Loading deepchem/models/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -7,6 +7,7 @@ from __future__ import unicode_literals from deepchem.models.models import Model from deepchem.models.sklearn_models import SklearnModel from deepchem.models.xgboost_models import XGBoostModel from deepchem.models.tf_new_models.multitask_classifier import MultitaskGraphClassifier from deepchem.models.tf_new_models.multitask_regressor import MultitaskGraphRegressor from deepchem.models.tf_new_models.support_classifier import SupportGraphClassifier Loading deepchem/models/xgboost_models/__init__.py 0 → 100644 +114 −0 Original line number Diff line number Diff line """ Scikit-learn wrapper interface of xgboost """ import xgboost as xgb import numpy as np from deepchem.models import Model from deepchem.models.sklearn_models import SklearnModel from deepchem.utils.save import load_from_disk from deepchem.utils.save import save_to_disk from sklearn.cross_validation import train_test_split from sklearn.grid_search import GridSearchCV class XGBoostModel(SklearnModel): """ Abstract base class for XGBoost model. """ def __init__(self, model_instance=None, model_dir=None, verbose=True, **kwargs): """Abstract class for XGBoost models. Parameters: ----------- model_instance: object Scikit-learn wrapper interface of xgboost model_dir: str Path to directory where model will be stored. """ if model_dir is not None: if not os.path.exists(model_dir): os.makedirs(model_dir) else: model_dir = tempfile.mkdtemp() self.model_dir = model_dir self.model_instance = model_instance self.model_class = model_instance.__class__ self.verbose = verbose if 'early_stopping_rounds' in kwargs: self.early_stopping_rounds = kwargs['early_stopping_rounds'] else: self.early_stopping_rounds = 50 def fit(self, dataset, **kwargs): """ Fits XGBoost model to data. """ X = dataset.X y = np.squeeze(dataset.y) w = np.squeeze(dataset.w) seed = self.model_instance.seed if isinstance(self.model_instance,xgb.XGBClassifier): xgb_metric = "auc" sklearn_metric = "roc_auc" elif isinstance(self.model_instance,xgb.XGBRegressor): xgb_metric = "mae" sklearn_metric = "neg_mean_absolute_error" best_param = self._search_param(sklearn_metric) # update model with best param self.model_instance = self.model_class(**best_param) # Find optimal n_estimators based on original learning_rate # and early_stopping_rounds X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=seed, stratify=y) self.model_instance.fit(X_train, y_train, early_stopping_rounds=self.early_stopping_rounds, eval_metric=xgb_metric,eval_set=[(X_test, y_test)], verbose=self.verbose) # Since test size is 20%, when retrain model to whole data, expect # n_estimator increased to 1/0.8 = 1.25 time. estimated_best_round = np.round(self.model_instance.best_ntree_limit * 1.25) self.model_instance.n_estimators = np.int64(estimated_best_round) self.model_instance.fit(X_train, y_train, eval_metric=xgb_metric, verbose=self.verbose) def _search_param(self,metric): ''' Find best potential parameters set using few n_estimators ''' # Make sure user specified params are in the grid. max_depth_grid = list(np.unique([self.model_instance.max_depth,5,7])) colsample_bytree_grid = list(np.unique( [self.model_instance.colsample_tree,0.66,0.9])) reg_lambda_grid = list(np.unique( [self.model_instance.reg_lambda,1,5])) param_grid = { 'max_depth': max_depth_grid, 'learning_rate': [max(self.model_instance.learning_rate,0.3)], 'n_estimators': [min(self.model_instance.n_estimators,60)], 'gamma': [self.model_instance.gamma], 'min_child_weight': [self.model_instance.min_child_weight], 'max_delta_step': [self.model_instance.max_delta_step], 'subsample': [self.model_instance.subsample], 'colsample_bytree': colsample_bytree_grid, 'colsample_bylevel': [self.model_instance.colsample_bylevel], 'reg_alpha': [self.model_instance.reg_alpha], 