def test_graph_conv_atom_features(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'Raw', num_tasks=1)
atom_feature_name = 'feature'
y = []
for mol in dataset.X:
atom_features = []
for atom in mol.GetAtoms():
val = np.random.normal()
mol.SetProp("atom %08d %s" % (atom.GetIdx(), atom_feature_name),
str(val))
atom_features.append(np.random.normal())
y.append([np.sum(atom_features)])
featurizer = ConvMolFeaturizer(atom_properties=[atom_feature_name])
X = featurizer.featurize(dataset.X)
dataset = dc.data.NumpyDataset(X, np.array(y))
batch_size = 50
model = GraphConvModel(
len(tasks),
number_atom_features=featurizer.feature_length(),
batch_size=batch_size,
mode='regression')
model.fit(dataset, nb_epoch=1)
y_pred1 = model.predict(dataset)
model.save()
model2 = TensorGraph.load_from_dir(model.model_dir)
y_pred2 = model2.predict(dataset)
self.assertTrue(np.allclose(y_pred1, y_pred2))
def test_weave_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'Weave')
model = WeaveModel(len(tasks), mode='classification')
model.fit(dataset, nb_epoch=50)
scores = model.evaluate(dataset, [metric], transformers)
assert scores['mean-roc_auc_score'] >= 0.9
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean-roc_auc_score'],
scores2['mean-roc_auc_score'])
def test_weave_regression_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'Weave')
model = WeaveModel(len(tasks), mode='regression')
model.fit(dataset, nb_epoch=80)
scores = model.evaluate(dataset, [metric], transformers)
assert all(s < 0.1 for s in scores['mean_absolute_error'])
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean_absolute_error'],
scores2['mean_absolute_error'])
def test_graph_conv_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'GraphConv')
batch_size = 50
model = GraphConvModel(
len(tasks), batch_size=batch_size, mode='classification')
model.fit(dataset, nb_epoch=10)
scores = model.evaluate(dataset, [metric], transformers)
assert scores['mean-roc_auc_score'] >= 0.9
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean-roc_auc_score'],
scores2['mean-roc_auc_score'])
def test_change_loss_function(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'GraphConv', num_tasks=1)
batch_size = 50
model = GraphConvModel(len(tasks), batch_size=batch_size, mode='regression')
model.fit(dataset, nb_epoch=1)
model.save()
model2 = TensorGraph.load_from_dir(model.model_dir, restore=False)
dummy_label = model2.labels[-1]
dummy_ouput = model2.outputs[-1]
loss = ReduceSum(L2Loss(in_layers=[dummy_label, dummy_ouput]))
module = model2.create_submodel(loss=loss)
model2.restore()
model2.fit(dataset, nb_epoch=1, submodel=module)
def test_graph_conv_regression_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'GraphConv')
batch_size = 50
model = GraphConvModel(len(tasks), batch_size=batch_size, mode='regression')
model.fit(dataset, nb_epoch=100)
scores = model.evaluate(dataset, [metric], transformers)
assert all(s < 0.1 for s in scores['mean_absolute_error'])
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(
scores['mean_absolute_error'],
scores2['mean_absolute_error'],
rtol=1e-4)
def test_dag_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'GraphConv')
max_atoms = max([mol.get_num_atoms() for mol in dataset.X])
transformer = dc.trans.DAGTransformer(max_atoms=max_atoms)
dataset = transformer.transform(dataset)
model = DAGModel(
len(tasks), max_atoms=max_atoms, mode='classification', use_queue=False)
model.fit(dataset, nb_epoch=10)
scores = model.evaluate(dataset, [metric], transformers)
assert scores['mean-roc_auc_score'] >= 0.9
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean-roc_auc_score'],
scores2['mean-roc_auc_score'])
def test_mpnn_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'Weave')
model = MPNNModel(len(tasks),
mode='classification',
n_hidden=75,
n_atom_feat=75,
n_pair_feat=14,
T=1,
M=1)
model.fit(dataset, nb_epoch=20)
scores = model.evaluate(dataset, [metric], transformers)
assert scores['mean-roc_auc_score'] >= 0.9
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean-roc_auc_score'],
scores2['mean-roc_auc_score'])
def test_change_loss_function_weave(self):
tasks, dataset, transformers, metric = self.get_dataset('regression',
'Weave',
num_tasks=1)
batch_size = 50
model = WeaveModel(len(tasks),
batch_size=batch_size,
mode='regression',
use_queue=False)
model.fit(dataset, nb_epoch=1)
model.save()
model2 = TensorGraph.load_from_dir(model.model_dir, restore=False)
dummy_label = model2.labels[-1]
dummy_ouput = model2.outputs[-1]
loss = ReduceSum(L2Loss(in_layers=[dummy_label, dummy_ouput]))
