文本词频统计2

gzj137070928

# 文本词频统计2
# threekingdomsV1：找一个三国演义的文件，保存为threekingdoms.txt，放在同一目录里面
# 记录输出出现次数最多的前十五个人物名输出

1. import jieba
   
2. 
   
3. filename = "threekingdoms.txt"
   
4. txt = open(filename, "r", encoding="utf-8").read()
   
5. words = jieba.lcut(txt)
   
6. counts = {}
   
7. for word in words:
   
8.     if len(word)==1:
   
9.         continue
   
10.     else:
    
11.         counts[word] = counts.get(word, 0) + 1
    
12. items = list(counts.items())
    
13. items.sort(key=lambda x:x[1],reverse=True)
    
14. # 将出现次数最多的前十五个人物名输出
    
15. for i in range(15):
    
16.     word, count = items[i]
    
17.     print("{0:<10}{1:>5}".format(word, count))
    

复制代码