NLP学习—中文词义消歧（11）

将统计好的中文词、语义、词性依次合并到txt中

def count_char_merge(word_list, semantics_list, pos_list, wps_list):
    '''将统计好的中文词、语义、词性依次合并到txt中'''
    shuffle_char_list = []
    text_list = []

    with open(word_list, "r+", encoding="utf-8", errors='ignore') as f1:
        t1_ids = []
        lines = f1.readlines()
        for line in lines:
            text_list.append(line.strip())
            t1_id = lines.index(line)
            t1_ids.append(t1_id)
    with open(semantics_list, "r+", encoding="utf-8", errors='ignore') as f2:
        t2_ids = []
        lines = f2.readlines()
        for line in lines:
            text_list.append(line.strip())
            t2_id = lines.index(line) + int(t1_id) + 1
            t2_ids.append(t2_id)
    with open(pos_list, "r+", encoding="utf-8", errors='ignore') as f3:
        t3_ids = []
        lines = f3.readlines()
        for line in lines:
            text_list.append(line.strip())
            t3_id = lines.index(line) + int(t2_id) + 1
            t3_ids.append(t3_id)
        ids = t1_ids + t2_ids + t3_ids
        for i_d in ids:
            shuffle_char_list.append(text_list[int(i_d)])
        shuffle_char = '\n'.join(shuffle_char_list)
        with open(wps_list, "a", encoding="utf-8", errors='ignore') as f4:
            f4.write(shuffle_char)
            f4.close()


if __name__ == '__main__':
    i = '使'
    list1 = './word_count_word/{}.txt'.format(i)
    list2 = './word_count_semantics/{}.txt'.format(i)
    list3 = './word_count_pos/{}.txt'.format(i)
    list4 = './word_count_wps/{}.txt'.format(i)
    count_char_merge(list1, list2, list3, list4)

运行结果：

合并后的中文词、语义、词性：