Forecaster
DirRecTabularRegressionForecaster
Dir-rec reduction from forecasting to tabular regression.
For the hybrid dir-rec strategy, a separate forecaster is fitted for each step ahead of the forecasting horizon and then the previous forecasting horizon is added as an input for training the next forecaster, following the recursive strategy.
Quickstart
python
from sktime.forecasting.compose import DirRecTabularRegressionForecaster
estimator = DirRecTabularRegressionForecaster(estimator, window_length=10, transformers=None, pooling='local')Tags
Capabilities
- Categorical features
- Prediction intervals
- Missing values
- In-sample predictions: Not supported
- In-sample prediction intervals: Not supported
- Exogenous variables: Not supported
- Multivariate: Not supported
Properties
- Needs forecast horizon in fitrequires-fh-in-fit
- Yes
- X and y need the same indexX-y-must-have-same-index
- Yes
Parameters(2)
- estimatorsklearn estimator object
- Tabular regressor.
- window_lengthint, optional (default=10)
- The length of the sliding window used to transform the series into a tabular matrix