中文词频统计及词云制作

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

f0 = open(‘全职法师.txt‘,‘r‘,encoding=‘utf-8‘)
qz = f0.read()
f0.close()

words = list(jieba.cut(qz))

ul={‘那个‘, ‘但‘, ‘整个‘, ‘控‘,‘跟‘,‘再‘, ‘我们‘,‘个‘,‘看‘,‘没‘,‘们‘, ‘对‘,    ‘怎么‘, ‘能够‘,‘颗‘,‘他们‘, ‘你们‘,‘知道‘, ‘什么‘,‘把‘, ‘一个‘,‘吧‘,‘系‘,    ‘她‘,‘没有‘,‘已经‘,‘就是‘,‘可以‘,‘被‘,‘说‘,‘这个‘,‘得‘,‘给‘,‘还‘, ‘说道‘,    ‘去‘,‘下‘, ‘上‘,‘好‘,‘里‘,‘会‘,‘要‘,‘到‘,‘和‘,‘让‘,‘不‘,‘那‘, ‘啊‘,‘很‘,    ‘有‘,‘着‘,‘都‘,‘在‘, ‘这‘,‘的‘,‘了‘,‘是‘,‘就‘,‘我‘,‘也‘,‘他‘,‘你‘,‘、‘,‘”‘    ,‘“‘,‘。‘,‘！‘,‘？‘,‘ ‘,‘\u3000‘,‘，‘,‘\n‘}
dic={}

keys = set(words)-ul
for i in keys:
    dic[i]=words.count(i)

c = list(dic.items())
c.sort(key=lambda x:x[1],reverse=True)

f1 = open(‘词云.txt‘,‘w‘)
for i in range(20):
    print(c[i])
    for words_count in range(c[i][1]):
        f1.write(c[i][0]+‘ ‘)
f1.close()

f3 = open(‘词云.txt‘,‘r‘)
cy_file = f3.read()
f3.close()
cy = WordCloud().generate(cy_file)
plt.imshow(cy)
plt.axis("off")
plt.show()