def pre_process(self):
processed_dir = osp.join(self.root, 'processed')
pre_processed_file_path = osp.join(processed_dir, 'data_processed')
if osp.exists(pre_processed_file_path):
self.graph = torch.load(pre_processed_file_path, 'rb')
else:
### check download
has_necessary_file_simple = osp.exists(
osp.join(self.root, "raw",
"edge.csv.gz")) and (not self.is_hetero)
has_necessary_file_hetero = osp.exists(
osp.join(self.root, "raw",
"triplet-type-list.csv.gz")) and self.is_hetero
has_necessary_file = has_necessary_file_simple or has_necessary_file_hetero
if not has_necessary_file:
url = self.meta_info[self.name]["url"]
if decide_download(url):
path = download_url(url, self.original_root)
extract_zip(path, self.original_root)
os.unlink(path)
# delete folder if there exists
try:
shutil.rmtree(self.root)
except:
pass
shutil.move(
osp.join(self.original_root, self.download_name),
self.root)
else:
print("Stop download.")
exit(-1)
raw_dir = osp.join(self.root, "raw")
### pre-process and save
add_inverse_edge = self.meta_info[
self.name]["add_inverse_edge"] == "True"
if self.meta_info[self.name]["additional node files"] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info[
self.name]["additional node files"].split(',')
if self.meta_info[self.name]["additional edge files"] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info[
self.name]["additional edge files"].split(',')
if self.is_hetero:
self.graph = read_csv_heterograph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)[
0] # only a single graph
else:
self.graph = read_csv_graph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)[
0] # only a single graph
print('Saving...')
torch.save(self.graph, pre_processed_file_path, pickle_protocol=4)
def pre_process(self):
processed_dir = osp.join(self.root, 'processed')
pre_processed_file_path = osp.join(processed_dir, 'data_processed')
if osp.exists(pre_processed_file_path):
# loaded_dict = torch.load(pre_processed_file_path)
loaded_dict = load_pickle(pre_processed_file_path)
self.graph, self.labels = loaded_dict['graph'], loaded_dict[
'labels']
else:
### check download
if self.binary:
# npz format
has_necessary_file_simple = osp.exists(
osp.join(self.root, 'raw',
'data.npz')) and (not self.is_hetero)
has_necessary_file_hetero = osp.exists(
osp.join(self.root, 'raw',
'edge_index_dict.npz')) and self.is_hetero
else:
# csv file
has_necessary_file_simple = osp.exists(
osp.join(self.root, 'raw',
'edge.csv.gz')) and (not self.is_hetero)
has_necessary_file_hetero = osp.exists(
osp.join(self.root, 'raw',
'triplet-type-list.csv.gz')) and self.is_hetero
has_necessary_file = has_necessary_file_simple or has_necessary_file_hetero
if not has_necessary_file:
url = self.meta_info['url']
if decide_download(url):
path = download_url(url, self.original_root)
extract_zip(path, self.original_root)
os.unlink(path)
# delete folder if there exists
try:
shutil.rmtree(self.root)
except:
pass
shutil.move(
osp.join(self.original_root, self.download_name),
self.root)
else:
print('Stop download.')
exit(-1)
raw_dir = osp.join(self.root, 'raw')
### pre-process and save
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:
if self.binary:
self.graph = read_binary_heterograph_raw(
raw_dir, add_inverse_edge=add_inverse_edge)[
0] # only a single graph
tmp = np.load(osp.join(raw_dir, 'node-label.npz'))
self.labels = {}
for key in list(tmp.keys()):
self.labels[key] = tmp[key]
del tmp
else:
self.graph = read_csv_heterograph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)[
0] # only a single graph
self.labels = read_node_label_hetero(raw_dir)
else:
if self.binary:
self.graph = read_binary_graph_raw(
raw_dir, add_inverse_edge=add_inverse_edge)[
0] # only a single graph
self.labels = np.load(osp.join(
raw_dir, 'node-label.npz'))['node_label']
else:
self.graph = read_csv_graph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)[
0] # only a single graph
self.labels = pd.read_csv(osp.join(raw_dir,
'node-label.csv.gz'),
compression='gzip',
header=None).values
print('Saving...')
# torch.save({'graph': self.graph, 'labels': self.labels}, pre_processed_file_path, pickle_protocol=4)
dump_pickle({
'graph': self.graph,
'labels': self.labels
}, pre_processed_file_path)
def pre_process(self):
processed_dir = osp.join(self.root, 'processed')
raw_dir = osp.join(self.root, 'raw')
pre_processed_file_path = osp.join(processed_dir, 'data_processed')
if os.path.exists(pre_processed_file_path):
loaded_dict = torch.load(pre_processed_file_path, 'rb')
self.graphs, self.labels = loaded_dict['graphs'], loaded_dict[
'labels']
else:
### check download
if self.binary:
# npz format
has_necessary_file = osp.exists(
osp.join(self.root, 'raw', 'data.npz'))
else:
# csv file
has_necessary_file = osp.exists(
osp.join(self.root, 'raw', 'edge.csv.gz'))
### download
if not has_necessary_file:
url = self.meta_info['url']
if decide_download(url):
path = download_url(url, self.original_root)
extract_zip(path, self.original_root)
os.unlink(path)
# delete folder if there exists
try:
shutil.rmtree(self.root)
except:
pass
shutil.move(
osp.join(self.original_root, self.download_name),
self.root)
else:
print('Stop download.')
