import random
if __name__ == '__main__':

    name = './data/trec/train.txt'
    with open(name, 'r', encoding='utf-8') as f:
        lines = f.readlines()#获取所有行
        sum = 0
        list = []
        for line in lines:#第i行
            #找到第一个空格
            list.append(line)
            # for j in range(len(line)):
            #     if line[j].isspace() == True:
            #         a = line[:j]
            #         # if a not in list:
            #         list.append(a)
            #         sum += 1


    with open('./data/trec/dev.txt', 'a', encoding='utf-8') as g:
        a = random.sample(list, 500)#随机抽取500行
        for i in a:
            g.write(i)
	f.close()
	g.clost()
    print(sum)
Logo

腾讯云面向开发者汇聚海量精品云计算使用和开发经验,营造开放的云计算技术生态圈。

更多推荐