三国演义词频统计

import jieba
txt=open(“threekingdoms2.txt”,“r”,encoding=“utf-8”).read()
excludes = {‘将军’,‘却说’,‘荆州’,‘二人’,‘不可’,‘不能’,‘如此’}#错误的名字
words = jieba.lcut(txt)#jieba库自动分词
print(words)
counts = {}
for word in words:
if len(word) ==1:
continue
elif word == ‘诸葛亮’ or word == ‘孔明曰’:
rword = ‘孔明’
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())
items.sort(key=lambda x:x[1],reverse=True)
print(items)
for i in range(10):
word,count = items[i]
print(’{0:<10}{1:>5}’.format(word,count))
以上源于Mooc python程序设计课堂实例

关于文件编码格式，“utf-8”若是运行错误，可以直接另存为 修改文件文件编码格式