Loading deepchem/molnet/load_function/sweetlead_datasets.py +8 −6 Original line number Diff line number Diff line Loading @@ -13,13 +13,15 @@ import deepchem as dc logger = logging.getLogger(__name__) def load_sweet(featurizer='ECFP', split='index', reload=True, frac_train=.8): """Load sweet datasets.""" # Load Sweetlead dataset logger.info("About to load Sweetlead dataset.") data_dir = dc.utils.get_data_dir() if reload: save_dir = os.path.join(data_dir, "sweetlead/" + featurizer + "/" + str(split)) save_dir = os.path.join(data_dir, "sweetlead/" + featurizer + "/" + str(split)) dataset_file = os.path.join(data_dir, "sweet.csv.gz") if not os.path.exists(dataset_file): Loading @@ -39,10 +41,10 @@ def load_sweet(featurizer='ECFP', split='index', reload=True, frac_train=.8): tasks=SWEET_tasks, smiles_field="smiles", featurizer=featurizer) dataset = loader.featurize(dataset_file) # Initialize transformers transformers = [ dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)] dc.trans.BalancingTransformer(transform_w=True, dataset=dataset) ] print("About to transform data") for transformer in transformers: dataset = transformer.transform(dataset) Loading examples/sweetlead/sweet.py +12 −9 Original line number Diff line number Diff line Loading @@ -19,17 +19,19 @@ from deepchem import metrics from deepchem.metrics import Metric from deepchem.models.sklearn_models import SklearnModel tox_tasks, (tox_train, tox_valid, tox_test), tox_transformers = dc.molnet.load_tox21() tox_tasks, (tox_train, tox_valid, tox_test), tox_transformers = dc.molnet.load_tox21() classification_metric = Metric( metrics.roc_auc_score, np.mean, mode="classification") classification_metric = Metric(metrics.roc_auc_score, np.mean, mode="classification") def model_builder(model_dir): sklearn_model = RandomForestClassifier( class_weight="balanced", n_estimators=500, n_jobs=-1) class_weight="balanced", n_estimators=500, n_jobs=-1) return dc.models.SklearnModel(sklearn_model, model_dir) print(tox_train.get_task_names()) print(tox_tasks) tox_model = SingletaskToMultitask(tox_tasks, model_builder) Loading @@ -37,7 +39,9 @@ tox_model.fit(tox_train) # Load sider models now sider_tasks, (sider_train, sider_valid, sider_test), sider_transformers = dc.molnet.load_sider(split="random") sider_tasks, ( sider_train, sider_valid, sider_test), sider_transformers = dc.molnet.load_sider(split="random") sider_model = SingletaskToMultitask(sider_tasks, model_builder) sider_model.fit(sider_train) Loading Loading @@ -65,4 +69,3 @@ for i in range(tox_predictions.shape[0]): df = pd.DataFrame(confusion_matrix) df.to_csv("./tox_sider_matrix.csv") Loading
deepchem/molnet/load_function/sweetlead_datasets.py +8 −6 Original line number Diff line number Diff line Loading @@ -13,13 +13,15 @@ import deepchem as dc logger = logging.getLogger(__name__) def load_sweet(featurizer='ECFP', split='index', reload=True, frac_train=.8): """Load sweet datasets.""" # Load Sweetlead dataset logger.info("About to load Sweetlead dataset.") data_dir = dc.utils.get_data_dir() if reload: save_dir = os.path.join(data_dir, "sweetlead/" + featurizer + "/" + str(split)) save_dir = os.path.join(data_dir, "sweetlead/" + featurizer + "/" + str(split)) dataset_file = os.path.join(data_dir, "sweet.csv.gz") if not os.path.exists(dataset_file): Loading @@ -39,10 +41,10 @@ def load_sweet(featurizer='ECFP', split='index', reload=True, frac_train=.8): tasks=SWEET_tasks, smiles_field="smiles", featurizer=featurizer) dataset = loader.featurize(dataset_file) # Initialize transformers transformers = [ dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)] dc.trans.BalancingTransformer(transform_w=True, dataset=dataset) ] print("About to transform data") for transformer in transformers: dataset = transformer.transform(dataset) Loading
examples/sweetlead/sweet.py +12 −9 Original line number Diff line number Diff line Loading @@ -19,17 +19,19 @@ from deepchem import metrics from deepchem.metrics import Metric from deepchem.models.sklearn_models import SklearnModel tox_tasks, (tox_train, tox_valid, tox_test), tox_transformers = dc.molnet.load_tox21() tox_tasks, (tox_train, tox_valid, tox_test), tox_transformers = dc.molnet.load_tox21() classification_metric = Metric( metrics.roc_auc_score, np.mean, mode="classification") classification_metric = Metric(metrics.roc_auc_score, np.mean, mode="classification") def model_builder(model_dir): sklearn_model = RandomForestClassifier( class_weight="balanced", n_estimators=500, n_jobs=-1) class_weight="balanced", n_estimators=500, n_jobs=-1) return dc.models.SklearnModel(sklearn_model, model_dir) print(tox_train.get_task_names()) print(tox_tasks) tox_model = SingletaskToMultitask(tox_tasks, model_builder) Loading @@ -37,7 +39,9 @@ tox_model.fit(tox_train) # Load sider models now sider_tasks, (sider_train, sider_valid, sider_test), sider_transformers = dc.molnet.load_sider(split="random") sider_tasks, ( sider_train, sider_valid, sider_test), sider_transformers = dc.molnet.load_sider(split="random") sider_model = SingletaskToMultitask(sider_tasks, model_builder) sider_model.fit(sider_train) Loading Loading @@ -65,4 +69,3 @@ for i in range(tox_predictions.shape[0]): df = pd.DataFrame(confusion_matrix) df.to_csv("./tox_sider_matrix.csv")
