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.all(y_pred1 == y_pred2))
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_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=1)
scores = model.evaluate(dataset, [metric], transformers)
model.save()
model = TensorGraph.load_from_dir(model.model_dir)
scores = model.evaluate(dataset, [metric], transformers)
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'])
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_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)
#n_feat = 1000 # Number of features on conv-mols
batch_size = 1000 # Batch size of models
nb_epoch = 1000 # Number of epochs for convergence
model = GraphConvModel(
1,
batch_size=batch_size,
mode='regression',
dropout=0.2,
tensorboard=True,
model_dir=
"/home/rod/Dropbox/Quimica/Analysis/ANalisis/Borradores/GraphConvModel/"
) #To prevent overfitting
# Fit trained model
model.fit(train_dataset, nb_epoch=nb_epoch)
model.save()
print("Evaluating model")
train_scores = model.evaluate(train_dataset, [metric], transformers)
valid_scores = model.evaluate(valid_dataset, [metric], transformers)
print("Train scores")
print(train_scores)
print("Validation scores")
print(valid_scores)
"""
With featurizer = dc.feat.ConvMolFeaturizer()
----------------------------------------
Train scores
{'mean-pearson_r2_score': 0.9637847589740351}
Validation scores
