def process(self):
add_inverse_edge = self.meta_info['add_inverse_edge'] == 'True'
if self.meta_info['additional node files'] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info[
'additional node files'].split(',')
if self.meta_info['additional edge files'] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info[
'additional edge files'].split(',')
if self.is_hetero:
data = read_heterograph_pyg(
self.raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files,
binary=self.binary)[0]
else:
data = read_graph_pyg(self.raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files,
binary=self.binary)[0]
data = data if self.pre_transform is None else self.pre_transform(data)
print('Saving...')
torch.save(self.collate([data]), self.processed_paths[0])
def process(self):
### read pyg graph list
add_inverse_edge = self.meta_info['add_inverse_edge'] == 'True'
if self.meta_info['additional node files'] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info['additional node files'].split(',')
if self.meta_info['additional edge files'] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info['additional edge files'].split(',')
data_list = read_graph_pyg(self.raw_dir, add_inverse_edge = add_inverse_edge, additional_node_files = additional_node_files, additional_edge_files = additional_edge_files, binary=self.binary)
if self.task_type == 'subtoken prediction':
graph_label_notparsed = pd.read_csv(osp.join(self.raw_dir, 'graph-label.csv.gz'), compression='gzip', header = None).values
graph_label = [str(graph_label_notparsed[i][0]).split(' ') for i in range(len(graph_label_notparsed))]
for i, g in enumerate(data_list):
g.y = graph_label[i]
else:
if self.binary:
graph_label = np.load(osp.join(self.raw_dir, 'graph-label.npz'))['graph_label']
else:
graph_label = pd.read_csv(osp.join(self.raw_dir, 'graph-label.csv.gz'), compression='gzip', header = None).values
has_nan = np.isnan(graph_label).any()
for i, g in enumerate(data_list):
if 'classification' in self.task_type:
if has_nan:
g.y = torch.from_numpy(graph_label[i]).view(1,-1).to(torch.float32)
else:
g.y = torch.from_numpy(graph_label[i]).view(1,-1).to(torch.long)
else:
g.y = torch.from_numpy(graph_label[i]).view(1,-1).to(torch.float32)
if self.pre_transform is not None:
data_list = [self.pre_transform(data) for data in data_list]
data, slices = self.collate(data_list)
print('Saving...')
torch.save((data, slices), self.processed_paths[0])
def process(self):
add_inverse_edge = self.meta_info['add_inverse_edge'] == 'True'
if self.meta_info['additional node files'] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info[
'additional node files'].split(',')
if self.meta_info['additional edge files'] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info[
'additional edge files'].split(',')
if self.is_hetero:
data = read_heterograph_pyg(
self.raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files,
binary=self.binary)[0]
if self.binary:
tmp = np.load(osp.join(self.raw_dir, 'node-label.npz'))
node_label_dict = {}
for key in list(tmp.keys()):
node_label_dict[key] = tmp[key]
del tmp
else:
node_label_dict = read_node_label_hetero(self.raw_dir)
data.y_dict = {}
if 'classification' in self.task_type:
for nodetype, node_label in node_label_dict.items():
# detect if there is any nan
if np.isnan(node_label).any():
data.y_dict[nodetype] = torch.from_numpy(
node_label).to(torch.float32)
else:
data.y_dict[nodetype] = torch.from_numpy(
node_label).to(torch.long)
else:
for nodetype, node_label in node_label_dict.items():
data.y_dict[nodetype] = torch.from_numpy(node_label).to(
torch.float32)
else:
data = read_graph_pyg(self.raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files,
binary=self.binary)[0]
### adding prediction target
if self.binary:
node_label = np.load(osp.join(self.raw_dir,
'node-label.npz'))['node_label']
else:
node_label = pd.read_csv(osp.join(self.raw_dir,
'node-label.csv.gz'),
compression='gzip',
header=None).values
if 'classification' in self.task_type:
# detect if there is any nan
if np.isnan(node_label).any():
data.y = torch.from_numpy(node_label).to(torch.float32)
else:
data.y = torch.from_numpy(node_label).to(torch.long)
else:
data.y = torch.from_numpy(node_label).to(torch.float32)
data = data if self.pre_transform is None else self.pre_transform(data)
print('Saving...')
torch.save(self.collate([data]), self.processed_paths[0])
def process(self):
from ogb.io.read_graph_pyg import read_graph_pyg
### read pyg graph list
add_inverse_edge = self.meta_info['add_inverse_edge'] == 'True'
if self.meta_info['additional node files'] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info[
'additional node files'].split(',')
if self.meta_info['additional edge files'] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info[
'additional edge files'].split(',')
data_list = read_graph_pyg(self.raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files,
binary=self.binary)
if self.task_type == 'subtoken prediction':
graph_label_notparsed = pd.read_csv(os.path.join(
self.raw_dir, 'graph-label.csv.gz'),
compression='gzip',
header=None).values
graph_label = [
str(graph_label_notparsed[i][0]).split(' ')
for i in range(len(graph_label_notparsed))
]
for i, g in enumerate(data_list):
g.y = graph_label[i]
else:
if self.binary:
graph_label = np.load(
os.path.join(self.raw_dir,
'graph-label.npz'))['graph_label']
else:
graph_label = pd.read_csv(os.path.join(self.raw_dir,
'graph-label.csv.gz'),
compression='gzip',
header=None).values
has_nan = np.isnan(graph_label).any()
for i, g in enumerate(data_list):
if 'classification' in self.task_type:
if has_nan:
g.y = torch.from_numpy(graph_label[i]).view(1, -1).to(
torch.float32)
else:
g.y = torch.from_numpy(graph_label[i]).view(1, -1).to(
torch.long)
else:
g.y = torch.from_numpy(graph_label[i]).view(1, -1).to(
torch.float32)
if self.pre_transform is not None:
dataset = self.collate(data_list)
data_list = _process_dataset_pretransform_torch(
self.pre_transform, TensorSliceDataset(*dataset))
dataset = self.collate(data_list)
np.savez(self.processed_paths[0], **_dataset_to_dict(dataset))
