Recursive strategy time series forecasting

ts_recursive_strategy.py

def recursive_forecast(y, model, lags, 
                       n_steps=FCAST_STEPS, step="1H"):
    
    """
    Parameters
    ----------
    y: pd.Series holding the input time-series to forecast
    model: pre-trained machine learning model
    lags: list of lags used for training the model
    n_steps: number of time periods in the forecasting horizon
    step: forecasting time period
    
    Returns
    -------
    fcast_values: pd.Series with forecasted values 
    """
    
    # get the dates to forecast
    last_date = y.index[-1] + pd.Timedelta(hours=1)
    fcast_range = pd.date_range(last_date, 
                                periods=n_steps, 
                                freq=step)
    fcasted_values = []
    target = y.copy()
    
    for date in fcast_range:
      
        # build target time series using previously forecast value
        new_point = fcasted_values[-1] if len(fcasted_values) > 0 else 0.0   
        target = target.append(pd.Series(index=[date], data=new_point))
        
        # build feature vector using previous forecast values
        features = create_ts_features(target, lags=lags)
        
        # forecast
        predictions = model.predict(features)
        fcasted_values.append(predictions[-1])
        
    return pd.Series(index=fcast_range, data=fcasted_values)