def run_pipeline_from_automl(train_file_path: str, test_file_path: str, max_run_time: timedelta = timedelta(minutes=10)): """ Function run pipeline with Auto ML models in nodes :param train_file_path: path to the csv file with data for train :param test_file_path: path to the csv file with data for validation :param max_run_time: maximum running time for customization of the "tpot" model :return roc_auc_value: ROC AUC metric for pipeline """ train_data = InputData.from_csv(train_file_path) test_data = InputData.from_csv(test_file_path) testing_target = test_data.target node_scaling = PrimaryNode('scaling') node_tpot = PrimaryNode('tpot') node_tpot.operation.params = {'max_run_time_sec': max_run_time.seconds} node_lda = SecondaryNode('lda', nodes_from=[node_scaling]) node_rf = SecondaryNode('rf', nodes_from=[node_tpot, node_lda]) OperationTypesRepository.assign_repo('model', 'automl_repository.json') pipeline = Pipeline(node_rf) pipeline.fit(train_data) results = pipeline.predict(test_data) roc_auc_value = roc_auc(y_true=testing_target, y_score=results.predict) print(roc_auc_value) return roc_auc_value
def test_forecast_with_exog(): train_source_ts, predict_source_ts, train_exog_ts, predict_exog_ts, ts_test = synthetic_with_exogenous_ts( ) # Source data for lagged node node_lagged = PrimaryNode('lagged') # Set window size for lagged transformation node_lagged.custom_params = {'window_size': window_size} # Exogenous variable for exog node node_exog = PrimaryNode('exog_ts_data_source') node_final = SecondaryNode('linear', nodes_from=[node_lagged, node_exog]) pipeline = Pipeline(node_final) pipeline.fit(input_data=MultiModalData({ 'exog_ts_data_source': train_exog_ts, 'lagged': train_source_ts })) forecast = pipeline.predict( input_data=MultiModalData({ 'exog_ts_data_source': predict_exog_ts, 'lagged': predict_source_ts })) prediction = np.ravel(np.array(forecast.predict)) assert tuple(prediction) == tuple(ts_test)
def test_save_load_fitted_atomized_pipeline_correctly(): pipeline = create_pipeline_with_several_nested_atomized_model() train_data, test_data = create_data_for_train() pipeline.fit(train_data) json_actual = pipeline.save( 'test_save_load_fitted_atomized_pipeline_correctly') json_path_load = create_correct_path( 'test_save_load_fitted_atomized_pipeline_correctly') pipeline_loaded = Pipeline() pipeline_loaded.load(json_path_load) json_expected = pipeline_loaded.save( 'test_save_load_fitted_atomized_pipeline_correctly_loaded') assert pipeline.length == pipeline_loaded.length assert json_actual == json_expected before_save_predicted = pipeline.predict(test_data) pipeline_loaded.fit(train_data) after_save_predicted = pipeline_loaded.predict(test_data) bfr_tun_mse = mean_squared_error(y_true=test_data.target, y_pred=before_save_predicted.predict) aft_tun_mse = mean_squared_error(y_true=test_data.target, y_pred=after_save_predicted.predict) assert aft_tun_mse <= bfr_tun_mse
def run_tpot_vs_fedot_example(train_file_path: str, test_file_path: str): train_data = InputData.from_csv(train_file_path) test_data = InputData.from_csv(test_file_path) training_features = train_data.features testing_features = test_data.features training_target = train_data.target testing_target = test_data.target # Average CV score on the training set was: 0.93755 exported_pipeline = make_pipeline( StackingEstimator(estimator=BernoulliNB()), RandomForestClassifier()) # Fix random state for all the steps in exported pipeline set_param_recursive(exported_pipeline.steps, 'random_state', 1) exported_pipeline.fit(training_features, training_target) results = exported_pipeline.predict_proba(testing_features)[:, 1] roc_auc_value = roc_auc(y_true=testing_target, y_score=results) print(f'ROC AUC for TPOT: {roc_auc_value}') node_scaling = PrimaryNode('scaling') node_bernb = SecondaryNode('bernb', nodes_from=[node_scaling]) node_rf = SecondaryNode('rf', nodes_from=[node_bernb, node_scaling]) pipeline = Pipeline(node_rf) pipeline.fit(train_data) results = pipeline.predict(test_data) roc_auc_value = roc_auc(y_true=testing_target, y_score=results.predict) print(f'ROC AUC for FEDOT: {roc_auc_value}') return roc_auc_value
