未验证 提交 aeee367c 编写于 作者: K Kennycao123 提交者: GitHub

Update data_aug.py

上级 c9a87f24
...@@ -288,27 +288,26 @@ if __name__ == "__main__": ...@@ -288,27 +288,26 @@ if __name__ == "__main__":
if six.PY3: if six.PY3:
with open(input_file_path, encoding='UTF-8') as input_file: with open(input_file_path, 'r', encoding='UTF-8') as input_file:
with open(input_file_path) as input_file: with open(output_file_path, 'w', encoding='UTF-8') as output_file:
with open(output_file_path, 'w') as output_file: for i, l in enumerate(input_file.readlines()):
for i, l in enumerate(input_file.readlines()): parser = choose_parser()
parser = choose_parser() #print(parser.__name__ == "pos_replace_parser")
#print(parser.__name__ == "pos_replace_parser") if i % 1000 == 0:
if i % 1000 == 0: log.debug('parsing line %d' % i)
log.debug('parsing line %d' % i) print(l.strip(), file=output_file)
print(l.strip(), file=output_file)
for k in range(args.aug_times):
for k in range(args.aug_times): cols = l.strip().split('\t')
cols = l.strip().split('\t') for j in col_nums:
for j in col_nums: if parser.__name__ == "pos_replace_parser":
if parser.__name__ == "pos_replace_parser": cols[j - 1] = parser(cols[j - 1], pos_dict[j - 1])
cols[j - 1] = parser(cols[j - 1], pos_dict[j - 1]) counter[parser.__name__] += 1
counter[parser.__name__] += 1 else:
else: cols[j - 1] = parser(cols[j - 1])
cols[j - 1] = parser(cols[j - 1]) counter[parser.__name__] += 1
counter[parser.__name__] += 1 new_line = '\t'.join(cols)
new_line = '\t'.join(cols) print(new_line, file=output_file)
print(new_line, file=output_file)
elif six.PY2: elif six.PY2:
with open(input_file_path) as input_file: with open(input_file_path) as input_file:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册