Loading deepchem/models/tests/test_generalize.py +60 −61 Original line number Diff line number Diff line Loading @@ -5,10 +5,7 @@ Tests to make sure deepchem models can fit models on easy datasets. import sklearn import sklearn.datasets import numpy as np import unittest import tempfile import deepchem as dc from sklearn.ensemble import RandomForestRegressor from sklearn.linear_model import LinearRegression from sklearn.linear_model import LogisticRegression Loading Loading @@ -122,63 +119,65 @@ def test_sklearn_multitask_regression(): assert score > .5 #def test_sklearn_classification(): # """Test that sklearn models can learn on simple classification datasets.""" # np.random.seed(123) # dataset = sklearn.datasets.load_digits(n_class=2) # X, y = dataset.data, dataset.target # frac_train = .7 # n_samples = len(X) # n_train = int(frac_train*n_samples) # X_train, y_train = X[:n_train], y[:n_train] # X_test, y_test = X[n_train:], y[n_train:] # train_dataset = dc.data.NumpyDataset(X_train, y_train) # test_dataset = dc.data.NumpyDataset(X_test, y_test) # classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) # sklearn_model = LogisticRegression() # model = dc.models.SklearnModel(sklearn_model) # # Fit trained model # model.fit(train_dataset) # model.save() # # Eval model on test # scores = model.evaluate(test_dataset, [classification_metric]) # assert scores[classification_metric.name] > .5 #def test_sklearn_multitask_classification(): # """Test that sklearn models can learn on simple multitask classification.""" # np.random.seed(123) # n_tasks = 4 # tasks = range(n_tasks) # dataset = sklearn.datasets.load_digits(n_class=2) # X, y = dataset.data, dataset.target # y = np.reshape(y, (len(y), 1)) # y = np.hstack([y] * n_tasks) # # frac_train = .7 # n_samples = len(X) # n_train = int(frac_train*n_samples) # X_train, y_train = X[:n_train], y[:n_train] # X_test, y_test = X[n_train:], y[n_train:] # train_dataset = dc.data.DiskDataset.from_numpy(X_train, y_train) # test_dataset = dc.data.DiskDataset.from_numpy(X_test, y_test) # classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) # def model_builder(model_dir): # sklearn_model = LogisticRegression() # return dc.models.SklearnModel(sklearn_model, model_dir) # model = dc.models.SingletaskToMultitask(tasks, model_builder) # # Fit trained model # model.fit(train_dataset) # model.save() # # Eval model on test # scores = model.evaluate(test_dataset, [classification_metric]) # for score in scores[classification_metric.name]: # assert score > .5 def test_sklearn_classification(): """Test that sklearn models can learn on simple classification datasets.""" np.random.seed(123) dataset = sklearn.datasets.load_digits(n_class=2) X, y = dataset.data, dataset.target frac_train = .7 n_samples = len(X) n_train = int(frac_train * n_samples) X_train, y_train = X[:n_train], y[:n_train] X_test, y_test = X[n_train:], y[n_train:] train_dataset = dc.data.NumpyDataset(X_train, y_train) test_dataset = dc.data.NumpyDataset(X_test, y_test) classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) sklearn_model = LogisticRegression() model = dc.models.SklearnModel(sklearn_model) # Fit trained model model.fit(train_dataset) model.save() # Eval model on test scores = model.evaluate(test_dataset, [classification_metric]) assert scores[classification_metric.name] > .5 def test_sklearn_multitask_classification(): """Test that sklearn models can learn on simple multitask classification.""" np.random.seed(123) n_tasks = 4 tasks = range(n_tasks) dataset = sklearn.datasets.load_digits(n_class=2) X, y = dataset.data, dataset.target y = np.reshape(y, (len(y), 1)) y = np.hstack([y] * n_tasks) frac_train = .7 n_samples = len(X) n_train = int(frac_train * n_samples) X_train, y_train = X[:n_train], y[:n_train] X_test, y_test = X[n_train:], y[n_train:] train_dataset = dc.data.DiskDataset.from_numpy(X_train, y_train) test_dataset = dc.data.DiskDataset.from_numpy(X_test, y_test) classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) def model_builder(model_dir): sklearn_model = LogisticRegression() return dc.models.SklearnModel(sklearn_model, model_dir) model = dc.models.SingletaskToMultitask(tasks, model_builder) # Fit trained model model.fit(train_dataset) model.save() # Eval model on test scores = model.evaluate(test_dataset, [classification_metric]) assert scores[classification_metric.name] > .5 def test_xgboost_regression(): Loading Loading @@ -245,7 +244,7 @@ def test_xgboost_multitask_regression(): # Eval model on test scores = model.evaluate(test_dataset, [regression_metric]) score = scores[regression_metric.name] assert score < 50 assert score < 55 def test_xgboost_classification(): Loading Loading
