def test_customized_graph_dataset():
result = experiment(model="gin",
task="graph_classification",
dataset="mygraphdataset",
degree_feature=True,
max_epoch=10)
result = list(result.values())[0][0]
assert result["Acc"] >= 0
def test_customized_graph_dataset_graph2vec():
dataset = MyGraphClassificationDataset()
result = experiment(model="graph2vec",
dataset=dataset,
degree_node_features=False,
epochs=10,
cpu=True)
result = list(result.values())[0][0]
assert result["acc"] >= 0
def test_experiment():
results = experiment(task="node_classification",
dataset="cora",
model="gcn",
hidden_size=32,
max_epoch=10,
cpu=True)
assert ("cora", "gcn") in results
assert results[("cora", "gcn")][0]["Acc"] > 0
def test_autognn_experiment():
results = experiment(
dataset="cora",
model="autognn",
seed=[1],
n_trials=10,
epochs=2,
cpu=True,
)
assert ("cora", "autognn") in results
assert results[("cora", "autognn")][0]["test_acc"] > 0
def test_auto_experiment():
def search_space_example(trial):
return {
"lr":
trial.suggest_categorical("lr", [1e-3, 5e-3, 1e-2]),
"hidden_size":
trial.suggest_categorical("hidden_size", [16, 32, 64, 128]),
"dropout":
trial.suggest_uniform("dropout", 0.5, 0.9),
}
results = experiment(
dataset="cora",
model="gcn",
seed=[1, 2],
n_trials=2,
epochs=10,
search_space=search_space_example,
cpu=True,
)
assert ("cora", "gcn") in results
assert results[("cora", "gcn")][0]["test_acc"] > 0
def test_auto_experiment():
def func_search_example(trial):
return {
"lr":
trial.suggest_categorical("lr", [1e-3, 5e-3, 1e-2]),
"hidden_size":
trial.suggest_categorical("hidden_size", [16, 32, 64, 128]),
"dropout":
trial.suggest_uniform("dropout", 0.5, 0.9),
}
results = experiment(
task="node_classification",
dataset="cora",
model="gcn",
seed=[1, 2],
n_trials=2,
max_epoch=10,
func_search=func_search_example,
cpu=True,
)
assert ("cora", "gcn") in results
assert results[("cora", "gcn")][0]["Acc"] > 0
# load or generate your dataset
edge_index = torch.randint(0, num_nodes, (2, num_edges))
x = torch.randn(num_nodes, feat_dim)
y = torch.randint(0, 2, (num_nodes, ))
# set train/val/test mask in node_classification task
train_mask = torch.zeros(num_nodes).bool()
train_mask[0:int(0.3 * num_nodes)] = True
val_mask = torch.zeros(num_nodes).bool()
val_mask[int(0.3 * num_nodes):int(0.7 * num_nodes)] = True
test_mask = torch.zeros(num_nodes).bool()
test_mask[int(0.7 * num_nodes):] = True
data = Graph(x=x,
edge_index=edge_index,
y=y,
train_mask=train_mask,
val_mask=val_mask,
test_mask=test_mask)
return data
if __name__ == "__main__":
# Train customized dataset via defining a new class
dataset = MyNodeClassificationDataset()
experiment(dataset=dataset, model="gcn")
# Train customized dataset via feeding the graph data to NodeDataset
data = generate_random_graph(num_nodes=100, num_edges=300, num_feats=30)
dataset = NodeDataset(data=data)
experiment(dataset=dataset, model="gcn")