def _get_metric_value(self, pipeline: Pipeline, metric: MetricByTask) -> float: pipeline.fit(self._train_data, use_fitted=False) predicted = pipeline.predict(self._test_data) metric_value = metric.get_value(true=self._test_data, predicted=predicted) return metric_value
def test_data_preparation_for_multi_target_correct(multi_target_data_setup): train, test = multi_target_data_setup simple_pipeline = Pipeline(PrimaryNode('linear')) simple_pipeline.fit(input_data=train) source_shape = test.target.shape # Get converted data results, new_test = QualityMetric()._simple_prediction( simple_pipeline, test) number_elements = len(new_test.target) assert source_shape[0] * source_shape[1] == number_elements
def test_pipeline_with_wrong_data(): pipeline = Pipeline(PrimaryNode('linear')) data_seq = np.arange(0, 10) task = Task(TaskTypesEnum.ts_forecasting, TsForecastingParams(forecast_length=10)) data = InputData(idx=data_seq, features=data_seq, target=data_seq, data_type=DataTypesEnum.ts, task=task) with pytest.raises(ValueError): pipeline.fit(data)
def test_pipeline_unfit(data_fixture, request): data = request.getfixturevalue(data_fixture) pipeline = Pipeline(PrimaryNode('logit')) pipeline.fit(data) assert pipeline.is_fitted pipeline.unfit() assert not pipeline.is_fitted assert not pipeline.root_node.fitted_operation with pytest.raises(ValueError) as exc: assert pipeline.predict(data)
def execute_pipeline_for_text_problem(train_data, test_data): node_text_clean = PrimaryNode('text_clean') node_tfidf = SecondaryNode('tfidf', nodes_from=[node_text_clean]) model_node = SecondaryNode('multinb', nodes_from=[node_tfidf]) pipeline = Pipeline(model_node) pipeline.fit(train_data) predicted = pipeline.predict(test_data) roc_auc_metric = roc_auc(y_true=test_data.target, y_score=predicted.predict) return roc_auc_metric
def test_import_custom_json_object_to_pipeline_and_fit_correctly_no_exception(): test_file_path = str(os.path.dirname(__file__)) file = '../../data/test_custom_json_template.json' json_path_load = os.path.join(test_file_path, file) train_file_path, test_file_path = get_scoring_case_data_paths() train_data = InputData.from_csv(train_file_path) pipeline = Pipeline() pipeline.load(json_path_load) pipeline.fit(train_data) pipeline.save('test_import_custom_json_object_to_pipeline_and_fit_correctly_no_exception')
def test_log_clustering_fit_correct(data_fixture, request): data = request.getfixturevalue(data_fixture) train_data, test_data = train_test_data_setup(data=data) # Scaling pipeline. Fit predict it scaling_pipeline = Pipeline(PrimaryNode('normalization')) scaling_pipeline.fit(train_data) scaled_data = scaling_pipeline.predict(train_data) kmeans = Model(operation_type='kmeans') _, train_predicted = kmeans.fit(data=scaled_data) assert all(np.unique(train_predicted.predict) == [0, 1])
def test_secondary_nodes_is_invariant_to_inputs_order(data_setup): data = data_setup train, test = train_test_data_setup(data) first = PrimaryNode(operation_type='logit') second = PrimaryNode(operation_type='lda') third = PrimaryNode(operation_type='knn') final = SecondaryNode(operation_type='xgboost', nodes_from=[first, second, third]) pipeline = Pipeline() for node in [first, second, third, final]: pipeline.add_node(node) first = deepcopy(first) second = deepcopy(second) third = deepcopy(third) final_shuffled = SecondaryNode(operation_type='xgboost', nodes_from=[third, first, second]) pipeline_shuffled = Pipeline() # change order of nodes in list for node in [final_shuffled, third, first, second]: pipeline_shuffled.add_node(node) train_predicted = pipeline.fit(input_data=train) train_predicted_shuffled = pipeline_shuffled.fit(input_data=train) # train results should be invariant assert pipeline.root_node.descriptive_id == pipeline_shuffled.root_node.descriptive_id assert np.equal(train_predicted.predict, train_predicted_shuffled.predict).all() test_predicted = pipeline.predict(input_data=test) test_predicted_shuffled = pipeline_shuffled.predict(input_data=test) # predict results should be invariant assert np.equal(test_predicted.predict, test_predicted_shuffled.predict).all() # change parents order for the nodes fitted pipeline nodes_for_change = pipeline.nodes[3].nodes_from pipeline.nodes[3].nodes_from = [nodes_for_change[2], nodes_for_change[0], nodes_for_change[1]] pipeline.nodes[3].unfit() pipeline.fit(train) test_predicted_re_shuffled = pipeline.predict(input_data=test) # predict results should be invariant assert np.equal(test_predicted.predict, test_predicted_re_shuffled.predict).all()