deepchem/models/tests/test_generalize.py +60 −61 Original line number Diff line number Diff line Loading @@ -5,10 +5,7 @@ Tests to make sure deepchem models can fit models on easy datasets. import sklearn import sklearn.datasets import numpy as np import unittest import tempfile import deepchem as dc from sklearn.ensemble import RandomForestRegressor from sklearn.linear_model import LinearRegression from sklearn.linear_model import LogisticRegression Loading Loading @@ -122,63 +119,65 @@ def test_sklearn_multitask_regression(): assert score > .5 #def test_sklearn_classification(): # """Test that sklearn models can learn on simple classification datasets.""" # np.random.seed(123) # dataset = sklearn.datasets.load_digits(n_class=2) # X, y = dataset.data, dataset.target # frac_train = .7 # n_samples = len(X) # n_train = int(frac_train*n_samples) # X_train, y_train = X[:n_train], y[:n_train] # X_test, y_test = X[n_train:], y[n_train:] # train_dataset = dc.data.NumpyDataset(X_train, y_train) # test_dataset = dc.data.NumpyDataset(X_test, y_test) # classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) # sklearn_model = LogisticRegression() # model = dc.models.SklearnModel(sklearn_model) # # Fit trained model # model.fit(train_dataset) # model.save() # # Eval model on test # scores = model.evaluate(test_dataset, [classification_metric]) # assert scores[classification_metric.name] > .5 #def test_sklearn_multitask_classification(): # """Test that sklearn models can learn on simple multitask classification.""" # np.random.seed(123) # n_tasks = 4 # tasks = range(n_tasks) # dataset = sklearn.datasets.load_digits(n_class=2) # X, y = dataset.data, dataset.target # y = np.reshape(y, (len(y), 1)) # y = np.hstack([y] * n_tasks) # # frac_train = .7 # n_samples = len(X) # n_train = int(frac_train*n_samples) # X_train, y_train = X[:n_train], y[:n_train] # X_test, y_test = X[n_train:], y[n_train:] # train_dataset = dc.data.DiskDataset.from_numpy(X_train, y_train) # test_dataset = dc.data.DiskDataset.from_numpy(X_test, y_test) # classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) # def model_builder(model_dir): # sklearn_model = LogisticRegression() # return dc.models.SklearnModel(sklearn_model, model_dir) # model = dc.models.SingletaskToMultitask(tasks, model_builder) # # Fit trained model # model.fit(train_dataset) # model.save() # # Eval model on test # scores = model.evaluate(test_dataset, [classification_metric]) # for score in scores[classification_metric.name]: # assert score > .5 def test_sklearn_classification(): """Test that sklearn models can learn on simple classification datasets.""" np.random.seed(123) dataset = sklearn.datasets.load_digits(n_class=2) X, y = dataset.data, dataset.target frac_train = .7 n_samples = len(X) n_train = int(frac_train * n_samples) X_train, y_train = X[:n_train], y[:n_train] X_test, y_test = X[n_train:], y[n_train:] train_dataset = dc.data.NumpyDataset(X_train, y_train) test_dataset = dc.data.NumpyDataset(X_test, y_test) classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) sklearn_model = LogisticRegression() model = dc.models.SklearnModel(sklearn_model) # Fit trained model model.fit(train_dataset) model.save() # Eval model on test scores = model.evaluate(test_dataset, [classification_metric]) assert scores[classification_metric.name] > .5 def test_sklearn_multitask_classification(): """Test that sklearn models can learn on simple multitask classification.""" np.random.seed(123) n_tasks = 4 tasks = range(n_tasks) dataset = sklearn.datasets.load_digits(n_class=2) X, y = dataset.data, dataset.target y = np.reshape(y, (len(y), 1)) y = np.hstack([y] * n_tasks) frac_train = .7 n_samples = len(X) n_train = int(frac_train * n_samples) X_train, y_train = X[:n_train], y[:n_train] X_test, y_test = X[n_train:], y[n_train:] train_dataset = dc.data.DiskDataset.from_numpy(X_train, y_train) test_dataset = dc.data.DiskDataset.from_numpy(X_test, y_test) classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) def model_builder(model_dir): sklearn_model = LogisticRegression() return dc.models.SklearnModel(sklearn_model, model_dir) model = dc.models.SingletaskToMultitask(tasks, model_builder) # Fit trained model model.fit(train_dataset) model.save() # Eval model on test scores = model.evaluate(test_dataset, [classification_metric]) assert scores[classification_metric.name] > .5 def test_xgboost_regression(): Loading Loading @@ -245,7 +244,7 @@ def test_xgboost_multitask_regression(): # Eval model on test scores = model.evaluate(test_dataset, [regression_metric]) score = scores[regression_metric.name] assert score < 50 assert score < 55 def test_xgboost_classification(): Loading
