1 #統計《三國誌》裏人物的出現次數
 2 
 3 import jieba
 4 text = open(‘threekingdoms.txt‘,‘r‘,encoding=‘utf-8‘).read()
 5 excludes = {‘將軍‘,‘卻說‘,‘二人‘,‘不能‘,‘如此‘,‘荊州‘,‘不可‘,‘商議‘,‘如何‘,‘軍士‘,‘左右‘,‘主公‘,‘引兵‘,‘次日‘,‘大喜‘,‘軍馬‘,
 6 ‘天下‘,‘東吳‘,‘於是‘}
 7 #返回列表類型的分詞結果
 8 words = jieba.lcut(text)
 9 #通過字典映射，統計次數
10 counts = {}
11 for
 
 word in words:
12     if len(word) == 1:
13         continue
14     elif word == ‘孔明曰‘ or word == ‘孔明‘:
15         rword = ‘諸葛亮‘
16     elif word == ‘關公‘ or word == ‘雲長‘:
17         rword = ‘關羽‘
18     elif word == ‘玄德‘ or word == ‘玄德曰‘:
19         rword = ‘劉備‘
20     elif word == ‘孟德‘ or word == ‘丞相
 
‘:
21         rword = ‘曹操‘
22     else:
23         rword = word
24     counts[rword] = counts.get(rword,0) + 1
25 for word in excludes:
26     del counts[word]
27 items = list(counts.items())
28 #排序，從大到小
29 items.sort(key=lambda x:x[1],reverse=True)
30 for i in range(5):
31     word,count = items[i]
32
 
     print(‘{0:<10}{1:>5}‘.format(word,count))

python 利用jieba庫詞頻統計