FreqEncoder

class lightautoml.transformers.categorical.FreqEncoder(*args, **kwargs)[source]

Bases: LabelEncoder

Labels are encoded with frequency in train data.

Labels are integers from 1 to n. Unknown category encoded as 1.

fit(dataset)[source]

Estimate label frequencies and create encoding dicts.

Parameters:

dataset (Union[NumpyDataset, PandasDataset]) – Pandas or Numpy dataset of categorical features

Returns:

self.