def test_featuretools_index(mock_calculate_feature_matrix, mock_dfs, X_y_multi): X, y = X_y_multi X_pd = pd.DataFrame(X) X_new_index = X_pd.copy() index = [i for i in range(len(X))] new_index = [i * 2 for i in index] X_new_index['index'] = new_index mock_calculate_feature_matrix.return_value = pd.DataFrame({}) # check if _make_entity_set keeps the intended index feature = DFSTransformer() feature.fit(X_new_index) feature.transform(X_new_index) arg_es = mock_dfs.call_args[1]['entityset'].entities[0].df['index'] arg_tr = mock_calculate_feature_matrix.call_args[1]['entityset'].entities[0].df['index'] assert arg_es.to_list() == new_index assert arg_tr.to_list() == new_index # check if _make_entity_set fills in the proper index values feature.fit(X_pd) feature.transform(X_pd) arg_es = mock_dfs.call_args[1]['entityset'].entities[0].df['index'] arg_tr = mock_calculate_feature_matrix.call_args[1]['entityset'].entities[0].df['index'] assert arg_es.to_list() == index assert arg_tr.to_list() == index
def test_dfs_sets_max_depth_1(mock_dfs, X_y_multi): X, y = X_y_multi X_pd = pd.DataFrame(X) feature = DFSTransformer() feature.fit(X_pd, y) _, kwargs = mock_dfs.call_args assert kwargs['max_depth'] == 1
def test_ft_woodwork_custom_overrides_returned_by_components(X_df): y = pd.Series([1, 2, 1]) override_types = [Integer, Double, Categorical, Datetime, Boolean] for logical_type in override_types: try: X = ww.DataTable(X_df.copy(), logical_types={0: logical_type}) except TypeError: continue dft = DFSTransformer() dft.fit(X, y) transformed = dft.transform(X, y) assert isinstance(transformed, ww.DataTable) if logical_type == Datetime: assert transformed.logical_types == {'DAY(0)': Integer, 'MONTH(0)': Integer, 'WEEKDAY(0)': Integer, 'YEAR(0)': Integer} else: assert transformed.logical_types == {'0': logical_type}
def test_transform_subset(X_y_binary, X_y_multi, X_y_regression): datasets = locals() for dataset in datasets.values(): X, y = dataset X_pd = pd.DataFrame(X) X_pd.columns = X_pd.columns.astype(str) X_fit = X_pd.iloc[: len(X) // 3] X_transform = X_pd.iloc[len(X) // 3:] es = ft.EntitySet() es = es.entity_from_dataframe(entity_id="X", dataframe=X_transform, index='index', make_index=True) feature_matrix, features = ft.dfs(entityset=es, target_entity="X") feature = DFSTransformer() feature.fit(X_fit) X_t = feature.transform(X_transform) assert_frame_equal(feature_matrix, X_t.to_dataframe())
def test_numeric_columns(X_y_multi): X, y = X_y_multi X_pd = pd.DataFrame(X) feature = DFSTransformer() feature.fit(X_pd, y) feature.transform(X_pd)
def test_describe_component(): enc = OneHotEncoder() imputer = Imputer() simple_imputer = SimpleImputer("mean") column_imputer = PerColumnImputer({"a": "mean", "b": ("constant", 100)}) scaler = StandardScaler() feature_selection_clf = RFClassifierSelectFromModel(n_estimators=10, number_features=5, percent_features=0.3, threshold=-np.inf) feature_selection_reg = RFRegressorSelectFromModel(n_estimators=10, number_features=5, percent_features=0.3, threshold=-np.inf) drop_col_transformer = DropColumns(columns=['col_one', 'col_two']) drop_null_transformer = DropNullColumns() datetime = DateTimeFeaturizer() text_featurizer = TextFeaturizer() lsa = LSA() pca = PCA() lda = LinearDiscriminantAnalysis() ft = DFSTransformer() us = Undersampler() assert enc.describe(return_dict=True) == {'name': 'One Hot Encoder', 'parameters': {'top_n': 10, 'features_to_encode': None, 'categories': None, 'drop': 'if_binary', 'handle_unknown': 'ignore', 'handle_missing': 'error'}} assert imputer.describe(return_dict=True) == {'name': 'Imputer', 'parameters': {'categorical_impute_strategy': "most_frequent", 'categorical_fill_value': None, 