skforecast/skforecast-ai/forecasting-single-series

import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from skforecast.recursive import ForecasterRecursive
from skforecast.preprocessing import RollingFeatures
from skforecast.model_selection import backtesting_forecaster, TimeSeriesFold
# 1. Load and prepare data (MUST have DatetimeIndex with frequency)
data = pd.read_csv('data.csv', index_col='date', parse_dates=True)
data = data.asfreq('h')  # Set frequency — required
# 2. Train/test split (time-based, never random)
end_train = '2023-01-01'
y_train = data.loc[:end_train, 'target']
y_test = data.loc[end_train:, 'target']
# 3. Create forecaster with optional rolling features
rolling_features = RollingFeatures(
    stats=['mean', 'std'],
    window_sizes=24
)
forecaster = ForecasterRecursive(
    estimator=RandomForestRegressor(n_estimators=100, random_state=123),
    lags=24,
    window_features=rolling_features,
    transformer_y=None,          # e.g., StandardScaler() for scaling
    categorical_features='auto', # Auto-detect and encode non-numeric exog columns
    differentiation=None,        # e.g., 1 for first-order differencing
    dropna_from_series=False,    # True to drop NaN rows; False to keep (NaN-tolerant estimators)
)
# 4. Train
forecaster.fit(y=y_train)
# 5. Predict
predictions = forecaster.predict(steps=10)
# 6. Backtesting (proper evaluation)
cv = TimeSeriesFold(
    steps=10,
    initial_train_size=len(y_train),
    refit=False,
    fixed_train_size=False,
)
metric, predictions_bt = backtesting_forecaster(
    forecaster=forecaster,
    y=data['target'],
    cv=cv,
    metric='mean_absolute_error',
)
print(f"MAE: {metric}")
# 7. Prediction intervals
# Default interval is [0.05, 0.95] (90%). Here [0.1, 0.9] creates an 80% interval.
forecaster.fit(y=y_train, store_in_sample_residuals=True)
predictions_interval = forecaster.predict_interval(
    steps=10,
    interval=[0.1, 0.9],        # 80% prediction interval (quantiles, 0-1 scale)
    method='bootstrapping',
    n_boot=500,
)

# Exogenous variables must cover the forecast horizon during prediction
forecaster = ForecasterRecursive(
    estimator=RandomForestRegressor(n_estimators=100, random_state=123),
    lags=24,
)
forecaster.fit(y=y_train, exog=exog_train)
predictions = forecaster.predict(steps=10, exog=exog_test)

from skforecast.direct import ForecasterDirect
# Must specify `steps` at creation — trains one model per step
forecaster = ForecasterDirect(
    estimator=RandomForestRegressor(n_estimators=100, random_state=123),
    lags=24,
    steps=10,
    categorical_features='auto',  # Auto-detect and encode non-numeric exog columns
)
forecaster.fit(y=y_train, exog=exog_train)
predictions = forecaster.predict(exog=exog_test)