Loading deepchem/models/tests/example_DTNN.mat +3.34 KiB (13.4 KiB) File changed.No diff preview for this file type. View original file View changed file deepchem/models/tests/test_overfit.py +99 −2 Original line number Diff line number Diff line Loading @@ -940,7 +940,6 @@ class TestOverfit(test_util.TensorFlowTestCase): np.random.seed(123) tf.set_random_seed(123) # Load mini log-solubility dataset. input_file = os.path.join(self.current_dir, "example_DTNN.mat") dataset = scipy.io.loadmat(input_file) X = dataset['X'] Loading Loading @@ -983,7 +982,6 @@ class TestOverfit(test_util.TensorFlowTestCase): np.random.seed(123) tf.set_random_seed(123) # Load mini log-solubility dataset. input_file = os.path.join(self.current_dir, "example_DTNN.mat") dataset = scipy.io.loadmat(input_file) X = dataset['X'] Loading Loading @@ -1012,6 +1010,105 @@ class TestOverfit(test_util.TensorFlowTestCase): assert scores[regression_metric.name] > .9 def test_ANI_multitask_regression_overfit(self): """Test ANI-1 regression overfits tiny data.""" input_file = os.path.join(self.current_dir, "example_DTNN.mat") np.random.seed(123) tf.set_random_seed(123) dataset = scipy.io.loadmat(input_file) X = np.concatenate([np.expand_dims(dataset['Z'], 2), dataset['R']], axis=2) X = X[:, :13, :] y = dataset['T'] w = np.ones_like(y) dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids=None) regression_metric = dc.metrics.Metric( dc.metrics.pearson_r2_score, mode="regression") n_tasks = y.shape[1] batch_size = 10 transformers = [ dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset), dc.trans.ANITransformer( max_atoms=13, atom_cases=[1, 6, 7, 8], radial_cutoff=8., angular_cutoff=5., radial_length=8, angular_length=4) ] for transformer in transformers: dataset = transformer.transform(dataset) n_feat = transformers[-1].get_num_feats() - 1 model = dc.models.ANIRegression( n_tasks, 13, n_feat, atom_number_cases=[1, 6, 7, 8], batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression") # Fit trained model model.fit(dataset, nb_epoch=50) # Eval model on train scores = model.evaluate(dataset, [regression_metric], transformers[0:1]) assert scores[regression_metric.name] > .8 def test_BP_symmetry_function_overfit(self): """Test ANI-1 regression overfits tiny data.""" input_file = os.path.join(self.current_dir, "example_DTNN.mat") np.random.seed(123) tf.set_random_seed(123) dataset = scipy.io.loadmat(input_file) X = np.concatenate([np.expand_dims(dataset['Z'], 2), dataset['R']], axis=2) X = X[:, :13, :] y = dataset['T'] w = np.ones_like(y) dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids=None) regression_metric = dc.metrics.Metric( dc.metrics.pearson_r2_score, mode="regression") n_tasks = y.shape[1] batch_size = 10 transformers = [ dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset), dc.trans.ANITransformer( max_atoms=13, atom_cases=[1, 6, 7, 8], atomic_number_differentiated=False, radial_cutoff=8., angular_cutoff=5., radial_length=8, angular_length=4) ] for transformer in transformers: dataset = transformer.transform(dataset) n_feat = transformers[-1].get_num_feats() - 1 model = dc.models.ANIRegression( n_tasks, 13, n_feat, atom_number_cases=[1, 6, 7, 8], batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression") # Fit trained model model.fit(dataset, nb_epoch=50) # Eval model on train scores = model.evaluate(dataset, [regression_metric], transformers[0:1]) assert scores[regression_metric.name] > .8 def test_DAG_singletask_regression_overfit(self): """Test DAG regressor multitask overfits tiny data.""" np.random.seed(123) Loading deepchem/trans/transformers.py +3 −2 Original line number Diff line number Diff line Loading @@ -965,11 +965,11 @@ class ANITransformer(Transformer): def transform_array(self, X, y, w): if self.transform_X: n_samples = X.shape[0] batches = np.linspace(0, n_samples, int(n_samples / 100)).astype(int) batches = np.linspace(0, n_samples, int(n_samples / 100) + 1).astype(int) X_out = [] sess = tf.Session(graph=self.compute_graph) num_transformed = 0 for i, start in enumerate(batches[:-1]): for i, start in enumerate(batches): if start == batches[-1]: X_batch = X[start:] else: Loading @@ -978,6 +978,7 @@ class ANITransformer(Transformer): X_out.append(output) num_transformed = num_transformed + X_batch.shape[0] print('%i samples transformed' % num_transformed) X_new = np.concatenate(X_out, axis=0) assert X_new.shape[0] == X.shape[0] return (X_new, y, w) Loading Loading