'reg_lambda': reg_lambda_grid, 'scale_pos_weight': [self.model_instance.scale_pos_weight], 'base_score': [self.model_instance.base_score], 'seed': [self.model_instance.seed] } grid_search = GridSearchCV(self.model_instance, param_grid, cv=2, refit=False, scoring=metric) grid_search.fit(X,y) best_params = grid_search.best_params_ # Change params back original params best_params['learning_rate'] = self.model_instance.learning_rate best_params['n_estimators'] = self.model_instance.n_estimators return best_params examples/benchmark.py +158 −6 Original line number Diff line number Diff line Loading @@ -56,7 +56,7 @@ from qm9.qm9_datasets import load_qm9 from sampl.sampl_datasets import load_sampl from clintox.clintox_datasets import load_clintox from hiv.hiv_datasets import load_hiv import xgboost def benchmark_loading_datasets(hyper_parameters, dataset='tox21', Loading Loading @@ -313,7 +313,8 @@ def benchmark_classification(train_dataset, if metric == 'auc': classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean) assert model in ['rf', 'tf', 'tf_robust', 'logreg', 'irv', 'graphconv'] assert model in ['rf', 'tf', 'tf_robust', 'logreg', 'irv', 'graphconv', 'xgb_classifier'] if model == 'tf': # Loading hyper parameters Loading Loading @@ -564,6 +565,62 @@ def benchmark_classification(train_dataset, test_scores['rf'] = model_rf.evaluate( test_dataset, [classification_metric], transformers) if model == 'xgb_classifier': # Loading hyper parameters max_depth = hyper_parameters['max_depth'] learning_rate = hyper_parameters['learning_rate'] n_estimators = hyper_parameters['n_estimators'] gamma = hyper_parameters['gamma'] min_child_weight = hyper_parameters['min_child_weight'] max_delta_step = hyper_parameters['max_delta_step'] subsample = hyper_parameters['subsample'] colsample_bytree = hyper_parameters['colsample_bytree'] colsample_bylevel = hyper_parameters['colsample_bylevel'] reg_alpha = hyper_parameters['reg_alpha'] reg_lambda = hyper_parameters['reg_lambda'] scale_pos_weight = hyper_parameters['scale_pos_weight'] base_score = hyper_parameters['base_score'] seed = hyper_parameters['seed'] early_stopping_rounds = hyper_parameters['early_stopping_rounds'] esr = {'early_stopping_rounds' : early_stopping_rounds} # Building xgboost classification model def model_builder(model_dir_xgb): xgboost_model = xgboost.XGBClassifier( max_depth=max_depth, learning_rate=learning_rate, n_estimators=n_estimators, gamma=gamma, min_child_weight=min_child_weight, max_delta_step=max_delta_step, subsample=subsample, colsample_bytree=colsample_bytree, colsample_bylevel=colsample_bylevel, reg_alpha=reg_alpha, reg_lambda=reg_lambda, scale_pos_weight=scale_pos_weight, base_score=base_score, seed=seed) return dc.models.xgboost_models.XGBoostModel(xgboost_model, model_dir_xgb, **esr) model_xgb = dc.models.multitask.SingletaskToMultitask(tasks, model_builder) print('-------------------------------------') print('Start fitting by xgoost') model_xgb.fit(train_dataset) # Evaluating xgboost classification model train_scores['xgb_classifier'] = model_xgb.evaluate( train_dataset, [classification_metric], transformers) valid_scores['xgb_classifier'] = model_xgb.evaluate( valid_dataset, [classification_metric], transformers) if test: test_scores['xgb_classifier'] = model_xgb.evaluate( test_dataset, [classification_metric], transformers) return train_scores, valid_scores, test_scores Loading Loading @@ -623,7 +680,8 @@ def benchmark_regression(train_dataset, regression_metric = dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean) assert model in ['tf_regression', 'rf_regression', 'graphconvreg'] assert model in ['tf_regression', 'rf_regression', 'graphconvreg', 'xgb_regression'] if model == 'tf_regression': # Loading hyper parameters Loading Loading @@ -766,6 +824,62 @@ def