RDT NullTransformer doesn't replace nulls if missing_value_generation is None

[amontanez24]

Environment Details

Please indicate the following details about the environment in which you found the bug:

• RDT version: 1.5.0
• Python version: Any
• Operating System: Any

Error Description

When setting the missing_value_generation to None and the missing_value_replacement to 'mean', I would expect the forward transform to impute the nans with the mean value. Instead it currently does nothing. This is because of the following line:

RDT/rdt/transformers/null.py

Line 129 in 3970e40

if self._missing_value_generation is None:

Steps to reproduce

data = pd.Series([1, 2, np.nan, 3])
nt = NullTransformer(missing_value_replacement='mean', missing_value_generation=None)
nt.fit(data)
nt.transform(data)