def test_save_pfs(): # Regression xgboost_regressor_cls = get_xgboost_learner('xgboost.XGBRegressor') dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building path = 'Abalone' results = features_df.kxy.fit(target_column, xgboost_regressor_cls, \ problem_type='regression', feature_selection_method='pfs', \ path=path) loaded_predictor = PFSPredictor().load(path, xgboost_regressor_cls) feature_directions = loaded_predictor.feature_directions assert feature_directions.shape[1] == features_df.shape[1] - 1 predictions = loaded_predictor.predict(features_df) assert len(predictions.columns) == 1 assert target_column in predictions.columns assert set(features_df.index).difference(set(predictions.index)) == set() assert set(predictions.index).difference(set(features_df.index)) == set()
def test_lean_boosted_xgboost_regressor(): for clz in ['xgboost.XGBRegressor']: # Regression xgboost_regressor_cls = get_xgboost_learner(clz) dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, xgboost_regressor_cls, \ problem_type='regression', additive_learning=True, return_scores=True, \ n_down_perf_before_stop=1) model = results['predictor'].models[0] feature_columns = results['Selected Variables'] x = features_df[feature_columns].values predictions = model.predict(x) path = '../kxy/misc/cache/%s-%s.sav' % (dataset.name, clz) model.save(path) loaded_model = xgboost_regressor_cls(path=path) loaded_predictions = loaded_model.predict(x) assert np.allclose(predictions, loaded_predictions)
def test_rfe_predictor_xgboost(): for clz in ['xgboost.XGBRegressor']: # Regression xgboost_regressor_cls = get_xgboost_learner(clz) dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, xgboost_regressor_cls, \ problem_type='regression', feature_selection_method='rfe', rfe_n_features=5) predictor = results['predictor'] predictions = predictor.predict(features_df) path = '../kxy/misc/cache/%s-%s.sav' % (dataset.name, clz) predictor.save(path) loaded_predictor = RFEPredictor.load(path, xgboost_regressor_cls) loaded_predictions = loaded_predictor.predict(features_df) assert np.allclose(predictions, loaded_predictions)
def test_xgboost_regression(): regressor_cls = get_xgboost_learner('xgboost.XGBRegressor', random_state=0) fs = RFE(regressor_cls) dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Feature selection x_columns = [_ for _ in features_df.columns if _ != target_column] x_df = features_df[x_columns] y_df = features_df[[target_column]] n_vars = max(x_df.shape[1] - 5, 1) m = fs.fit(x_df, y_df, n_vars) # Assertions assert len(fs.selected_variables) == n_vars assert fs.selected_variables == ['Shell weight', 'Sex_I', 'Shucked weight.ABS(* - Q25(*))', 'Shucked weight', 'Shucked weight.ABS(* - MEDIAN(*))', \ 'Shucked weight.ABS(* - MEAN(*))', 'Diameter.ABS(* - Q75(*))', 'Height.ABS(* - Q75(*))', 'Diameter.ABS(* - MEAN(*))', 'Diameter.ABS(* - Q25(*))', \ 'Whole weight.ABS(* - MEDIAN(*))', 'Viscera weight.ABS(* - Q75(*))', 'Sex_M', 'Height.ABS(* - MEAN(*))', 'Shucked weight.ABS(* - Q75(*))', \ 'Viscera weight.ABS(* - MEAN(*))', 'Height.ABS(* - Q25(*))', 'Whole weight.ABS(* - MEAN(*))', 'Shell weight.ABS(* - Q25(*))', 'Whole weight.ABS(* - Q25(*))', \ 'Length.ABS(* - MEAN(*))', 'Length.ABS(* - Q75(*))', 'Whole weight.ABS(* - Q75(*))', 'Diameter.ABS(* - MEDIAN(*))', 'Shell weight.ABS(* - Q75(*))', \ 'Shell weight.ABS(* - MEAN(*))', 'Shell weight.ABS(* - MEDIAN(*))', 'Length.ABS(* - MEDIAN(*))', 'Sex_F', 'Viscera weight', 'Whole weight', \ 'Length.ABS(* - Q25(*))', 'Viscera weight.ABS(* - MEDIAN(*))']
def test_xgboost_classifier(): # Binary classification classifier_cls = get_xgboost_learner('xgboost.XGBClassifier', use_label_encoder=False, eval_metric='logloss', learning_rate=0.1, max_depth=10) fs = RFE(classifier_cls) dataset = BankNote() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Feature selection x_columns = [_ for _ in features_df.columns if _ != target_column] x_df = features_df[x_columns] y_df = features_df[[target_column]] n_vars = max(x_df.shape[1] - 5, 1) m = fs.fit(x_df, y_df, n_vars) # Assertions assert len(fs.selected_variables) == n_vars assert fs.selected_variables == ['Variance', 'Skewness', 'Kurtosis', 'Entropy', 'Skewness.ABS(* - MEDIAN(*))', \ 'Variance.ABS(* - MEAN(*))', 'Skewness.ABS(* - MEAN(*))', 'Kurtosis.ABS(* - MEDIAN(*))', 'Kurtosis.ABS(* - Q25(*))', \ 'Entropy.ABS(* - MEDIAN(*))', 'Skewness.ABS(* - Q25(*))', 'Entropy.ABS(* - MEAN(*))', 'Variance.ABS(* - Q25(*))', \ 'Kurtosis.ABS(* - MEAN(*))', 'Kurtosis.ABS(* - Q75(*))']
