingMean()],
        7: [RollingMean(window_size=14)],
    },
    date_features=['dayofweek', 'month'],
    num_threads=2,
)
fcst.fit(series_with_prices, static_features=['static_0', 'product_id'])

MLForecast(models=[LGBMRegressor], freq=D, lag_features=['lag7', 'expanding_mean_lag1', 'rolling_mean_lag7_window_size14'], date_features=['dayofweek', 'month'], num_threads=2)

fcst.ts.features_order_

['static_0',
 'product_id',
 'price',
 'lag7',
 'expanding_mean_lag1',
 'rolling_mean_lag7_window_size14',
 'dayofweek',
 'month']

preds = fcst.predict(h=7, X_df=prices_catalog)
preds.head()

from sklearn.linear_model import LinearRegression
from utilsforecast.feature_engineering import fourier

series.head()

transformed_df, future_df = fourier(series, freq='D', season_length=7, k=2, h=7)

transformed_df.head()

future_df.head()

fcst2 = MLForecast(models=LinearRegression(), freq='D')
fcst2.fit(transformed_df, static_features=['static_0', 'product_id'])

MLForecast(models=[LinearRegression], freq=D, lag_features=[], date_features=[], num_threads=1)

fcst2.predict(h=7, X_df=future_df).head()

import numpy as np

from mlforecast.callbacks import SaveFeatures

# check that the price was passed correctly
first_pred_date = series_with_prices['ds'].max() + pd.offsets.Day()
save_feats = SaveFeatures()
fcst.predict(7, X_df=prices_catalog, before_predict_callback=save_feats)
for h, actual in enumerate(save_feats._inputs):
    expected = prices_catalog.loc[prices_catalog['ds'].eq(first_pred_date + h * pd.offsets.Day())]
    np.testing.assert_allclose(
        actual['price'].values,
        expected['price'].values,
    )

preds2 = fcst.predict(7, X_df=prices_catalog)
preds3 = fcst.predict(7, new_df=series_with_prices, X_df=prices_catalog)

pd.testing.assert_frame_equal(preds, preds2)
pd.testing.assert_frame_equal(preds, preds3)

# test we can compute cross validation with
# exogenous variables without adding extra information
fcst.cross_validation(
    series_with_prices,
    h=7,
    n_windows=2,
    static_features=['static_0', 'product_id'],
);