python 利用jieba库词频统计

#统计《三国志》里人物的出现次数

import jieba
text = open('threekingdoms.txt','r',encoding='utf-8').read()
excludes = {'将军','却说','二人','不能','如此','荆州','不可','商议','如何','军士','左右','主公','引兵','次日','大喜','军马',
'天下','东吴','于是'}
#返回列表类型的分词结果
words = jieba.lcut(text)
#通过字典映射，统计次数
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == '孔明曰' or word == '孔明':
        rword = '诸葛亮'
    elif word == '关公' or word == '云长':
        rword = '关羽'
    elif word == '玄德' or word == '玄德曰':
        rword = '刘备'
    elif word == '孟德' or word == '丞相':
        rword = '曹操'
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
for word in excludes:
    del counts[word]
items = list(counts.items())
#排序，从大到小
items.sort(key=lambda x:x[1],reverse=True)
for i in range(5):
    word,count = items[i]
    print('{0:<10}{1:>5}'.format(word,count))