tabensemb.data.dataimputer.MiceImputer.fit_transform

method

MiceImputer.fit_transform(input_data: DataFrame, datamodule: DataModule) → DataFrame

Record feature names in the datamodule, fit the imputer and transform the input dataframe. This should be performed on the training and validation sets. Missing values in categorical features are filled by “UNK”. Continuous features that are totally missing will not be imputed.

Parameters:

input_data:

A tabular dataset.

datamodule:

A DataModule instance that contains necessary information required by imputers.

Returns:

pd.DataFrame

A transformed tabular dataset.