Python可视化词云图

    print(dir(函数))

    os.getcwd()

    os.chdir('要去的路径')

    WordCloud.generate(txt)

    plt.imshow('变量')

    plt.show()

    plt.axis('on/off')

 from wordcloud import WordCloud

    
 text=open('China145.txt','r').read()

    pip install wordcloud

 import os

    
 os.chdir('txt文件所在路径')
    
 print(os.getcwd())

    SyntaxError: (unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: truncated \UXXXXXXXX escape

 import matplotlib.pyplot as plt

    
 from wordcloud import WordCloud
    
 text=open('txt文件名','r',encoding='utf-8').read()
    
 w=WordCloud().generate(text)
    
 plt.imshow(w)
    
 plt.show()

 w=WordCloud(font_path=font).generate(text)

    
 font='找到系统自带的字体的路径，选择要用的字体名并加上后缀'
    
 （例如：'c:\Windows\Fonts\AdobeHeitiStd-Regular.otf'）

 import jieba

    
 words = "他来到了网易大厦。"
    
  
    
 print("/".join(jieba.cut(words)))    # 精简模式，返回一个列表类型的结果
    
 print("/".join(jieba.cut(words, cut_all=True)))      # 全模式，使用 'cut_all=True' 指定
    
 print("/".join(jieba.cut(words, cut_all=False)))      #精确模式
    
 print("/".join(jieba.cut_for_search(words)))     # 搜索引擎模式

 import jieba.possey as pseg

    
 words=pseg.cut('中国国家领导人在开会')
    
 for key in words:
    
     print(key.word,key.flag)

 import jieba

    
 with open('文件名','r') as f:
    
      renmin=f.read()
    
  
    
 jieba.load_userdict('本地词典')
    
 seg_list=jieba.cut(renmin.cut_all=False) #精确分词
    
  
    
 tf={}
    
 for seg in seg_list:
    
     if seg in tf:
    
       tf[seg]+=1
    
     else:
    
       tf[seg]=1     #将分词表放入字典里计数
    
 ci=list(tf.keys())
    
 print(len(ci))

 with open('停用词表','r',encoding='utf-8') as ft:

    
     stopword=ft.read()
    
 for seg in ci:
    
     if 不要词的条件1 or 不要词的条件2:
    
      tf.pop(seg)
    
 print(tf)
    
 print(len(tf))

 ci,num,data=list(tf.keys()),list(tf.values()),[]

    
 for i in range(len(tf)):
    
     data.append((num[i],ci[i]))
    
 data.sort()  #sort()默认按升序排列，若按降序，括号里加上reverse=False
    
 tf_sorted={}
    
 for i in range(len(data)):
    
     tf_sorted[data[i][1]]=data[i][0]
    
 print(tf_sorted)