def test_estimator_does_not_support_feature_names():
"""SelectFromModel works with estimators that do not support feature_names_in_.
Non-regression test for #21949.
"""
pytest.importorskip("pandas")
X, y = datasets.load_iris(as_frame=True, return_X_y=True)
all_feature_names = set(X.columns)
def importance_getter(estimator):
return np.arange(X.shape[1])
selector = SelectFromModel(
MinimalClassifier(), importance_getter=importance_getter
).fit(X, y)
# selector learns the feature names itself
assert_array_equal(selector.feature_names_in_, X.columns)
feature_names_out = set(selector.get_feature_names_out())
assert feature_names_out < all_feature_names
with pytest.warns(None) as records:
selector.transform(X.iloc[1:3])
assert not [w.message for w in records]
def test_prefit_get_feature_names_out():
"""Check the interaction between prefit and the feature names."""
clf = RandomForestClassifier(n_estimators=2, random_state=0)
clf.fit(data, y)
model = SelectFromModel(clf, prefit=True, max_features=1)
# FIXME: the error message should be improved. Raising a `NotFittedError`
# would be better since it would force to validate all class attribute and
# create all the necessary fitted attribute
err_msg = "Unable to generate feature names without n_features_in_"
with pytest.raises(ValueError, match=err_msg):
model.get_feature_names_out()
model.fit(data, y)
feature_names = model.get_feature_names_out()
assert feature_names == ["x3"]
