Merge 7792f51 into 766139b

deepchem/models/tensorgraph/models/graph_models.py

@@ -12,7 +12,7 @@
   DTNNEmbedding, DTNNStep, DTNNGather, DAGLayer, \
   DAGGather, DTNNExtract, MessagePassing, SetGather
 from deepchem.models.tensorgraph.graph_layers import WeaveLayerFactory
-from deepchem.models.tensorgraph.layers import Dense, Concat, SoftMax, \
+from deepchem.models.tensorgraph.layers import Dense, SoftMax, \
   SoftMaxCrossEntropy, GraphConv, BatchNorm, \
   GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization, Stack, Flatten, GraphCNN, GraphCNNPool
 from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature
@@ -116,7 +116,7 @@ def build_graph(self):
         cost = L2Loss(in_layers=[label, regression])
         costs.append(cost)
     if self.mode == "classification":
-      all_cost = Concat(in_layers=costs, axis=1)
+      all_cost = Stack(in_layers=costs, axis=1)
     elif self.mode == "regression":
       all_cost = Stack(in_layers=costs, axis=1)
     self.weights = Weights(shape=(None, self.n_tasks))
@@ -174,8 +174,8 @@ def default_generator(self,
           atom_feat.append(mol.get_atom_features())
           # pair features
           pair_feat.append(
-              np.reshape(mol.get_pair_features(), (n_atoms * n_atoms,
-                                                   self.n_pair_feat)))
+              np.reshape(mol.get_pair_features(),
+                         (n_atoms * n_atoms, self.n_pair_feat)))
 
         feed_dict[self.atom_features] = np.concatenate(atom_feat, axis=0)
         feed_dict[self.pair_features] = np.concatenate(pair_feat, axis=0)
@@ -310,8 +310,8 @@ def default_generator(self,
         num_atoms = list(map(sum, X_b.astype(bool)[:, :, 0]))
         atom_number = [
             np.round(
-                np.power(2 * np.diag(X_b[i, :num_atoms[i], :num_atoms[i]]), 1 /
-                         2.4)).astype(int) for i in range(len(num_atoms))
+                np.power(2 * np.diag(X_b[i, :num_atoms[i], :num_atoms[i]]),
+                         1 / 2.4)).astype(int) for i in range(len(num_atoms))
         ]
         start = 0
         for im, molecule in enumerate(atom_number):
@@ -425,7 +425,7 @@ def build_graph(self):
         cost = L2Loss(in_layers=[label, regression])
         costs.append(cost)
     if self.mode == "classification":
-      all_cost = Concat(in_layers=costs, axis=1)
+      all_cost = Stack(in_layers=costs, axis=1)
     elif self.mode == "regression":
       all_cost = Stack(in_layers=costs, axis=1)
     self.weights = Weights(shape=(None, self.n_tasks))
@@ -570,7 +570,7 @@ def build_graph(self):
         cost = L2Loss(in_layers=[label, regression])
         costs.append(cost)
     if self.mode == "classification":
-      entropy = Concat(in_layers=costs, axis=-1)
+      entropy = Stack(in_layers=costs, axis=-1)
     elif self.mode == "regression":
       entropy = Stack(in_layers=costs, axis=1)
     self.my_task_weights = Weights(shape=(None, self.n_tasks))
@@ -716,7 +716,7 @@ def build_graph(self):
         cost = L2Loss(in_layers=[label, regression])
         costs.append(cost)
     if self.mode == "classification":
-      entropy = Concat(in_layers=costs, axis=-1)
+      entropy = Stack(in_layers=costs, axis=1)
     elif self.mode == "regression":
       entropy = Stack(in_layers=costs, axis=1)
     self.my_task_weights = Weights(shape=(None, self.n_tasks))
@@ -994,7 +994,7 @@ def build_graph(self):
         cost = L2Loss(in_layers=[label, regression])
         costs.append(cost)
     if self.mode == "classification":
-      all_cost = Concat(in_layers=costs, axis=1)
+      all_cost = Stack(in_layers=costs, axis=1)
     elif self.mode == "regression":
       all_cost = Stack(in_layers=costs, axis=1)
     self.weights = Weights(shape=(None, self.n_tasks))
@@ -1051,8 +1051,8 @@ def default_generator(self,
           atom_feat.append(mol.get_atom_features())
           # pair features
           pair_feat.append(
-              np.reshape(mol.get_pair_features(), (n_atoms * n_atoms,
-                                                   self.n_pair_feat)))
+              np.reshape(mol.get_pair_features(),
+                         (n_atoms * n_atoms, self.n_pair_feat)))
 
         feed_dict[self.atom_features] = np.concatenate(atom_feat, axis=0)
         feed_dict[self.pair_features] = np.concatenate(pair_feat, axis=0)
@@ -1097,4 +1097,4 @@ def predict_proba_on_generator(self, generator, transformers=[]):
       return np.concatenate(results, axis=0)
 
   def predict_on_generator(self, generator, transformers=[]):
-    return self.predict_proba_on_generator(generator, transformers)
+    return self.predict_proba_on_generator(generator, transformers)

deepchem/models/tensorgraph/models/test_graph_models.py

@@ -11,21 +11,27 @@
 
 class TestGraphModels(unittest.TestCase):
 
-  def get_dataset(self, mode='classification', featurizer='GraphConv'):
+  def get_dataset(self,
+                  mode='classification',
+                  featurizer='GraphConv',
+                  num_tasks=2):
     data_points = 10
     tasks, all_dataset, transformers = load_delaney(featurizer)
     train, valid, test = all_dataset
+    for i in range(1, num_tasks):
+      tasks.append("random_task")
+    w = np.ones(shape=(data_points, len(tasks)))
 
     if mode == 'classification':
       y = np.random.randint(0, 2, size=(data_points, len(tasks)))
       metric = deepchem.metrics.Metric(
           deepchem.metrics.roc_auc_score, np.mean, mode="classification")
-    if mode == 'regression':
+    else:
       y = np.random.normal(size=(data_points, len(tasks)))
       metric = deepchem.metrics.Metric(
           deepchem.metrics.mean_absolute_error, mode="regression")
 
-    ds = NumpyDataset(train.X[:10], y, train.w[:10], train.ids[:10])
+    ds = NumpyDataset(train.X[:10], y, w, train.ids[:10])
 
     return tasks, ds, transformers, metric
 
@@ -61,7 +67,7 @@ def test_graph_conv_regression_model(self):
 
   def test_graph_conv_error_bars(self):
     tasks, dataset, transformers, metric = self.get_dataset(
-        'regression', 'GraphConv')
+        'regression', 'GraphConv', num_tasks=1)
 
     batch_size = 50
     model = GraphConvTensorGraph(

deepchem/models/tensorgraph/tests/test_layers.py

@@ -280,6 +280,7 @@ def test_log(self):
     with self.test_session() as sess:
       result = Log()(value).eval()
       assert np.array_equal(np.log(value), result)
+      assert np.all(np.isclose(np.log(value), result, atol=0.001))
 
   def test_exp(self):
     """Test that Exp can be invoked."""