def test_generator_constructor(self):
     generator = FullBatchLinkGenerator(self.G)
     assert generator.Aadj.shape == (self.N, self.N)
     assert generator.features.shape == (self.N, self.n_feat)
Example #2
0
 def test_generator_flow_targets_not_iterator(self):
     generator = FullBatchLinkGenerator(self.G)
     link_ids = list(self.G.edges())[:3]
     link_targets = 1
     with pytest.raises(TypeError):
         generator.flow(link_ids, link_targets)
Example #3
0
 def test_generator_constructor_hin(self):
     feature_sizes = {"t1": 1, "t2": 1}
     Ghin, nodes_type_1, nodes_type_2 = example_hin_3(feature_sizes)
     with pytest.raises(TypeError):
         generator = FullBatchLinkGenerator(Ghin)
Example #4
0
 def test_generator_constructor_wrong_G_type(self):
     with pytest.raises(TypeError):
         generator = FullBatchLinkGenerator(nx.Graph())
edges = pd.DataFrame({"source": Source, "target": Target, "weight": Value})
Gs = sg.StellarGraph(nodes=nodes, edges=edges)

import tensorflow as tf

# Define an edge splitter on the original graph G:
edge_splitter_train = EdgeSplitter(Gs)

# Randomly sample a fraction p=0.1 of all positive links, and same number of negative links
# reduced graph G_train with the sampled links removed:
G_train, edge_ids_train, edge_labels_train = edge_splitter_train.train_test_split(
    p=0.1, method="global", keep_connected=True)

epochs = 300

train_gen = FullBatchLinkGenerator(G_train, method="gcn", weighted=True)
train_flow = train_gen.flow(edge_ids_train, edge_labels_train)

layer_sizes = [20, 20]

gcn = GCN(layer_sizes=layer_sizes,
          activations=["elu", "softmax"],
          generator=train_gen,
          dropout=0.5)

x_inp, x_out = gcn.in_out_tensors()

prediction = LinkEmbedding(activation="relu", method="ip")(x_out)

model = keras.Model(inputs=x_inp, outputs=prediction)
 def test_generator_constructor_hin(self):
     Ghin = example_hin_1({})
     with pytest.raises(TypeError):
         generator = FullBatchLinkGenerator(Ghin)