def test_multi_modal_pipeline(): task = Task(TaskTypesEnum.classification) images_size = (128, 128) files_path = os.path.join('test', 'data', 'multi_modal') path = os.path.join(str(fedot_project_root()), files_path) train_num, _, train_img, _, train_text, _ = \ prepare_multi_modal_data(path, task, images_size, with_split=False) # image image_node = PrimaryNode('cnn') image_node.custom_params = {'image_shape': (images_size[0], images_size[1], 1), 'architecture': 'simplified', 'num_classes': 2, 'epochs': 1, 'batch_size': 128} # image ds_image = PrimaryNode('data_source_img') image_node = SecondaryNode('cnn', nodes_from=[ds_image]) image_node.custom_params = {'image_shape': (images_size[0], images_size[1], 1), 'architecture': 'simplified', 'num_classes': 2, 'epochs': 15, 'batch_size': 128} # table ds_table = PrimaryNode('data_source_table') scaling_node = SecondaryNode('scaling', nodes_from=[ds_table]) numeric_node = SecondaryNode('rf', nodes_from=[scaling_node]) # text ds_text = PrimaryNode('data_source_text') node_text_clean = SecondaryNode('text_clean', nodes_from=[ds_text]) text_node = SecondaryNode('tfidf', nodes_from=[node_text_clean]) pipeline = Pipeline(SecondaryNode('logit', nodes_from=[numeric_node, image_node, text_node])) fit_data = MultiModalData({ 'data_source_img': train_img, 'data_source_table': train_num, 'data_source_text': train_text }) pipeline.fit(fit_data) prediction = pipeline.predict(fit_data) assert prediction is not None
def composer_metric(self, metrics, train_data: Union[InputData, MultiModalData], test_data: Union[InputData, MultiModalData], pipeline: Pipeline) -> Optional[Tuple[Any]]: try: validate(pipeline) pipeline.log = self.log if type(metrics) is not list: metrics = [metrics] if self.cache is not None: # TODO improve cache pipeline.fit_from_cache(self.cache) if not pipeline.is_fitted: self.log.debug( f'Pipeline {pipeline.root_node.descriptive_id} fit started' ) pipeline.fit(input_data=train_data, time_constraint=self.composer_requirements. max_pipeline_fit_time) try: self.cache.save_pipeline(pipeline) except Exception as ex: self.log.info(f'Cache can not be saved: {ex}. Continue.') evaluated_metrics = () for metric in metrics: if callable(metric): metric_func = metric else: metric_func = MetricsRepository().metric_by_id(metric) evaluated_metrics = evaluated_metrics + (metric_func( pipeline, reference_data=test_data), ) self.log.debug( f'Pipeline {pipeline.root_node.descriptive_id} with metrics: {list(evaluated_metrics)}' ) # enforce memory cleaning pipeline.unfit() gc.collect() except Exception as ex: self.log.info(f'Pipeline assessment warning: {ex}. Continue.') evaluated_metrics = None return evaluated_metrics
def test_svc_fit_correct(data_fixture, request): data = request.getfixturevalue(data_fixture) train_data, test_data = train_test_data_setup(data=data) # Scaling pipeline. Fit predict it scaling_pipeline = Pipeline(PrimaryNode('normalization')) scaling_pipeline.fit(train_data) scaled_data = scaling_pipeline.predict(train_data) svc = Model(operation_type='svc') _, train_predicted = svc.fit(data=scaled_data) roc_on_train = get_roc_auc(valid_data=train_data, predicted_data=train_predicted) roc_threshold = 0.95 assert roc_on_train >= roc_threshold
def test_pipeline_hierarchy_fit_correct(data_setup): data = data_setup train, _ = train_test_data_setup(data) first = PrimaryNode(operation_type='logit') second = SecondaryNode(operation_type='logit', nodes_from=[first]) third = SecondaryNode(operation_type='logit', nodes_from=[first]) final = SecondaryNode(operation_type='logit', nodes_from=[second, third]) pipeline = Pipeline() for node in [first, second, third, final]: pipeline.add_node(node) pipeline.unfit() train_predicted = pipeline.fit(input_data=train) assert pipeline.root_node.descriptive_id == ( '((/n_logit_default_params;)/' 'n_logit_default_params;;(/' 'n_logit_default_params;)/' 'n_logit_default_params;)/' 'n_logit_default_params') assert pipeline.length == 4 assert pipeline.depth == 3 assert train_predicted.predict.shape[0] == train.target.shape[0] assert final.fitted_operation is not None
