jieba 分词 hamlet

def getTaxt():
    txt=open('hamlet.txt')
    txt = txt.lower()
    for ch in '!"#$%&()*+,-./:;<=>?@[\]^_‘{|}~':
        txt = txt.replace(ch, " ")   #将文本中特殊字符替换为空格
    return txt

hamletTxt = getText()
words  = hamletTxt.split()
counts = {}
for word in words:            
    counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    # print ("{0:<10}{1:>5}".format(word, count))  输出出现最多的10个单词和其出现次数
    print (word,count)  #输出出现最多的10个单词

 词云表示

import jieba
import wordcloud
import matplotlib.pyplot as plt
f = open("D:\360安全浏览器下载\hamlet.txt", "r", encoding="utf-8")#文件路经每个人都不一样，此程序可以在jupyter上运行
 
t = f.read()
f.close()
ls = jieba.lcut(t)
 
txt = " ".join(ls)
w = wordcloud.WordCloud( 
    width = 1000, height = 700,
    background_color = "pink",
    font_path = "msyh.ttc"    
    )
myword=w.generate(txt)
plt.imshow(myword)
plt.axis("off")
plt.show()
w.to_file("g.png")