def test_xgboost_regression(): regressor_cls = get_xgboost_learner('xgboost.XGBRegressor', random_state=0) fs = Boruta(regressor_cls) dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Feature selection x_columns = [_ for _ in features_df.columns if _ != target_column] x_df = features_df[x_columns] y_df = features_df[[target_column]] m = fs.fit(x_df, y_df) # Assertions assert len(fs.selected_variables) == 5 assert fs.selected_variables == [ 'Shucked weight', 'Shell weight', 'Sex_I', 'Shucked weight.ABS(* - Q25(*))', 'Whole weight' ]
def test_lean_boosted_xgboost_classifier(): # Binary classification xgboost_classifier_cls = get_xgboost_learner('xgboost.XGBClassifier', use_label_encoder=False, eval_metric='logloss', learning_rate=0.1, max_depth=10) dataset = BankNote() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, xgboost_classifier_cls, \ problem_type='classification', additive_learning=True, return_scores=True, \ n_down_perf_before_stop=1) assert results['Testing Accuracy'] == '0.974' assert results['Selected Variables'] == [ 'Variance', 'Skewness.ABS(* - Q25(*))', 'Kurtosis' ]
def test_boruta(): # Regression sklearn_regressor_cls = get_xgboost_learner('xgboost.XGBRegressor') dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, sklearn_regressor_cls, \ problem_type='regression', feature_selection_method='boruta', boruta_n_evaluations=100) assert results['Selected Variables'] == ['Shucked weight', 'Shell weight', 'Sex_I', \ 'Shucked weight.ABS(* - Q25(*))', 'Whole weight']
def test_single_learner(): # Regression xgboost_regressor_cls = get_xgboost_learner('xgboost.XGBRegressor') dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, xgboost_regressor_cls, \ problem_type='regression', start_n_features=2, min_n_features=2, max_n_features=2, \ additive_learning=True, return_scores=True, n_down_perf_before_stop=1) assert results['Testing R-Squared'] == '0.493' assert results['Selected Variables'] == ['Shell weight', 'Shucked weight'] assert len(features_df.kxy.predictor.models) == 1
def test_lean_boosted_xgboost_regressor(): # Regression xgboost_regressor_cls = get_xgboost_learner('xgboost.XGBRegressor') dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, xgboost_regressor_cls, \ problem_type='regression', additive_learning=True, return_scores=True, \ n_down_perf_before_stop=1) assert results['Testing R-Squared'] == '0.496' assert results['Selected Variables'] == ['Shell weight', 'Shucked weight', 'Whole weight', \ 'Shell weight.ABS(* - Q25(*))', 'Viscera weight.ABS(* - MEDIAN(*))', 'Viscera weight.ABS(* - MEAN(*))', \ 'Height', 'Length', 'Diameter', 'Sex_I', 'Shucked weight.ABS(* - MEDIAN(*))', 'Diameter.ABS(* - MEDIAN(*))', \ 'Viscera weight.ABS(* - Q75(*))', 'Viscera weight.ABS(* - Q25(*))', 'Diameter.ABS(* - Q25(*))', 'Sex_M', 'Sex_F']
def test_pfs_feature_selection(): # Regression xgboost_regressor_cls = get_xgboost_learner('xgboost.XGBRegressor') dataset = Abalone() target_column = dataset.y_column df = dataset.df # Features generation features_df = df.kxy.generate_features(entity=None, max_lag=None, entity_name='*', exclude=[target_column]) # Model building results = features_df.kxy.fit(target_column, xgboost_regressor_cls, \ problem_type='regression', feature_selection_method='pfs') assert results['Feature Directions'].shape[1] == features_df.shape[1] - 1 predictor = results['predictor'] predictions = predictor.predict(features_df) assert len(predictions.columns) == 1 assert target_column in predictions.columns assert set(features_df.index).difference(set(predictions.index)) == set() assert set(predictions.index).difference(set(features_df.index)) == set()
def xgboost_classification_benchmark(): # LeanML vs Boruta vs RFE xgboost_classifier_cls = get_xgboost_learner('xgboost.XGBClassifier') classification_benchmark(xgboost_classifier_cls, 'xgboost')
def xgboost_regression_benchmark(): # LeanML vs Boruta vs RFE xgboost_regressor_cls = get_xgboost_learner('xgboost.XGBRegressor') regression_benchmark(xgboost_regressor_cls, 'xgboost')