benchmark_regression(train_dataset, test_scores['rf_regression'] = model_rf_regression.evaluate( test_dataset, [regression_metric], transformers) if model == 'xgb_regression': # Loading hyper parameters max_depth = hyper_parameters['max_depth'] learning_rate = hyper_parameters['learning_rate'] n_estimators = hyper_parameters['n_estimators'] gamma = hyper_parameters['gamma'] min_child_weight = hyper_parameters['min_child_weight'] max_delta_step = hyper_parameters['max_delta_step'] subsample = hyper_parameters['subsample'] colsample_bytree = hyper_parameters['colsample_bytree'] colsample_bylevel = hyper_parameters['colsample_bylevel'] reg_alpha = hyper_parameters['reg_alpha'] reg_lambda = hyper_parameters['reg_lambda'] scale_pos_weight = hyper_parameters['scale_pos_weight'] base_score = hyper_parameters['base_score'] seed = hyper_parameters['seed'] early_stopping_rounds = hyper_parameters['early_stopping_rounds'] esr = {'early_stopping_rounds' : early_stopping_rounds} # Building xgboost classification model def model_builder(model_dir_xgb): xgboost_model = xgboost.XGBRegressor( max_depth=max_depth, learning_rate=learning_rate, n_estimators=n_estimators, gamma=gamma, min_child_weight=min_child_weight, max_delta_step=max_delta_step, subsample=subsample, colsample_bytree=colsample_bytree, colsample_bylevel=colsample_bylevel, reg_alpha=reg_alpha, reg_lambda=reg_lambda, scale_pos_weight=scale_pos_weight, base_score=base_score, seed=seed) return dc.models.xgboost_models.XGBoostModel(xgboost_model, model_dir_xgb, **esr) model_xgb = dc.models.multitask.SingletaskToMultitask(tasks, model_builder) print('-------------------------------------') print('Start fitting by xgoost') model_xgb.fit(train_dataset) # Evaluating xgboost classification model train_scores['xgb_regression'] = model_xgb.evaluate( train_dataset, [regression_metric], transformers) valid_scores['xgb_regression'] = model_xgb.evaluate( valid_dataset, [regression_metric], transformers) if test: test_scores['xgb_regression'] = model_xgb.evaluate( test_dataset, [regression_metric], transformers) return train_scores, valid_scores, test_scores Loading @@ -788,7 +902,7 @@ if __name__ == '__main__': dest='model_args', default=[], help='Choice of model: tf, tf_robust, logreg, rf, irv, graphconv, ' + 'tf_regression, rf_regression, graphconvreg') 'tf_regression, rf_regression, graphconvreg, xgb_classifier, xgb_regression') parser.add_argument( '-d', action='append', Loading Loading @@ -906,13 +1020,50 @@ if __name__ == '__main__': 'seed': 123 }] hps['xgb_classifier'] = [{ 'max_depth': 5, 'learning_rate': 0.05, 'n_estimators': 3000, 'gamma': 0, 'min_child_weight': 5, 'max_delta_step': 1, 'subsample': 0.53, 'colsample_bytree': 0.66, 'colsample_bylevel': 1, 'reg_alpha': 0, 'reg_lambda': 1, 'scale_pos_weight': 1, 'base_score': 0.5, 'seed': 2016, 'early_stopping_rounds': 100 }] hps['xgb_regression'] = [{ 'max_depth': 5, 'learning_rate': 0.05, 'n_estimators': 3000, 'gamma': 0, 'min_child_weight': 5, 'max_delta_step': 1, 'subsample': 0.53, 'colsample_bytree': 0.66, 'colsample_bylevel': 1, 'reg_alpha': 0, 'reg_lambda': 1, 'scale_pos_weight': 1, 'base_score': 0.5, 'seed': 2016, 'early_stopping_rounds': 100 }] for split in splitters: for dataset in datasets: if dataset in [ 'tox21', 'sider', 'muv', 'toxcast', 'pcba', 'clintox', 'hiv' ]: for model in models: if model in ['tf', 'tf_robust', 'logreg', 'graphconv', 'rf', 'irv']: if model in ['tf', 'tf_robust', 'logreg', 'graphconv', 'rf', 'irv', 'xgb_classifier']: benchmark_loading_datasets( hps, dataset=dataset, Loading @@ -922,7 +1073,8 @@ if __name__ == '__main__': test=test) else: for model in models: if model in ['tf_regression', 'rf_regression', 'graphconvreg']: if model in ['tf_regression', 'rf_regression', 'graphconvreg', 'xgb_regression']: benchmark_loading_datasets( hps, dataset=dataset, Loading Loading
