Loading deepchem/models/tests/test_reload.py +69 −85 Original line number Diff line number Diff line Loading @@ -522,6 +522,75 @@ def test_progressivemultitaskregressor_reload(): assert scores[regression_metric.name] < 0.1 def test_DAG_regression_reload(): """Test DAG regressor reloads.""" np.random.seed(123) tf.random.set_seed(123) n_tasks = 1 #current_dir = os.path.dirname(os.path.abspath(__file__)) # Load mini log-solubility dataset. featurizer = dc.feat.ConvMolFeaturizer() tasks = ["outcome"] mols = ["CC", "CCO", "CC", "CCC", "CCCCO", "CO", "CC", "CCCCC", "CCC", "CCCO"] n_samples = len(mols) X = featurizer(mols) y = np.random.rand(n_samples, n_tasks) dataset = dc.data.NumpyDataset(X, y) regression_metric = dc.metrics.Metric( dc.metrics.pearson_r2_score, task_averager=np.mean) n_feat = 75 batch_size = 10 transformer = dc.trans.DAGTransformer(max_atoms=50) dataset = transformer.transform(dataset) model_dir = tempfile.mkdtemp() model = dc.models.DAGModel( n_tasks, max_atoms=50, n_atom_feat=n_feat, batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression", model_dir=model_dir) # Fit trained model model.fit(dataset, nb_epoch=100) # Eval model on train scores = model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] > .1 reloaded_model = dc.models.DAGModel( n_tasks, max_atoms=50, n_atom_feat=n_feat, batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression", model_dir=model_dir) reloaded_model.restore() # Check predictions match on random sample predmols = ["CCCC", "CCCCCO", "CCCCC"] Xpred = featurizer(predmols) predset = dc.data.NumpyDataset(Xpred) predset = transformer.transform(predset) origpred = model.predict(predset) reloadpred = reloaded_model.predict(predset) assert np.all(origpred == reloadpred) # Eval model on train scores = reloaded_model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] > .1 def test_weave_classification_reload(): """Test weave model can be reloaded.""" np.random.seed(123) Loading Loading @@ -586,91 +655,6 @@ def test_weave_classification_reload(): assert scores[classification_metric.name] > .6 ## TODO: THIS IS FAILING! #@pytest.mark.slow #def test_weave_classification_reload(): # """Test weave model can be reloaded.""" # np.random.seed(123) # tf.random.set_seed(123) # n_tasks = 1 # # # Load mini log-solubility dataset. # featurizer = dc.feat.WeaveFeaturizer() # tasks = ["outcome"] # mols = ["C", "CO", "CC"] # n_samples = len(mols) # X = featurizer(mols) # y = np.random.randint(2, size=(n_samples, n_tasks)) # dataset = dc.data.NumpyDataset(X, y) # # classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) # # batch_size = 3 # # model_dir = tempfile.mkdtemp() # model = dc.models.WeaveModel( # n_tasks, # batch_size=batch_size, # learning_rate=0.0003, # mode="classification", # dropouts=0.0, # model_dir=model_dir) # # # Fit trained model # model.fit(dataset, nb_epoch=3) # # # Eval model on train # scores = model.evaluate(dataset, [classification_metric]) # assert scores[classification_metric.name] > .9 # # # Check predictions match on random sample # predmols = ["CCCC", "CCCCCO", "CCCCC"] # Xpred = featurizer(predmols) # # predset = dc.data.NumpyDataset(Xpred) # origpred = model.predict(predset) # origpred2 = model.predict(predset) # assert np.all(origpred == origpred2) # # reloaded_model = dc.models.WeaveModel( # n_tasks, # batch_size=batch_size, # learning_rate=0.0003, # mode="classification", # dropouts=0.0, # model_dir=model_dir) # reloaded_model.restore() # # Xproc = reloaded_model.compute_features_on_batch(Xpred) # reloadout = reloaded_model.model(Xproc) # print("reloadout") # print(reloadout) # # reloadpred = reloaded_model.predict(predset) # print("reloadpred") # print(reloadpred) # # print("origpred") # print(origpred) # ## Try re-restore # #reloaded_model.restore() # #reloadpred = reloaded_model.predict(predset) # # #assert np.all(origpred == reloadpred) # print("np.amax(origpred - reloadpred)") # print(np.amax(origpred - reloadpred)) # print("np.allclose(origpred, reloadpred)") # print(np.allclose(origpred, reloadpred)) # # # Eval model on train # scores = reloaded_model.evaluate(dataset, [classification_metric]) # print("scores") # print(scores) # assert scores[classification_metric.name] > .9 # # assert np.all(origpred == reloadpred) # TODO: THIS IS FAILING! #def test_MPNN_regression_reload(): # """Test MPNN can reload datasets.""" Loading Loading
