if __name__ == '__main__':
import json
import os
scr = './Smerge.json'
# 读取JSON文件
with open(scr, 'r',encoding='utf-8') as f:
data = f.readlines()
data_new = []
print(len(data))
# 在每行的末尾添加一个句号
for i in range(len(data)):
if json.loads(data[i])['paragraph'][0]['a'][0] != '':
data_new.append(data[i])
# # 将更改后的数据写回JSON文件
with open('./SSmerge.json', 'w',encoding='utf-8') as f:
for index ,line in enumerate(data_new):
# line = json.loads(line)
# line['id'] = index +1
# line = str(line)
f.write(line)
print(len(data_new))
参考上面的代码删除训练数据中output为空的数据.