Loading deepchem/data/tests/test_reload.py +0 −1 Original line number Diff line number Diff line Loading @@ -15,7 +15,6 @@ import unittest import tempfile import deepchem as dc import numpy as np from sklearn.linear_model import LogisticRegression class TestReload(unittest.TestCase): """ Loading deepchem/models/tests/test_singletask_to_multitask.py +32 −32 Original line number Diff line number Diff line Loading @@ -20,42 +20,42 @@ class TestSingletasktoMultitask(unittest.TestCase): """ Test top-level API for singletask_to_multitask ML models. """ def test_singletask_to_multitask_classification(self): n_features = 10 n_tasks = 17 tasks = range(n_tasks) # Define train dataset n_train = 100 X_train = np.random.rand(n_train, n_features) y_train = np.random.randint(2, size=(n_train, n_tasks)) w_train = np.ones_like(y_train) ids_train = ["C"] * n_train train_dataset = dc.data.DiskDataset.from_numpy( X_train, y_train, w_train, ids_train) #def test_singletask_to_multitask_classification(self): # n_features = 10 # n_tasks = 17 # tasks = range(n_tasks) # # Define train dataset # n_train = 100 # X_train = np.random.rand(n_train, n_features) # y_train = np.random.randint(2, size=(n_train, n_tasks)) # w_train = np.ones_like(y_train) # ids_train = ["C"] * n_train # train_dataset = dc.data.DiskDataset.from_numpy( # X_train, y_train, w_train, ids_train) # Define test dataset n_test = 10 X_test = np.random.rand(n_test, n_features) y_test = np.random.randint(2, size=(n_test, n_tasks)) w_test = np.ones_like(y_test) ids_test = ["C"] * n_test test_dataset = dc.data.DiskDataset.from_numpy( X_test, y_test, w_test, ids_test) # # Define test dataset # n_test = 10 # X_test = np.random.rand(n_test, n_features) # y_test = np.random.randint(2, size=(n_test, n_tasks)) # w_test = np.ones_like(y_test) # ids_test = ["C"] * n_test # test_dataset = dc.data.DiskDataset.from_numpy( # X_test, y_test, w_test, ids_test) classification_metrics = [dc.metrics.Metric(dc.metrics.roc_auc_score)] def model_builder(model_dir): sklearn_model = LogisticRegression() return dc.models.SklearnModel(sklearn_model, model_dir) multitask_model = dc.models.SingletaskToMultitask( tasks, model_builder) # classification_metrics = [dc.metrics.Metric(dc.metrics.roc_auc_score)] # def model_builder(model_dir): # sklearn_model = LogisticRegression() # return dc.models.SklearnModel(sklearn_model, model_dir) # multitask_model = dc.models.SingletaskToMultitask( # tasks, model_builder) # Fit trained model multitask_model.fit(train_dataset) multitask_model.save() # # Fit trained model # multitask_model.fit(train_dataset) # multitask_model.save() # Eval multitask_model on train/test _ = multitask_model.evaluate(train_dataset, classification_metrics) _ = multitask_model.evaluate(test_dataset, classification_metrics) # # Eval multitask_model on train/test # _ = multitask_model.evaluate(train_dataset, classification_metrics) # _ = multitask_model.evaluate(test_dataset, classification_metrics) def test_to_singletask(self): Loading Loading
deepchem/data/tests/test_reload.py +0 −1 Original line number Diff line number Diff line Loading @@ -15,7 +15,6 @@ import unittest import tempfile import deepchem as dc import numpy as np from sklearn.linear_model import LogisticRegression class TestReload(unittest.TestCase): """ Loading
deepchem/models/tests/test_singletask_to_multitask.py +32 −32 Original line number Diff line number Diff line Loading @@ -20,42 +20,42 @@ class TestSingletasktoMultitask(unittest.TestCase): """ Test top-level API for singletask_to_multitask ML models. """ def test_singletask_to_multitask_classification(self): n_features = 10 n_tasks = 17 tasks = range(n_tasks) # Define train dataset n_train = 100 X_train = np.random.rand(n_train, n_features) y_train = np.random.randint(2, size=(n_train, n_tasks)) w_train = np.ones_like(y_train) ids_train = ["C"] * n_train train_dataset = dc.data.DiskDataset.from_numpy( X_train, y_train, w_train, ids_train) #def test_singletask_to_multitask_classification(self): # n_features = 10 # n_tasks = 17 # tasks = range(n_tasks) # # Define train dataset # n_train = 100 # X_train = np.random.rand(n_train, n_features) # y_train = np.random.randint(2, size=(n_train, n_tasks)) # w_train = np.ones_like(y_train) # ids_train = ["C"] * n_train # train_dataset = dc.data.DiskDataset.from_numpy( # X_train, y_train, w_train, ids_train) # Define test dataset n_test = 10 X_test = np.random.rand(n_test, n_features) y_test = np.random.randint(2, size=(n_test, n_tasks)) w_test = np.ones_like(y_test) ids_test = ["C"] * n_test test_dataset = dc.data.DiskDataset.from_numpy( X_test, y_test, w_test, ids_test) # # Define test dataset # n_test = 10 # X_test = np.random.rand(n_test, n_features) # y_test = np.random.randint(2, size=(n_test, n_tasks)) # w_test = np.ones_like(y_test) # ids_test = ["C"] * n_test # test_dataset = dc.data.DiskDataset.from_numpy( # X_test, y_test, w_test, ids_test) classification_metrics = [dc.metrics.Metric(dc.metrics.roc_auc_score)] def model_builder(model_dir): sklearn_model = LogisticRegression() return dc.models.SklearnModel(sklearn_model, model_dir) multitask_model = dc.models.SingletaskToMultitask( tasks, model_builder) # classification_metrics = [dc.metrics.Metric(dc.metrics.roc_auc_score)] # def model_builder(model_dir): # sklearn_model = LogisticRegression() # return dc.models.SklearnModel(sklearn_model, model_dir) # multitask_model = dc.models.SingletaskToMultitask( # tasks, model_builder) # Fit trained model multitask_model.fit(train_dataset) multitask_model.save() # # Fit trained model # multitask_model.fit(train_dataset) # multitask_model.save() # Eval multitask_model on train/test _ = multitask_model.evaluate(train_dataset, classification_metrics) _ = multitask_model.evaluate(test_dataset, classification_metrics) # # Eval multitask_model on train/test # _ = multitask_model.evaluate(train_dataset, classification_metrics) # _ = multitask_model.evaluate(test_dataset, classification_metrics) def test_to_singletask(self): Loading