deepchem/models/tests/test_reload.py +69 −85 Original line number Diff line number Diff line Loading @@ -522,6 +522,75 @@ def test_progressivemultitaskregressor_reload(): assert scores[regression_metric.name] < 0.1 def test_DAG_regression_reload(): """Test DAG regressor reloads.""" np.random.seed(123) tf.random.set_seed(123) n_tasks = 1 #current_dir = os.path.dirname(os.path.abspath(__file__)) # Load mini log-solubility dataset. featurizer = dc.feat.ConvMolFeaturizer() tasks = ["outcome"] mols = ["CC", "CCO", "CC", "CCC", "CCCCO", "CO", "CC", "CCCCC", "CCC", "CCCO"] n_samples = len(mols) X = featurizer(mols) y = np.random.rand(n_samples, n_tasks) dataset = dc.data.NumpyDataset(X, y) regression_metric = dc.metrics.Metric( dc.metrics.pearson_r2_score, task_averager=np.mean) n_feat = 75 batch_size = 10 transformer = dc.trans.DAGTransformer(max_atoms=50) dataset = transformer.transform(dataset) model_dir = tempfile.mkdtemp() model = dc.models.DAGModel( n_tasks, max_atoms=50, n_atom_feat=n_feat, batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression", model_dir=model_dir) # Fit trained model model.fit(dataset, nb_epoch=100) # Eval model on train scores = model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] > .1 reloaded_model = dc.models.DAGModel( n_tasks, max_atoms=50, n_atom_feat=n_feat, batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression", model_dir=model_dir) reloaded_model.restore() # Check predictions match on random sample predmols = ["CCCC", "CCCCCO", "CCCCC"] Xpred = featurizer(predmols) predset = dc.data.NumpyDataset(Xpred) predset = transformer.transform(predset) origpred = model.predict(predset) reloadpred = reloaded_model.predict(predset) assert np.all(origpred == reloadpred) # Eval model on train scores = reloaded_model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] > .1 def test_weave_classification_reload(): """Test weave model can be reloaded.""" np.random.seed(123) Loading Loading @@ -586,91 +655,6 @@ def test_weave_classification_reload(): assert scores[classification_metric.name] > .6 ## TODO: THIS IS FAILING! #@pytest.mark.slow #def test_weave_classification_reload(): # """Test weave model can be reloaded.""" # np.random.seed(123) # tf.random.set_seed(123) # n_tasks = 1 # # # Load mini log-solubility dataset. # featurizer = dc.feat.WeaveFeaturizer() # tasks = ["outcome"] # mols = ["C", "CO", "CC"] # n_samples = len(mols) # X = featurizer(mols) # y = np.random.randint(2, size=(n_samples, n_tasks)) # dataset = dc.data.NumpyDataset(X, y) # # classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score) # # batch_size = 3 # # model_dir = tempfile.mkdtemp() # model = dc.models.WeaveModel( # n_tasks, # batch_size=batch_size, # learning_rate=0.0003, # mode="classification", # dropouts=0.0, # model_dir=model_dir) # # # Fit trained model # model.fit(dataset, nb_epoch=3) # # # Eval model on train # scores = model.evaluate(dataset, [classification_metric]) # assert scores[classification_metric.name] > .9 # # # Check predictions match on random sample # predmols = ["CCCC", "CCCCCO", "CCCCC"] # Xpred = featurizer(predmols) # # predset = dc.data.NumpyDataset(Xpred) # origpred = model.predict(predset) # origpred2 = model.predict(predset) # assert np.all(origpred == origpred2) # # reloaded_model = dc.models.WeaveModel( # n_tasks, # batch_size=batch_size, # learning_rate=0.0003, # mode="classification", # dropouts=0.0, # model_dir=model_dir) # reloaded_model.restore() # # Xproc = reloaded_model.compute_features_on_batch(Xpred) # reloadout = reloaded_model.model(Xproc) # print("reloadout") # print(reloadout) # # reloadpred = reloaded_model.predict(predset) # print("reloadpred") # print(reloadpred) # # print("origpred") # print(origpred) # ## Try re-restore # #reloaded_model.restore() # #reloadpred = reloaded_model.predict(predset) # # #assert np.all(origpred == reloadpred) # print("np.amax(origpred - reloadpred)") # print(np.amax(origpred - reloadpred)) # print("np.allclose(origpred, reloadpred)") # print(np.allclose(origpred, reloadpred)) # # # Eval model on train # scores = reloaded_model.evaluate(dataset, [classification_metric]) # print("scores") # print(scores) # assert scores[classification_metric.name] > .9 # # assert np.all(origpred == reloadpred) # TODO: THIS IS FAILING! #def test_MPNN_regression_reload(): # """Test MPNN can reload datasets.""" Loading