module = model2.create_submodel(loss=loss)
model2.restore()
model2.fit(dataset, nb_epoch=1, submodel=module)
def test_mpnn_regression_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'Weave')
model = MPNNModel(
len(tasks),
mode='regression',
n_hidden=75,
n_atom_feat=75,
n_pair_feat=14,
T=1,
M=1)
model.fit(dataset, nb_epoch=50)
scores = model.evaluate(dataset, [metric], transformers)
assert all(s < 0.1 for s in scores['mean_absolute_error'])
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean_absolute_error'],
scores2['mean_absolute_error'])
def test_dag_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'GraphConv')
max_atoms = max([mol.get_num_atoms() for mol in dataset.X])
transformer = dc.trans.DAGTransformer(max_atoms=max_atoms)
dataset = transformer.transform(dataset)
model = DAGModel(len(tasks),
max_atoms=max_atoms,
mode='classification',
use_queue=False)
model.fit(dataset, nb_epoch=10)
scores = model.evaluate(dataset, [metric], transformers)
assert scores['mean-roc_auc_score'] >= 0.9
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean-roc_auc_score'],
scores2['mean-roc_auc_score'])
def test_mpnn_regression_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'Weave')
model = MPNNModel(
len(tasks),
mode='regression',
n_hidden=75,
n_atom_feat=75,
n_pair_feat=14,
T=1,
M=1)
model.fit(dataset, nb_epoch=50)
scores = model.evaluate(dataset, [metric], transformers)
assert all(s < 0.1 for s in scores['mean_absolute_error'])
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean_absolute_error'],
scores2['mean_absolute_error'])
def test_mpnn_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'classification', 'Weave')
model = MPNNModel(
len(tasks),
mode='classification',
n_hidden=75,
n_atom_feat=75,
n_pair_feat=14,
T=1,
M=1)
model.fit(dataset, nb_epoch=20)
scores = model.evaluate(dataset, [metric], transformers)
assert scores['mean-roc_auc_score'] >= 0.9
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean-roc_auc_score'],
scores2['mean-roc_auc_score'])
def test_dag_regression_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'GraphConv')
max_atoms = max([mol.get_num_atoms() for mol in dataset.X])
transformer = dc.trans.DAGTransformer(max_atoms=max_atoms)
dataset = transformer.transform(dataset)
model = DAGModel(len(tasks),
max_atoms=max_atoms,
mode='regression',
learning_rate=0.003,
use_queue=False)
model.fit(dataset, nb_epoch=100)
scores = model.evaluate(dataset, [metric], transformers)
assert all(s < 0.15 for s in scores['mean_absolute_error'])
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean_absolute_error'],
scores2['mean_absolute_error'])
def test_save_load(self):
"""Test SaScoreModel anc be saved and loaded"""
n_samples = 10
n_features = 3
n_tasks = 1
# Create a dataset and an input function for processing it.
np.random.seed(123)
X = np.random.rand(n_samples, 2, n_features)
y = np.zeros((n_samples, n_tasks))
dataset = deepchem.data.NumpyDataset(X, y)
model = deepchem.models.ScScoreModel(n_features, dropouts=0)
model.fit(dataset, nb_epoch=1)
pred1 = model.predict(dataset)
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
pred2 = model.predict(dataset)
for m1, m2 in zip(pred1, pred2):
self.assertTrue(np.all(m1 == m2))
def test_save_load(self):
"""Test SaScoreModel anc be saved and loaded"""
n_samples = 10
n_features = 3
n_tasks = 1
# Create a dataset and an input function for processing it.
np.random.seed(123)
X = np.random.rand(n_samples, 2, n_features)
y = np.zeros((n_samples, n_tasks))
dataset = deepchem.data.NumpyDataset(X, y)
model = deepchem.models.ScScoreModel(n_features, dropouts=0)
model.fit(dataset, nb_epoch=1)
pred1 = model.predict(dataset)
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
pred2 = model.predict(dataset)
for m1, m2 in zip(pred1, pred2):
self.assertTrue(np.all(m1 == m2))
def test_dag_regression_model(self):
tasks, dataset, transformers, metric = self.get_dataset(
'regression', 'GraphConv')
max_atoms = max([mol.get_num_atoms() for mol in dataset.X])
transformer = dc.trans.DAGTransformer(max_atoms=max_atoms)
dataset = transformer.transform(dataset)
model = DAGModel(
len(tasks),
max_atoms=max_atoms,
mode='regression',
learning_rate=0.003,
use_queue=False)
model.fit(dataset, nb_epoch=100)
scores = model.evaluate(dataset, [metric], transformers)
assert all(s < 0.15 for s in scores['mean_absolute_error'])
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores2 = model.evaluate(dataset, [metric], transformers)
assert np.allclose(scores['mean_absolute_error'],
scores2['mean_absolute_error'])
