2021-04-27

##三国词云图

import matplotlib.pylab as plt
import jieba
from wordcloud import WordCloud

txt = open('threekingdoms.txt','r',encoding='utf-8').read()#读取文本文件
print(txt)
words = jieba.lcut(txt)#对读取的文本进行分词，使用 jieba.lcut()
#词频统计
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 == "诸葛亮" or word == "孔明日":
        rword = "孔明"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"
    else:
        rword = word
    counts[rword]=counts.get(rword,0)+1
#设置停用词，排除无效词
exclouds = {"将军","却说","荆州","二人","不可","不能","如此"}
for word in exclouds:
    del counts[word]
#对统计的结果按照词频进行降序排序，打印前五十个词
items = list(counts.items())
c = list()
items.sort(key = lambda x:x[1],reverse = True)
for i in range(50):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))
    c.append(word)
#生成词云图
text = " ".join(c)
font_path = 'simkai.ttf'
w = WordCloud(width=800,height=500,font_path=font_path,background_color="pink",max_words=50)#以 WordCloud 对象为基础进行操作
w.generate(text)#根据文本生成词云
w.to_file('res.png')#输出文件
#显示词云图，并保存到本地
plt.imshow(w)#用词云图片

plt.axis('off')#不显示坐标
plt.show()#显示生成的词云图
w.to_file("threekingdoms.png") #保存到本地

代码是借鉴大神的，请看结果……


这是上实验课，雯姐姐帮我弄出来得，多谢大神指点！