def test_key_error_feature_name_to_index(
self, X_columns, y_columns, target_to_feature_dict, expected
):
with pytest.raises(KeyError):
MultiFeatureGAR._feature_name_to_index(
target_to_feature_dict, X_columns, y_columns
)
def test_fit_target_to_feature_dict_working(self, data, X_y, estimator):
X, y = X_y
X_train, y_train, X_test, y_test = FeatureSplitter().transform(X, y)
target_to_feature_dict = data.draw(
str_target_to_feature_dicts(targets=y.columns, features=X.columns)
)
multi_feature_gar = MultiFeatureGAR(estimator)
multi_feature_gar.fit(X_train, y_train, target_to_features_dict=target_to_feature_dict)
def test_fit_target_to_feature_dict_consistent(self, data, X_y, estimator):
X, y = X_y
X_train, y_train, X_test, y_test = FeatureSplitter().transform(X, y)
target_to_feature_dict = data.draw(
str_target_to_feature_dicts(targets=y.columns, features=X.columns)
)
multi_feature_gar = MultiFeatureGAR(estimator)
multi_feature_gar.fit(X_train, y_train, target_to_features_dict=target_to_feature_dict)
for i, estimator_ in enumerate(multi_feature_gar.estimators_):
expected_n_features = len(target_to_feature_dict[y.columns[i]])
assert len(estimator_.coef_) == expected_n_features
def test_fit_as_multi_output_regressor_if_target_to_feature_none(
self, estimator, X_y
):
X, y = X_y
X_train, y_train, X_test, y_test = FeatureSplitter().transform(X, y)
multi_feature_gar = MultiFeatureGAR(estimator)
multi_feature_gar.fit(X_train, y_train)
gar = GAR(estimator)
gar.fit(X_train, y_train)
pd.testing.assert_frame_equal(
multi_feature_gar.predict(X_test), gar.predict(X_test),
)
def test_feature_name_to_index(
self, X_columns, y_columns, target_to_feature_dict, expected
):
computed = MultiFeatureGAR._feature_name_to_index(
target_to_feature_dict, X_columns, y_columns
)
for key, value in computed.items():
assert_array_equal(value, expected[key])
def test_predict_target_to_feature_dict_explainable(
self, data, X_y, estimator):
X, y = X_y
X_train, y_train, X_test, y_test = FeatureSplitter().transform(X, y)
target_to_feature_dict = data.draw(
str_target_to_feature_dicts(targets=y.columns, features=X.columns))
multi_feature_gar = MultiFeatureGAR(estimator, explainer_type="shap")
multi_feature_gar.target_to_features_dict = target_to_feature_dict
multi_feature_gar.fit(X_train, y_train)
multi_feature_gar.predict(X_test)
def test_error_predict_target_to_feature_dict_wrong_X_shape(
self, data, X_y, estimator):
X, y = X_y
X_train, y_train, X_test, y_test = FeatureSplitter().transform(X, y)
target_to_feature_dict = data.draw(
str_target_to_feature_dicts(targets=y.columns, features=X.columns))
multi_feature_gar = MultiFeatureGAR(
estimator, target_to_features_dict=target_to_feature_dict)
multi_feature_gar.fit(X_train, y_train)
X_test = X_test.iloc[:, :2]
with pytest.raises(ValueError):
multi_feature_gar.predict(X_test)
def test_error_predict_with_no_fit(self, estimator, X):
regressor = MultiFeatureGAR(estimator)
with pytest.raises(NotFittedError):
regressor.predict(X)
def test_constructor(self, estimator):
multi_feature_gar = MultiFeatureGAR(estimator)
assert multi_feature_gar.n_jobs == 1