exit(-1)
### preprocess
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.binary:
self.graphs = read_binary_graph_raw(
raw_dir, add_inverse_edge=add_inverse_edge)
else:
self.graphs = read_csv_graph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)
if self.task_type == 'subtoken prediction':
labels_joined = pd.read_csv(osp.join(raw_dir,
'graph-label.csv.gz'),
compression='gzip',
header=None).values
# need to split each element into subtokens
self.labels = [
str(labels_joined[i][0]).split(' ')
for i in range(len(labels_joined))
]
else:
if self.binary:
self.labels = np.load(osp.join(
raw_dir, 'graph-label.npz'))['graph_label']
else:
self.labels = pd.read_csv(osp.join(raw_dir,
'graph-label.csv.gz'),
compression='gzip',
header=None).values
print('Saving...')
torch.save({
'graphs': self.graphs,
'labels': self.labels
},
pre_processed_file_path,
pickle_protocol=4)
def pre_process(self):
processed_dir = osp.join(self.root, 'processed')
raw_dir = osp.join(self.root, 'raw')
pre_processed_file_path = osp.join(processed_dir, 'data_processed')
if os.path.exists(pre_processed_file_path):
loaded_dict = torch.load(pre_processed_file_path, 'rb')
self.graphs, self.labels = loaded_dict['graphs'], loaded_dict[
'labels']
else:
### download
url = self.meta_info[self.name]["url"]
if decide_download(url):
path = download_url(url, self.original_root)
extract_zip(path, self.original_root)
os.unlink(path)
# delete folder if there exists
try:
shutil.rmtree(self.root)
except:
pass
shutil.move(osp.join(self.original_root, self.download_name),
self.root)
else:
print("Stop download.")
exit(-1)
### preprocess
add_inverse_edge = self.meta_info[
self.name]["add_inverse_edge"] == "True"
if self.meta_info[self.name]["additional node files"] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info[
self.name]["additional node files"].split(',')
if self.meta_info[self.name]["additional edge files"] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info[
self.name]["additional edge files"].split(',')
self.graphs = read_csv_graph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)
if self.task_type == 'subtoken prediction':
labels_joined = pd.read_csv(osp.join(raw_dir,
"graph-label.csv.gz"),
compression="gzip",
header=None).values
# need to split each element into subtokens
self.labels = [
str(labels_joined[i][0]).split(' ')
for i in range(len(labels_joined))
]
else:
self.labels = pd.read_csv(osp.join(raw_dir,
"graph-label.csv.gz"),
compression="gzip",
header=None).values
print('Saving...')
torch.save({
'graphs': self.graphs,
'labels': self.labels
},
pre_processed_file_path,
pickle_protocol=4)
def pre_process(self):
processed_dir = osp.join(self.root, 'processed')
pre_processed_file_path = osp.join(processed_dir, 'data_processed')
if osp.exists(pre_processed_file_path):
loaded_dict = torch.load(pre_processed_file_path)
self.graph, self.labels = loaded_dict['graph'], loaded_dict[
'labels']
else:
### check download
if not osp.exists(osp.join(self.root, "raw", "edge.csv.gz")):
url = self.meta_info[self.name]["url"]
if decide_download(url):
path = download_url(url, self.original_root)
extract_zip(path, self.original_root)
os.unlink(path)
# delete folder if there exists
try:
shutil.rmtree(self.root)
except:
pass
shutil.move(
osp.join(self.original_root, self.download_name),
self.root)
else:
print("Stop download.")
exit(-1)
raw_dir = osp.join(self.root, "raw")
### pre-process and save
add_inverse_edge = self.meta_info[
self.name]["add_inverse_edge"] == "True"
if self.meta_info[self.name]["additional node files"] == 'None':
additional_node_files = []
else:
additional_node_files = self.meta_info[
self.name]["additional node files"].split(',')
if self.meta_info[self.name]["additional edge files"] == 'None':
additional_edge_files = []
else:
additional_edge_files = self.meta_info[
self.name]["additional edge files"].split(',')
self.graph = read_csv_graph_raw(
raw_dir,
add_inverse_edge=add_inverse_edge,
additional_node_files=additional_node_files,
additional_edge_files=additional_edge_files)[
0] # only a single graph
### adding prediction target
self.labels = pd.read_csv(osp.join(raw_dir, 'node-label.csv.gz'),
compression="gzip",
header=None).values
print('Saving...')
torch.save({
'graph': self.graph,
'labels': self.labels
}, pre_processed_file_path)