版权声明:本文为博主原创文章,但部分内容来源自互联网,大家可以随意转载,点赞或留言均可! https://blog.csdn.net/csdn_kou/article/details/83962302
统计哈姆雷特文本中高频词的个数
kou@ubuntu:~/python$ cat ClaHamlet.py
#!/usr/bin/env python
# coding=utf-8
#e10.1CalHamlet.py
def getText():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
txt = txt.replace(ch, " ") #将文本中特殊字符替换为空格
return txt
hamletTxt = getText()
words = hamletTxt.split()
counts = {}
for word in words:
counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
word, count = items[i]
print ("{0:<10}{1:>5}".format(word, count))