文本词频统计

gzj137070928

# 文本词频统计
# HamletV1：找一个哈姆雷特的文件，保存为hamlet.txt，放在同一目录里面

1. def getText(filename):
   
2.     txt = open(filename, "r").read()
   
3.     txt = txt.lower()
   
4.     for ch in '!@#$%^&*+-()[]{}<>=_:;\\‘’"|~.':
   
5.         txt = txt.replace(ch, " ")
   
6.     return txt
   
7. 
   
8. f_name = "hamlet.txt"
   
9. hamletTxt = getText(f_name)
   
10. words = hamletTxt.split()
    
11. counts = {}
    
12. for word in words:
    
13.     # word之前没有则创建初始值为0，然后逐次加1
    
14.     counts[word] = counts.get(word, 0) + 1
    
15. items = list(counts.items())
    
16. items.sort(key=lambda x:x[1],reverse=True)
    
17. # 将出现次数最多的前十个词输出
    
18. for i in range(10):
    
19.     word, count = items[i]
    
20.     print("{0:<10}{1:>5}".format(word, count))
    

复制代码