Loading README.md +12 −12 Original line number Diff line number Diff line Loading @@ -206,20 +206,20 @@ different subclasses of ``Featurizer`` for convenience: |Dataset |Model |Train score/ROC-AUC|Valid score/ROC-AUC|Time(loading)/s |Time(running)/s| |-----------|--------------------|-------------------|-------------------|----------------|---------------| |tox21 |logistic regression |0.910 |0.759 |30 |30 | | |tensorflow(MT-NN) |0.987 |0.800 | |30 | | |graph convolution |0.930 |0.819 | |40 | |muv |logistic regression |0.910 |0.744 |400 |800 | | |tensorflow(MT-NN) |0.980 |0.710 | |800 | | |graph convolution |0.881 |0.832 | |1200 | | |tensorflow(MT-NN) |0.987 |0.800 |30 |30 | | |graph convolution |0.930 |0.819 |40 |40 | |muv |logistic regression |0.910 |0.744 |600 |800 | | |tensorflow(MT-NN) |0.980 |0.710 |600 |800 | | |graph convolution |0.881 |0.832 |800 |1200 | |pcba |logistic regression |0.759 |0.736 |1800 |5400 | | |tensorflow(MT-NN) |0.949 |0.791 | |7200 | | |graph convolution |0.866 |0.836 | |20000 | |sider |logistic regression |0.900 |0.620 |20 |40 | | |tensorflow(MT-NN) |0.931 |0.647 | |60 | | |graph convolution |0.845 |0.646 | |60 | | |tensorflow(MT-NN) |0.949 |0.791 |1800 |7200 | | |graph convolution |0.866 |0.836 |2200 |20000 | |sider |logistic regression |0.900 |0.620 |15 |40 | | |tensorflow(MT-NN) |0.931 |0.647 |15 |60 | | |graph convolution |0.845 |0.646 |20 |60 | |toxcast |logistic regression |0.762 |0.622 |80 |2000 | | |tensorflow(MT-NN) |0.926 |0.705 | |2400 | | |graph convolution |0.906 |0.725 | |3000 | | |tensorflow(MT-NN) |0.926 |0.705 |80 |2400 | | |graph convolution |0.906 |0.725 |80 |3000 | ## Contributing to DeepChem Loading deepchem/models/tests/test_overfit.py +32 −0 Original line number Diff line number Diff line Loading @@ -463,6 +463,38 @@ class TestOverfit(test_util.TensorFlowTestCase): scores = model.evaluate(dataset, [classification_metric]) assert scores[classification_metric.name] > .9 def test_tf_logreg_multitask_classification_overfit(self): """Test tf multitask overfits tiny data.""" n_tasks = 10 n_samples = 10 n_features = 3 n_classes = 2 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) verbosity = "high" classification_metric = dc.metrics.Metric( dc.metrics.accuracy_score, verbosity=verbosity, task_averager=np.mean) tensorflow_model = dc.models.TensorflowLogisticRegression( n_tasks, n_features, learning_rate=0.01, weight_init_stddevs=[.01], batch_size=n_samples, verbosity=verbosity) model = dc.models.TensorflowModel(tensorflow_model) # Fit trained model model.fit(dataset) model.save() # Eval model on train scores = model.evaluate(dataset, [classification_metric]) assert scores[classification_metric.name] > .9 def test_sklearn_multitask_regression_overfit(self): """Test SKLearn singletask-to-multitask overfits tiny regression data.""" n_tasks = 2 Loading Loading
README.md +12 −12 Original line number Diff line number Diff line Loading @@ -206,20 +206,20 @@ different subclasses of ``Featurizer`` for convenience: |Dataset |Model |Train score/ROC-AUC|Valid score/ROC-AUC|Time(loading)/s |Time(running)/s| |-----------|--------------------|-------------------|-------------------|----------------|---------------| |tox21 |logistic regression |0.910 |0.759 |30 |30 | | |tensorflow(MT-NN) |0.987 |0.800 | |30 | | |graph convolution |0.930 |0.819 | |40 | |muv |logistic regression |0.910 |0.744 |400 |800 | | |tensorflow(MT-NN) |0.980 |0.710 | |800 | | |graph convolution |0.881 |0.832 | |1200 | | |tensorflow(MT-NN) |0.987 |0.800 |30 |30 | | |graph convolution |0.930 |0.819 |40 |40 | |muv |logistic regression |0.910 |0.744 |600 |800 | | |tensorflow(MT-NN) |0.980 |0.710 |600 |800 | | |graph convolution |0.881 |0.832 |800 |1200 | |pcba |logistic regression |0.759 |0.736 |1800 |5400 | | |tensorflow(MT-NN) |0.949 |0.791 | |7200 | | |graph convolution |0.866 |0.836 | |20000 | |sider |logistic regression |0.900 |0.620 |20 |40 | | |tensorflow(MT-NN) |0.931 |0.647 | |60 | | |graph convolution |0.845 |0.646 | |60 | | |tensorflow(MT-NN) |0.949 |0.791 |1800 |7200 | | |graph convolution |0.866 |0.836 |2200 |20000 | |sider |logistic regression |0.900 |0.620 |15 |40 | | |tensorflow(MT-NN) |0.931 |0.647 |15 |60 | | |graph convolution |0.845 |0.646 |20 |60 | |toxcast |logistic regression |0.762 |0.622 |80 |2000 | | |tensorflow(MT-NN) |0.926 |0.705 | |2400 | | |graph convolution |0.906 |0.725 | |3000 | | |tensorflow(MT-NN) |0.926 |0.705 |80 |2400 | | |graph convolution |0.906 |0.725 |80 |3000 | ## Contributing to DeepChem Loading
deepchem/models/tests/test_overfit.py +32 −0 Original line number Diff line number Diff line Loading @@ -463,6 +463,38 @@ class TestOverfit(test_util.TensorFlowTestCase): scores = model.evaluate(dataset, [classification_metric]) assert scores[classification_metric.name] > .9 def test_tf_logreg_multitask_classification_overfit(self): """Test tf multitask overfits tiny data.""" n_tasks = 10 n_samples = 10 n_features = 3 n_classes = 2 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) verbosity = "high" classification_metric = dc.metrics.Metric( dc.metrics.accuracy_score, verbosity=verbosity, task_averager=np.mean) tensorflow_model = dc.models.TensorflowLogisticRegression( n_tasks, n_features, learning_rate=0.01, weight_init_stddevs=[.01], batch_size=n_samples, verbosity=verbosity) model = dc.models.TensorflowModel(tensorflow_model) # Fit trained model model.fit(dataset) model.save() # Eval model on train scores = model.evaluate(dataset, [classification_metric]) assert scores[classification_metric.name] > .9 def test_sklearn_multitask_regression_overfit(self): """Test SKLearn singletask-to-multitask overfits tiny regression data.""" n_tasks = 2 Loading