deepchem/models/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -7,6 +7,7 @@ from __future__ import unicode_literals from deepchem.models.models import Model from deepchem.models.sklearn_models import SklearnModel from deepchem.models.xgboost_models import XGBoostModel from deepchem.models.tf_new_models.multitask_classifier import MultitaskGraphClassifier from deepchem.models.tf_new_models.multitask_regressor import MultitaskGraphRegressor from deepchem.models.tf_new_models.support_classifier import SupportGraphClassifier Loading
deepchem/models/xgboost_models/__init__.py 0 → 100644 +114 −0 Original line number Diff line number Diff line """ Scikit-learn wrapper interface of xgboost """ import xgboost as xgb import numpy as np from deepchem.models import Model from deepchem.models.sklearn_models import SklearnModel from deepchem.utils.save import load_from_disk from deepchem.utils.save import save_to_disk from sklearn.cross_validation import train_test_split from sklearn.grid_search import GridSearchCV class XGBoostModel(SklearnModel): """ Abstract base class for XGBoost model. """ def __init__(self, model_instance=None, model_dir=None, verbose=True, **kwargs): """Abstract class for XGBoost models. Parameters: ----------- model_instance: object Scikit-learn wrapper interface of xgboost model_dir: str Path to directory where model will be stored. """ if model_dir is not None: if not os.path.exists(model_dir): os.makedirs(model_dir) else: model_dir = tempfile.mkdtemp() self.model_dir = model_dir self.model_instance = model_instance self.model_class = model_instance.__class__ self.verbose = verbose if 'early_stopping_rounds' in kwargs: self.early_stopping_rounds = kwargs['early_stopping_rounds'] else: self.early_stopping_rounds = 50 def fit(self, dataset, **kwargs): """ Fits XGBoost model to data. """ X = dataset.X y = np.squeeze(dataset.y) w = np.squeeze(dataset.w) seed = self.model_instance.seed if isinstance(self.model_instance,xgb.XGBClassifier): xgb_metric = "auc" sklearn_metric = "roc_auc" elif isinstance(self.model_instance,xgb.XGBRegressor): xgb_metric = "mae" sklearn_metric = "neg_mean_absolute_error" best_param = self._search_param(sklearn_metric) # update model with best param self.model_instance = self.model_class(**best_param) # Find optimal n_estimators based on original learning_rate # and early_stopping_rounds X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=seed, stratify=y) self.model_instance.fit(X_train, y_train, early_stopping_rounds=self.early_stopping_rounds, eval_metric=xgb_metric,eval_set=[(X_test, y_test)], verbose=self.verbose) # Since test size is 20%, when retrain model to whole data, expect # n_estimator increased to 1/0.8 = 1.25 time. estimated_best_round = np.round(self.model_instance.best_ntree_limit * 1.25) self.model_instance.n_estimators = np.int64(estimated_best_round) self.model_instance.fit(X_train, y_train, eval_metric=xgb_metric, verbose=self.verbose) def _search_param(self,metric): ''' Find best potential parameters set using few n_estimators ''' # Make sure user specified params are in the grid. max_depth_grid = list(np.unique([self.model_instance.max_depth,5,7])) colsample_bytree_grid = list(np.unique( [self.model_instance.colsample_tree,0.66,0.9])) reg_lambda_grid = list(np.unique( [self.model_instance.reg_lambda,1,5])) param_grid = { 'max_depth': max_depth_grid, 'learning_rate': [max(self.model_instance.learning_rate,0.3)], 'n_estimators': [min(self.model_instance.n_estimators,60)], 'gamma': [self.model_instance.gamma], 'min_child_weight': [self.model_instance.min_child_weight], 'max_delta_step': [self.model_instance.max_delta_step], 'subsample': [self.model_instance.subsample], 'colsample_bytree': colsample_bytree_grid, 'colsample_bylevel': [self.model_instance.colsample_bylevel], 'reg_alpha': [self.model_instance.reg_alpha], 'reg_lambda': reg_lambda_grid, 'scale_pos_weight': [self.model_instance.scale_pos_weight], 'base_score': [self.model_instance.base_score], 'seed': [self.model_instance.seed] } grid_search = GridSearchCV(self.model_instance, param_grid, cv=2, refit=False, scoring=metric) grid_search.fit(X,y) best_params = grid_search.best_params_ # Change params back original params best_params['learning_rate'] = self.model_instance.learning_rate best_params['n_estimators'] = self.model_instance.n_estimators return best_params
