聊斋相关的分词,出现次数最高的20个

import  jieba
 
txt = open("聊斋志异白话简写版.txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt)     # 使用精确模式对文本进行分词
counts = {}     # 通过键值对的形式存储词语及其出现的次数
 
for word in words:
    if len(word) == 1:
        continue   
    elif word == "小倩" or word == "鬼妻":
        rword = "聂小倩"
    elif word == "采臣":
        rword = "唐僧"
    elif word == "黑山" or word=="万妖群魔之首":
        rword = "黑山老妖"
    elif word=="十四娘":
        rword="辛十四娘"
    elif word == "子楚":
        rword = "孙子楚"
    elif word=="赵阿宝":
        rword="阿宝"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
         
items = list(counts.items())#将键值对转换成列表
items.sort(key=lambda x: x[1], reverse=True)    # 根据词语出现的次数进行从大到小排序
 
for i in range(20):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))

posted @ 2020-11-15 01:17  山自山  阅读(154)  评论(0编辑  收藏  举报