'numeric_impute_strategy': "mean", 'numeric_fill_value': None}} assert simple_imputer.describe(return_dict=True) == {'name': 'Simple Imputer', 'parameters': {'impute_strategy': 'mean', 'fill_value': None}} assert column_imputer.describe(return_dict=True) == {'name': 'Per Column Imputer', 'parameters': {'impute_strategies': {'a': 'mean', 'b': ('constant', 100)}, 'default_impute_strategy': 'most_frequent'}} assert scaler.describe(return_dict=True) == {'name': 'Standard Scaler', 'parameters': {}} assert feature_selection_clf.describe(return_dict=True) == {'name': 'RF Classifier Select From Model', 'parameters': {'number_features': 5, 'n_estimators': 10, 'max_depth': None, 'percent_features': 0.3, 'threshold': -np.inf, 'n_jobs': -1}} assert feature_selection_reg.describe(return_dict=True) == {'name': 'RF Regressor Select From Model', 'parameters': {'number_features': 5, 'n_estimators': 10, 'max_depth': None, 'percent_features': 0.3, 'threshold': -np.inf, 'n_jobs': -1}} assert drop_col_transformer.describe(return_dict=True) == {'name': 'Drop Columns Transformer', 'parameters': {'columns': ['col_one', 'col_two']}} assert drop_null_transformer.describe(return_dict=True) == {'name': 'Drop Null Columns Transformer', 'parameters': {'pct_null_threshold': 1.0}} assert datetime.describe(return_dict=True) == {'name': 'DateTime Featurization Component', 'parameters': {'features_to_extract': ['year', 'month', 'day_of_week', 'hour'], 'encode_as_categories': False}} assert text_featurizer.describe(return_dict=True) == {'name': 'Text Featurization Component', 'parameters': {}} assert lsa.describe(return_dict=True) == {'name': 'LSA Transformer', 'parameters': {}} assert pca.describe(return_dict=True) == {'name': 'PCA Transformer', 'parameters': {'n_components': None, 'variance': 0.95}} assert lda.describe(return_dict=True) == {'name': 'Linear Discriminant Analysis Transformer', 'parameters': {'n_components': None}} assert ft.describe(return_dict=True) == {'name': 'DFS Transformer', 'parameters': {"index": "index"}} assert us.describe(return_dict=True) == {'name': 'Undersampler', 'parameters': {"balanced_ratio": 4, "min_samples": 100, "min_percentage": 0.1}} # testing estimators base_classifier = BaselineClassifier() base_regressor = BaselineRegressor() lr_classifier = LogisticRegressionClassifier() en_classifier = ElasticNetClassifier() en_regressor = ElasticNetRegressor() et_classifier = ExtraTreesClassifier(n_estimators=10, max_features="auto") et_regressor = ExtraTreesRegressor(n_estimators=10, max_features="auto") rf_classifier = RandomForestClassifier(n_estimators=10, max_depth=3) rf_regressor = RandomForestRegressor(n_estimators=10, max_depth=3) linear_regressor = LinearRegressor() svm_classifier = SVMClassifier() svm_regressor = SVMRegressor() assert base_classifier.describe(return_dict=True) == {'name': 'Baseline Classifier', 'parameters': {'strategy': 'mode'}} assert base_regressor.describe(return_dict=True) == {'name': 'Baseline Regressor', 'parameters': {'strategy': 'mean'}} assert lr_classifier.describe(return_dict=True) == {'name': 'Logistic Regression Classifier', 'parameters': {'penalty': 'l2', 'C': 1.0, 'n_jobs': -1, 'multi_class': 'auto', 'solver': 'lbfgs'}} assert en_classifier.describe(return_dict=True) == {'name': 'Elastic Net Classifier', 'parameters': {'alpha': 0.5, 'l1_ratio': 0.5, 'n_jobs': -1, 'max_iter': 1000, "loss": 'log', 'penalty': 'elasticnet'}} assert en_regressor.describe(return_dict=True) == {'name': 'Elastic Net Regressor', 'parameters': {'alpha': 0.5, 'l1_ratio': 0.5, 'max_iter': 1000, 'normalize': False}} assert et_classifier.describe(return_dict=True) == {'name': 'Extra Trees Classifier', 'parameters': {'n_estimators': 10, 'max_features': 