examples/benchmark.py +158 −6 Original line number Diff line number Diff line Loading @@ -56,7 +56,7 @@ from qm9.qm9_datasets import load_qm9 from sampl.sampl_datasets import load_sampl from clintox.clintox_datasets import load_clintox from hiv.hiv_datasets import load_hiv import xgboost def benchmark_loading_datasets(hyper_parameters, dataset='tox21', Loading Loading @@ -313,7 +313,8 @@ def benchmark_classification(train_dataset, if metric == 'auc': classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean) assert model in ['rf', 'tf', 'tf_robust', 'logreg', 'irv', 'graphconv'] assert model in ['rf', 'tf', 'tf_robust', 'logreg', 'irv', 'graphconv', 'xgb_classifier'] if model == 'tf': # Loading hyper parameters Loading Loading @@ -564,6 +565,62 @@ def benchmark_classification(train_dataset, test_scores['rf'] = model_rf.evaluate( test_dataset, [classification_metric], transformers) if model == 'xgb_classifier': # Loading hyper parameters max_depth = hyper_parameters['max_depth'] learning_rate = hyper_parameters['learning_rate'] n_estimators = hyper_parameters['n_estimators'] gamma = hyper_parameters['gamma'] min_child_weight = hyper_parameters['min_child_weight'] max_delta_step = hyper_parameters['max_delta_step'] subsample = hyper_parameters['subsample'] colsample_bytree = hyper_parameters['colsample_bytree'] colsample_bylevel = hyper_parameters['colsample_bylevel'] reg_alpha = hyper_parameters['reg_alpha'] reg_lambda = hyper_parameters['reg_lambda'] scale_pos_weight = hyper_parameters['scale_pos_weight'] base_score = hyper_parameters['base_score'] seed = hyper_parameters['seed'] early_stopping_rounds = hyper_parameters['early_stopping_rounds'] esr = {'early_stopping_rounds' : early_stopping_rounds} # Building xgboost classification model def model_builder(model_dir_xgb): xgboost_model = xgboost.XGBClassifier( max_depth=max_depth, learning_rate=learning_rate, n_estimators=n_estimators, gamma=gamma, min_child_weight=min_child_weight, max_delta_step=max_delta_step, subsample=subsample, colsample_bytree=colsample_bytree, colsample_bylevel=colsample_bylevel, reg_alpha=reg_alpha, reg_lambda=reg_lambda, scale_pos_weight=scale_pos_weight, base_score=base_score, seed=seed) return dc.models.xgboost_models.XGBoostModel(xgboost_model, model_dir_xgb, **esr) model_xgb = dc.models.multitask.SingletaskToMultitask(tasks, model_builder) print('-------------------------------------') print('Start fitting by xgoost') model_xgb.fit(train_dataset) # Evaluating xgboost classification model train_scores['xgb_classifier'] = model_xgb.evaluate( train_dataset, [classification_metric], transformers) valid_scores['xgb_classifier'] = model_xgb.evaluate( valid_dataset, [classification_metric], transformers) if test: test_scores['xgb_classifier'] = model_xgb.evaluate( test_dataset, [classification_metric], transformers) return train_scores, valid_scores, test_scores Loading Loading @@ -623,7 +680,8 @@ def benchmark_regression(train_dataset, regression_metric = dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean) assert model in ['tf_regression', 'rf_regression', 'graphconvreg'] assert model in ['tf_regression', 'rf_regression', 'graphconvreg', 'xgb_regression'] if model == 'tf_regression': # Loading hyper parameters Loading Loading @@ -766,6 +824,62 @@ def