def __init__(self, args=None):
dataset = "jknet_cora"
path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data", dataset)
if not osp.exists(path):
os.makedirs(path)
super(CoraDataset, self).__init__(path)
with open(self.processed_paths[0], 'rb') as fin:
load_data = pickle.load(fin)
self.num_nodes = load_data['node_num']
data = Data()
data.x = load_data['xs']
data.y = load_data['ys']
train_size = int(self.num_nodes * 0.8)
train_mask = np.zeros((self.num_nodes, ), dtype=bool)
train_idx = np.random.choice(np.arange(self.num_nodes), size=train_size, replace=False)
train_mask[train_idx] = True
test_mask = np.ones((self.num_nodes, ), dtype=bool)
test_mask[train_idx] = False
val_mask = test_mask
edges = load_data['edges']
edges = np.array(edges, dtype=int).transpose((1, 0))
data.edge_index = torch.from_numpy(edges)
data.train_mask = torch.from_numpy(train_mask)
data.test_mask = torch.from_numpy(test_mask)
data.val_mask = torch.from_numpy(val_mask)
data.x = torch.Tensor(data.x)
data.y = torch.LongTensor(data.y)
self.data = data
self.num_classes = torch.max(self.data.y).item() + 1
def read_gtn_data(self, folder):
edges = pickle.load(open(osp.join(folder, 'edges.pkl'), 'rb'))
labels = pickle.load(open(osp.join(folder, 'labels.pkl'), 'rb'))
node_features = pickle.load(
open(osp.join(folder, 'node_features.pkl'), 'rb'))
data = Data()
data.x = torch.from_numpy(node_features).type(torch.FloatTensor)
num_nodes = edges[0].shape[0]
node_type = np.zeros((num_nodes), dtype=int)
assert len(edges) == 4
assert len(edges[0].nonzero()) == 2
node_type[edges[0].nonzero()[0]] = 0
node_type[edges[0].nonzero()[1]] = 1
node_type[edges[1].nonzero()[0]] = 1
node_type[edges[1].nonzero()[1]] = 0
node_type[edges[2].nonzero()[0]] = 0
node_type[edges[2].nonzero()[1]] = 2
node_type[edges[3].nonzero()[0]] = 2
node_type[edges[3].nonzero()[1]] = 0
print(node_type)
data.pos = torch.from_numpy(node_type)
edge_list = []
for i, edge in enumerate(edges):
edge_tmp = torch.from_numpy(
np.vstack((edge.nonzero()[0],
edge.nonzero()[1]))).type(torch.LongTensor)
edge_list.append(edge_tmp)
data.edge_index = torch.cat(edge_list, 1)
A = []
for i, edge in enumerate(edges):
edge_tmp = torch.from_numpy(
np.vstack((edge.nonzero()[0],
edge.nonzero()[1]))).type(torch.LongTensor)
value_tmp = torch.ones(edge_tmp.shape[1]).type(torch.FloatTensor)
A.append((edge_tmp, value_tmp))
edge_tmp = torch.stack(
(torch.arange(0, num_nodes),
torch.arange(0, num_nodes))).type(torch.LongTensor)
value_tmp = torch.ones(num_nodes).type(torch.FloatTensor)
A.append((edge_tmp, value_tmp))
data.adj = A
data.train_node = torch.from_numpy(np.array(labels[0])[:, 0]).type(
torch.LongTensor)
data.train_target = torch.from_numpy(np.array(labels[0])[:, 1]).type(
torch.LongTensor)
data.valid_node = torch.from_numpy(np.array(labels[1])[:, 0]).type(
torch.LongTensor)
data.valid_target = torch.from_numpy(np.array(labels[1])[:, 1]).type(
torch.LongTensor)
data.test_node = torch.from_numpy(np.array(labels[2])[:, 0]).type(
torch.LongTensor)
data.test_target = torch.from_numpy(np.array(labels[2])[:, 1]).type(
torch.LongTensor)
y = np.zeros((num_nodes), dtype=int)
x_index = torch.cat((data.train_node, data.valid_node, data.test_node))
y_index = torch.cat(
(data.train_target, data.valid_target, data.test_target))
y[x_index.numpy()] = y_index.numpy()
data.y = torch.from_numpy(y)
self.data = data
