def test_rename_column_names_to_numeric():
X = np.array([[1, 2], [3, 4]])
pd.testing.assert_frame_equal(_rename_column_names_to_numeric(X),
pd.DataFrame(X))
X = pd.DataFrame({"<>": [1, 2], ">>": [2, 4]})
pd.testing.assert_frame_equal(_rename_column_names_to_numeric(X),
pd.DataFrame({
0: [1, 2],
1: [2, 4]
}))
X = ww.DataTable(pd.DataFrame({
"<>": [1, 2],
">>": [2, 4]
}),
logical_types={
"<>": "categorical",
">>": "categorical"
})
X_renamed = _rename_column_names_to_numeric(X)
X_expected = pd.DataFrame({
0: pd.Series([1, 2], dtype="category"),
1: pd.Series([2, 4], dtype="category")
})
pd.testing.assert_frame_equal(X_renamed.to_dataframe(), X_expected)
assert X_renamed.logical_types == {
0: ww.logical_types.Categorical,
1: ww.logical_types.Categorical
}
def _encode_categories(self, X, fit=False):
"""Encodes each categorical feature using ordinal encoding."""
X_encoded = _convert_to_woodwork_structure(X)
X_encoded = _rename_column_names_to_numeric(X_encoded)
cat_cols = list(X_encoded.select('category').columns)
X_encoded = _convert_woodwork_types_wrapper(X_encoded.to_dataframe())
if len(cat_cols) == 0:
return X_encoded
if fit:
self._ordinal_encoder = OrdinalEncoder()
encoder_output = self._ordinal_encoder.fit_transform(X_encoded[cat_cols])
else:
encoder_output = self._ordinal_encoder.transform(X_encoded[cat_cols])
X_encoded[cat_cols] = pd.DataFrame(encoder_output)
X_encoded[cat_cols] = X_encoded[cat_cols].astype('category')
return X_encoded
def predict_proba(self, X):
X = _rename_column_names_to_numeric(X, flatten_tuples=False)
return super().predict_proba(X)
def fit(self, X, y=None):
X, y = super()._manage_woodwork(X, y)
self.input_feature_names = list(X.columns)
X = _rename_column_names_to_numeric(X, flatten_tuples=False)
self._component_obj.fit(X, y)
return self
def predict(self, X):
X = _rename_column_names_to_numeric(X)
predictions = super().predict(X)
return predictions
def fit(self, X, y=None):
X = _rename_column_names_to_numeric(X)
return super().fit(X, y)
def predict_proba(self, X):
X = _rename_column_names_to_numeric(X)
return super().predict_proba(X)