benchmark_regression(train_dataset, test_scores['rf_regression'] = model_rf_regression.evaluate( test_dataset, [regression_metric], transformers) if model == 'xgb_regression': # Loading hyper parameters max_depth = hyper_parameters['max_depth'] learning_rate = hyper_parameters['learning_rate'] n_estimators = hyper_parameters['n_estimators'] gamma = hyper_parameters['gamma'] min_child_weight = hyper_parameters['min_child_weight'] max_delta_step = hyper_parameters['max_delta_step'] subsample = hyper_parameters['subsample'] colsample_bytree = hyper_parameters['colsample_bytree'] colsample_bylevel = hyper_parameters['colsample_bylevel'] reg_alpha = hyper_parameters['reg_alpha'] reg_lambda = hyper_parameters['reg_lambda'] scale_pos_weight = hyper_parameters['scale_pos_weight'] base_score = hyper_parameters['base_score'] seed = hyper_parameters['seed'] early_stopping_rounds = hyper_parameters['early_stopping_rounds'] esr = {'early_stopping_rounds' : early_stopping_rounds} # Building xgboost classification model def model_builder(model_dir_xgb): xgboost_model = xgboost.XGBRegressor( max_depth=max_depth, learning_rate=learning_rate, n_estimators=n_estimators, gamma=gamma, min_child_weight=min_child_weight, max_delta_step=max_delta_step, subsample=subsample, colsample_bytree=colsample_bytree, colsample_bylevel=colsample_bylevel, reg_alpha=reg_alpha, reg_lambda=reg_lambda, scale_pos_weight=scale_pos_weight, base_score=base_score, seed=seed) return dc.models.xgboost_models.XGBoostModel(xgboost_model, model_dir_xgb, **esr) model_xgb = dc.models.multitask.SingletaskToMultitask(tasks, model_builder) print('-------------------------------------') print('Start fitting by xgoost') model_xgb.fit(train_dataset) # Evaluating xgboost classification model train_scores['xgb_regression'] = model_xgb.evaluate( train_dataset, [regression_metric], transformers) valid_scores['xgb_regression'] = model_xgb.evaluate( valid_dataset, [regression_metric], transformers) if test: test_scores['xgb_regression'] = model_xgb.evaluate( test_dataset, [regression_metric], transformers) return train_scores, valid_scores, test_scores Loading @@ -788,7 +902,7 @@ if __name__ == '__main__': dest='model_args', default=[], help='Choice of model: tf, tf_robust, logreg, rf, irv, graphconv, ' + 'tf_regression, rf_regression, graphconvreg') 'tf_regression, rf_regression, graphconvreg, xgb_classifier, xgb_regression') parser.add_argument( '-d', action='append', Loading Loading @@ -906,13 +1020,50 @@ if __name__ == '__main__': 'seed': 123 }] hps['xgb_classifier'] = [{ 'max_depth': 5, 'learning_rate': 0.05, 'n_estimators': 3000, 'gamma': 0, 'min_child_weight': 5, 'max_delta_step': 1, 'subsample': 0.53, 'colsample_bytree': 0.66, 'colsample_bylevel': 1, 'reg_alpha': 0, 'reg_lambda': 1, 'scale_pos_weight': 1, 'base_score': 0.5, 'seed': 2016, 'early_stopping_rounds': 100 }] hps['xgb_regression'] = [{ 'max_depth': 5, 'learning_rate': 0.05, 'n_estimators': 3000, 'gamma': 0, 'min_child_weight': 5, 'max_delta_step': 1, 'subsample': 0.53, 'colsample_bytree': 0.66, 'colsample_bylevel': 1, 'reg_alpha': 0, 'reg_lambda': 1, 'scale_pos_weight': 1, 'base_score': 0.5, 'seed': 2016, 'early_stopping_rounds': 100 }] for split in splitters: for dataset in datasets: if dataset in [ 'tox21', 'sider', 'muv', 'toxcast', 'pcba', 'clintox', 'hiv' ]: for model in models: if model in ['tf', 'tf_robust', 'logreg', 'graphconv', 'rf', 'irv']: if model in ['tf', 'tf_robust', 'logreg', 'graphconv', 'rf', 'irv', 'xgb_classifier']: benchmark_loading_datasets( hps, dataset=dataset, Loading @@ -922,7 +1073,8 @@ if __name__ == '__main__': test=test) else: for model in models: if model in ['tf_regression', 'rf_regression', 'graphconvreg']: if model in ['tf_regression', 'rf_regression', 'graphconvreg', 'xgb_regression']: benchmark_loading_datasets( hps, dataset=dataset, Loading
