The above referenced whats_new/v0.20.rst mentions sklearn.impute.SimpleImputer, sklearn.preprocessing.FunctionTransformer (for the axis keyword), and numpy.nan (for the missing_values keyword) as replacements.
I have no experience with scikit-learn so am not able to offer further assistance/PRs, unfortunately.
scikit-learn deprecated the
sklearn.preprocessing.Imputer
in0.20.0
and removed it in0.22.0
: https://github.com/scikit-learn/scikit-learn/blame/0.22.1/doc/whats_new/v0.20.rst#L1444-L1468This means
py_entitymatching
is incompatible withscikit-learn >=0.22
due to https://github.com/anhaidgroup/py_entitymatching/blob/v0.3.2/py_entitymatching/matcher/matcherutils.py#L11 and https://github.com/anhaidgroup/py_entitymatching/blob/v0.3.2/py_entitymatching/matcher/matcherutils.py#L221-L224This in turn means
py_entitymatching
does not fully work with Python 3.8 sincescikit-learn <0.22
does not support the latter. ref: https://github.com/conda-forge/py_entitymatching-feedstock/pull/3The above referenced
whats_new/v0.20.rst
mentionssklearn.impute.SimpleImputer
,sklearn.preprocessing.FunctionTransformer
(for theaxis
keyword), andnumpy.nan
(for themissing_values
keyword) as replacements. I have no experience with scikit-learn so am not able to offer further assistance/PRs, unfortunately.