西游记jieba分词前20个

由信计01创作

·西游记jieba分词代码如下：

import  jieba
excludes = {"一个","那里","怎么","我们","不知","两个","什么","不是"} 
txt = open("D:\PythonWork\Pythondaima\第六章\西游记.txt", "r", encoding='gb18030').read()
words = jieba.lcut(txt)    
counts = {}    
 
for word in words:
    if len(word) == 1:
        continue   
    elif word == "大圣" or word=="老孙" or word=="行者" or word=="孙大圣" or word=="孙行者" or word=="猴王" or word=="悟空" or word=="齐天大圣" or word=="猴子":
        rword = "孙悟空"
    elif word == "师父" or word == "三藏" or word=="圣僧":
        rword = "唐僧"
    elif word == "呆子" or word=="八戒" or word=="老猪":
        rword = "猪八戒"
    elif word=="沙和尚":
        rword="沙僧"
    elif word == "妖精" or word=="妖魔" or word=="妖道":
        rword = "妖怪"
    elif word=="佛祖":
        rword="如来"
    elif word=="三太子":
        rword="白马"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
for word in excludes:
    del(counts[word])        
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)     
for i in range(20):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))

·西游记的txt文件在上传附件里可查看

·运行后的代码显示：