deepchem/models/tests/example_DTNN.mat +3.34 KiB (13.4 KiB) File changed.No diff preview for this file type. View original file View changed file
deepchem/models/tests/test_overfit.py +99 −2 Original line number Diff line number Diff line Loading @@ -940,7 +940,6 @@ class TestOverfit(test_util.TensorFlowTestCase): np.random.seed(123) tf.set_random_seed(123) # Load mini log-solubility dataset. input_file = os.path.join(self.current_dir, "example_DTNN.mat") dataset = scipy.io.loadmat(input_file) X = dataset['X'] Loading Loading @@ -983,7 +982,6 @@ class TestOverfit(test_util.TensorFlowTestCase): np.random.seed(123) tf.set_random_seed(123) # Load mini log-solubility dataset. input_file = os.path.join(self.current_dir, "example_DTNN.mat") dataset = scipy.io.loadmat(input_file) X = dataset['X'] Loading Loading @@ -1012,6 +1010,105 @@ class TestOverfit(test_util.TensorFlowTestCase): assert scores[regression_metric.name] > .9 def test_ANI_multitask_regression_overfit(self): """Test ANI-1 regression overfits tiny data.""" input_file = os.path.join(self.current_dir, "example_DTNN.mat") np.random.seed(123) tf.set_random_seed(123) dataset = scipy.io.loadmat(input_file) X = np.concatenate([np.expand_dims(dataset['Z'], 2), dataset['R']], axis=2) X = X[:, :13, :] y = dataset['T'] w = np.ones_like(y) dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids=None) regression_metric = dc.metrics.Metric( dc.metrics.pearson_r2_score, mode="regression") n_tasks = y.shape[1] batch_size = 10 transformers = [ dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset), dc.trans.ANITransformer( max_atoms=13, atom_cases=[1, 6, 7, 8], radial_cutoff=8., angular_cutoff=5., radial_length=8, angular_length=4) ] for transformer in transformers: dataset = transformer.transform(dataset) n_feat = transformers[-1].get_num_feats() - 1 model = dc.models.ANIRegression( n_tasks, 13, n_feat, atom_number_cases=[1, 6, 7, 8], batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression") # Fit trained model model.fit(dataset, nb_epoch=50) # Eval model on train scores = model.evaluate(dataset, [regression_metric], transformers[0:1]) assert scores[regression_metric.name] > .8 def test_BP_symmetry_function_overfit(self): """Test ANI-1 regression overfits tiny data.""" input_file = os.path.join(self.current_dir, "example_DTNN.mat") np.random.seed(123) tf.set_random_seed(123) dataset = scipy.io.loadmat(input_file) X = np.concatenate([np.expand_dims(dataset['Z'], 2), dataset['R']], axis=2) X = X[:, :13, :] y = dataset['T'] w = np.ones_like(y) dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids=None) regression_metric = dc.metrics.Metric( dc.metrics.pearson_r2_score, mode="regression") n_tasks = y.shape[1] batch_size = 10 transformers = [ dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset), dc.trans.ANITransformer( max_atoms=13, atom_cases=[1, 6, 7, 8], atomic_number_differentiated=False, radial_cutoff=8., angular_cutoff=5., radial_length=8, angular_length=4) ] for transformer in transformers: dataset = transformer.transform(dataset) n_feat = transformers[-1].get_num_feats() - 1 model = dc.models.ANIRegression( n_tasks, 13, n_feat, atom_number_cases=[1, 6, 7, 8], batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression") # Fit trained model model.fit(dataset, nb_epoch=50) # Eval model on train scores = model.evaluate(dataset, [regression_metric], transformers[0:1]) assert scores[regression_metric.name] > .8 def test_DAG_singletask_regression_overfit(self): """Test DAG regressor multitask overfits tiny data.""" np.random.seed(123) Loading
deepchem/trans/transformers.py +3 −2 Original line number Diff line number Diff line Loading @@ -965,11 +965,11 @@ class ANITransformer(Transformer): def transform_array(self, X, y, w): if self.transform_X: n_samples = X.shape[0] batches = np.linspace(0, n_samples, int(n_samples / 100)).astype(int) batches = np.linspace(0, n_samples, int(n_samples / 100) + 1).astype(int) X_out = [] sess = tf.Session(graph=self.compute_graph) num_transformed = 0 for i, start in enumerate(batches[:-1]): for i, start in enumerate(batches): if start == batches[-1]: X_batch = X[start:] else: Loading @@ -978,6 +978,7 @@ class ANITransformer(Transformer): X_out.append(output) num_transformed = num_transformed + X_batch.shape[0] print('%i samples transformed' % num_transformed) X_new = np.concatenate(X_out, axis=0) assert X_new.shape[0] == X.shape[0] return (X_new, y, w) Loading