def test_pca_model_removes_redunant_features_correct(): n_informative = 5 data = classification_dataset_with_redunant_features( n_samples=1000, n_features=100, n_informative=n_informative) train_data, test_data = train_test_data_setup(data=data) # Scaling pipeline. Fit predict it scaling_pipeline = Pipeline(PrimaryNode('normalization')) scaling_pipeline.fit(train_data) scaled_data = scaling_pipeline.predict(train_data) pca = DataOperation(operation_type='pca') _, train_predicted = pca.fit(data=scaled_data) transformed_features = train_predicted.predict assert transformed_features.shape[1] < data.features.shape[1]
def test_forecast_with_sparse_lagged(): train_source_ts, predict_source_ts, train_exog_ts, predict_exog_ts, ts_test = synthetic_with_exogenous_ts( ) # Source data for lagged node node_lagged = PrimaryNode('sparse_lagged') # Set window size for lagged transformation node_lagged.custom_params = {'window_size': window_size} node_final = SecondaryNode('linear', nodes_from=[node_lagged]) pipeline = Pipeline(node_final) pipeline.fit(input_data=MultiModalData({'sparse_lagged': train_source_ts})) forecast = pipeline.predict( input_data=MultiModalData({'sparse_lagged': predict_source_ts})) is_forecasted = True assert is_forecasted
def test_pipeline_with_datamodel_fit_correct(data_setup): data = data_setup train_data, test_data = train_test_data_setup(data) pipeline = Pipeline() node_data = PrimaryNode('logit') node_first = PrimaryNode('bernb') node_second = SecondaryNode('rf') node_second.nodes_from = [node_first, node_data] pipeline.add_node(node_data) pipeline.add_node(node_first) pipeline.add_node(node_second) pipeline.fit(train_data) results = np.asarray(probs_to_labels(pipeline.predict(test_data).predict)) assert results.shape == test_data.target.shape
def test_clean_text_preprocessing(): test_text = [ 'This is the first document.', 'This document is the second document.', 'And this is the third one.', 'Is this the first document?', ] input_data = InputData(features=test_text, target=[0, 1, 1, 0], idx=np.arange(0, len(test_text)), task=Task(TaskTypesEnum.classification), data_type=DataTypesEnum.text) preprocessing_pipeline = Pipeline(PrimaryNode('text_clean')) preprocessing_pipeline.fit(input_data) predicted_output = preprocessing_pipeline.predict(input_data) cleaned_text = predicted_output.predict assert len(test_text) == len(cleaned_text)
def test_regression_pipeline_with_data_operation_fit_correct(): data = get_synthetic_regression_data() train_data, test_data = train_test_data_setup(data) # linear # / \ # ridge | # | | # ransac_lin_reg lasso # \ / # scaling node_scaling = PrimaryNode('scaling') node_ransac = SecondaryNode('ransac_lin_reg', nodes_from=[node_scaling]) node_lasso = SecondaryNode('lasso', nodes_from=[node_scaling]) node_ridge = SecondaryNode('ridge', nodes_from=[node_ransac]) node_root = SecondaryNode('linear', nodes_from=[node_lasso, node_ridge]) pipeline = Pipeline(node_root) pipeline.fit(train_data) results = pipeline.predict(test_data) assert results.predict.shape == test_data.target.shape
def test_pipeline_with_custom_params_for_model(data_setup): data = data_setup custom_params = dict(n_neighbors=1, weights='uniform', p=1) first = PrimaryNode(operation_type='logit') second = PrimaryNode(operation_type='lda') final = SecondaryNode(operation_type='knn', nodes_from=[first, second]) pipeline = Pipeline() pipeline.add_node(final) pipeline_default_params = deepcopy(pipeline) pipeline.root_node.custom_params = custom_params pipeline_default_params.fit(data) pipeline.fit(data) custom_params_prediction = pipeline.predict(data).predict default_params_prediction = pipeline_default_params.predict(data).predict assert not np.array_equal(custom_params_prediction, default_params_prediction)