NLP学习—中文词义消歧（3）

为每个中文句子添加语义类别，标签为数字形式，从1开始编号

import os


def add_type_label(from_list, to_list):
    '''为每个中文句子添加语义类别，标签为数字形式，从1开始编号'''
    From_Path = from_list
    To_Path = to_list
    label = 1
    for file_path in os.listdir(From_Path):
        Path1 = From_Path + '/%s'
        Path2 = To_Path + '/%s.txt'
        with open(Path1 % file_path, "r+", encoding="utf-8", errors='ignore') as P1:
            lines = P1.readlines()
            for line in lines:
                line = line.replace('\n', '')
                with open(Path2 % file_path[:file_path.find('.txt')], "a+", encoding="utf-8", errors='ignore') as P2:
                    P2.write(line + str(label) + '\n')
            label = label + 1


if __name__ == '__main__':
    i = '使'
    list1 = './word/{}'.format(i)
    list2 = './word_label/{}'.format(i)
    add_type_label(list1, list2)

运行结果：

中文句子数据：

处理后的结果：