python 学习 红楼梦字频统计 DAY17

import jieba
txt = open(r"C:\Users\lenovo\Desktop\redbuilding.txt","r",encoding="utf-8").read()
words = jieba.lcut(txt)
excludes = ["什么","一个","我们","你们","如今","说道","知道","出来","那里","起来"]
counts = {}
for word in words:
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,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))       
    


 

猜你喜欢

转载自blog.csdn.net/u011451186/article/details/81108177