python三国演义人物出场统计

完整代码

开源代码

统计三国演义人物高频次数

#!/usr/bin/env python
# coding=utf-8
#e10.4CalThreeKingdoms.py
import jieba
excludes = {"来到","人马","领兵","将军","却说","荆州","二人","不可","不能","如此"}
txt = open("threekingdom.txt", "rb").read()
words  = jieba.lcut(txt)
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) 
for i in range(55):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

代码运行：人物频率统计

threekingdom.txt  kingdom.py
kou@ubuntu:~/python/file_文本处理$ python3 kingdom.py 
Building prefix dict from the default dictionary ...
Dumping model to file cache /tmp/jieba.cache
Loading model cost 2.446 seconds.
Prefix dict has been built succesfully.
曹操         1348
刘备         1144
孔明          865
关羽          557
吕布          322
张飞          300

词云图片

#!/usr/bin/env python
# coding=utf-8

import jieba
import wordcloud

f = open("threekingdom.txt","rb")
t = f.read()
f.close()
ls = jieba.lcut(t)
txt = " ".join(ls)
w = wordcloud.WordCloud(    font_path = "NotoSerifCJK-Bold.ttc",\
                        width = 1000,height = 700,background_color = "white",\
                       )

w.generate(txt)
w.to_file("gr.png")

代码运行