tabensemb.data.datamodule.DataModule.get_base_predictor#

method

DataModule.get_base_predictor(categorical: bool = True, **kwargs) → Pipeline | RandomForestRegressor[source]#

Get a sklearn RandomForestRegressor for fundamental usages like pre-processing.

Parameters:

categorical: Whether to include OneHotEncoder for categorical features.
kwargs: Arguments for sklearn.ensemble.RandomForestRegressor

Returns:

sklearn.pipeline.Pipeline or sklearn.ensemble.RandomForestRegressor: A Pipeline if categorical is True, or a RandomForestRegressor if categorical is False.