'auto', 'max_depth': 6, 'min_samples_split': 2, 'min_weight_fraction_leaf': 0.0, 'n_jobs': -1}} assert et_regressor.describe(return_dict=True) == {'name': 'Extra Trees Regressor', 'parameters': {'n_estimators': 10, 'max_features': 'auto', 'max_depth': 6, 'min_samples_split': 2, 'min_weight_fraction_leaf': 0.0, 'n_jobs': -1}} assert rf_classifier.describe(return_dict=True) == {'name': 'Random Forest Classifier', 'parameters': {'n_estimators': 10, 'max_depth': 3, 'n_jobs': -1}} assert rf_regressor.describe(return_dict=True) == {'name': 'Random Forest Regressor', 'parameters': {'n_estimators': 10, 'max_depth': 3, 'n_jobs': -1}} assert linear_regressor.describe(return_dict=True) == {'name': 'Linear Regressor', 'parameters': {'fit_intercept': True, 'normalize': False, 'n_jobs': -1}} assert svm_classifier.describe(return_dict=True) == {'name': 'SVM Classifier', 'parameters': {'C': 1.0, 'kernel': 'rbf', 'gamma': 'scale', 'probability': True}} assert svm_regressor.describe(return_dict=True) == {'name': 'SVM Regressor', 'parameters': {'C': 1.0, 'kernel': 'rbf', 'gamma': 'scale'}} try: xgb_classifier = XGBoostClassifier(eta=0.1, min_child_weight=1, max_depth=3, n_estimators=75) xgb_regressor = XGBoostRegressor(eta=0.1, min_child_weight=1, max_depth=3, n_estimators=75) assert xgb_classifier.describe(return_dict=True) == {'name': 'XGBoost Classifier', 'parameters': {'eta': 0.1, 'max_depth': 3, 'min_child_weight': 1, 'n_estimators': 75}} assert xgb_regressor.describe(return_dict=True) == {'name': 'XGBoost Regressor', 'parameters': {'eta': 0.1, 'max_depth': 3, 'min_child_weight': 1, 'n_estimators': 75}} except ImportError: pass try: cb_classifier = CatBoostClassifier() cb_regressor = CatBoostRegressor() assert cb_classifier.describe(return_dict=True) == {'name': 'CatBoost Classifier', 'parameters': {'allow_writing_files': False, 'n_estimators': 10, 'eta': 0.03, 'max_depth': 6, 'bootstrap_type': None, 'silent': True}} assert cb_regressor.describe(return_dict=True) == {'name': 'CatBoost Regressor', 'parameters': {'allow_writing_files': False, 'n_estimators': 10, 'eta': 0.03, 'max_depth': 6, 'bootstrap_type': None, 'silent': False}} except ImportError: pass try: lg_classifier = LightGBMClassifier() lg_regressor = LightGBMRegressor() assert lg_classifier.describe(return_dict=True) == {'name': 'LightGBM Classifier', 'parameters': {'boosting_type': 'gbdt', 'learning_rate': 0.1, 'n_estimators': 100, 'max_depth': 0, 'num_leaves': 31, 'min_child_samples': 20, 'n_jobs': -1, 'bagging_fraction': 0.9, 'bagging_freq': 0}} assert lg_regressor.describe(return_dict=True) == {'name': 'LightGBM Regressor', 'parameters': {'boosting_type': 'gbdt', 'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 0, 'num_leaves': 31, 'min_child_samples': 20, 'n_jobs': -1, 'bagging_fraction': 0.9, 'bagging_freq': 0}} except ImportError: pass
def test_transform(X_y_binary, X_y_multi, X_y_regression): datasets = locals() for dataset in datasets.values(): X, y = dataset X_pd = pd.DataFrame(X) X_pd.columns = X_pd.columns.astype(str) es = ft.EntitySet() es = es.entity_from_dataframe(entity_id="X", dataframe=X_pd, index='index', make_index=True) feature_matrix, features = ft.dfs(entityset=es, target_entity="X") feature = DFSTransformer() feature.fit(X) X_t = feature.transform(X) assert_frame_equal(feature_matrix, X_t.to_dataframe()) assert features == feature.features feature.fit(X, y) feature.transform(X) X_ww = ww.DataTable(X_pd) feature.fit(X_ww) feature.transform(X_ww)
def test_index_errors(X_y_binary): with pytest.raises(TypeError, match="Index provided must be string"): DFSTransformer(index=0) with pytest.raises(TypeError, match="Index provided must be string"): DFSTransformer(index=None)