1 # 如果您需要使用此代码，os.chdir路经需要指定到txt文本所在路径
  2 # 使用Zipin函数，需要txt有read()函数可以打开的正确的编码格式
  3 # 使用Cipin函数需要安装jieba库
  4 # 使用word cloud函数需要安装wordcloud与matplotlib库
  5 import os
  6 import codecs
  7 import jieba
  8 import pandas as pd
  9 from wordcloud import WordCloud
 10 from scipy.misc import imread
 11 import matplotlib.pyplot as plt
 12 os.chdir("/Users/Zhaohaibo/Desktop")
 13 
 14 class Hlm(object): 
 15 
 16     # —————————————————————
 17     # Zipin(self, readdoc, writedoc)
 18     # readdoc: 要读取的文件名
 19     # writedoc:要写入的文件名
 20 
 21     # output
 22     # 字频前100，并写入writedoc
 23     # —————————————————————
 24     def Zipin(self, readdoc, writedoc):
 25         word_lst = []
 26         word_dict = {}       
 27         exclude_str = "，。！？、（）【】<>《》=：+-*—“”…" 
 28         with open(readdoc,"r") as fileIn ,open(writedoc,‘w‘) as fileOut:
 29 
 30             # 添加每一个字到列表中
 31             for line in fileIn:
 32                 for char in line:
 33                     word_lst.append(char)
 34 
 35             # 用字典统计每个字出现的个数       
 36             for char in word_lst:
 37                 if char not in exclude_str:
 38                     if char.strip() not in word_dict: # strip去除各种空白
 39                         word_dict[char] = 1
 40                     else :
 41                         word_dict[char] += 1
 42 
 43             # 排序x[1]是按字频排序，x[0]则是按字排序
 44             lstWords = sorted(word_dict.items(), key=lambda x:x[1],  reverse=True) 
 45 
 46             # 输出结果 (前100)
 47             print (‘字符\t字频‘)
 48             print (‘=============‘)
 49             for e in lstWords[:100]:
 50                 print (‘%s\t%d‘ % e)
 51                 fileOut.write(‘%s, %d\n‘ % e)
 52 
 53 
 54     # —————————————————————
 55     # Cipin(self, doc)
 56     # doc: 要读取的文件名
 57 
 58     # return:
 59     # 词频表（DataFrame格式）
 60     # —————————————————————
 61     def Cipin(self, doc):
 62         wdict = {}
 63         f = open(doc,"r")
 64         for line in f.readlines():
 65             words = jieba.cut(line)
 66             for w in words:
 67                 if(w not in wdict):
 68                     wdict[w] = 1
 69                 else:
 70                     wdict[w] += 1                
 71         # 导入停用词表
 72         stop = pd.read_csv(‘stoplist.txt‘, encoding = ‘utf-8‘, sep = ‘zhao‘, header = None,engine = ‘python‘) #sep:分割符号（需要用一个确定不会出现在停用词表中的单词）
 73         stop.columns = [‘word‘]    
 74         stop = [‘ ‘] + list(stop.word) #python读取时不会读取到空格。但空格依旧需要去除。所以加上空格； 读取后的stop是series的结构，需要转成列表
 75         for i in range(len(stop)):
 76             if(stop[i] in wdict):
 77                 wdict.pop(stop[i])
 78 
 79         ind = list(wdict.keys())
 80         val = list(wdict.values())
 81         ind = pd.Series(ind)
 82         val = pd.Series(val)
 83         data =  pd.DataFrame()
 84         data[‘词‘] = ind
 85         data[‘词频‘] = val
 86         return data
 87 
 88     # —————————————————————
 89     # Ciyun(self, doc)
 90     # doc: 要读取的文件名
 91 
 92     # output: 
 93     # 词云图
 94     # —————————————————————
 95     def Ciyun(self,doc):
 96         g = open(doc,"r").read()
 97         back_pic = imread("aixin.jpg")  # 设置背景图片  
 98         wc = WordCloud( font_path=‘/System/Library/Fonts/STHeiti Medium.ttc‘,#设置字体  
 99                           background_color="white", #背景颜色  
100                           max_words=2000,# 词云显示的最大词数  
101                           mask=back_pic,#设置背景图片  
102                           max_font_size=200, #字体最大值  
103                           random_state=42,  
104                          ).generate(g)   
105         plt.figure(figsize=(64,32))
106         plt.imshow(wc)
107         plt.axis(‘off‘)
108         plt.savefig("ciyun.jpg")
109         plt.show()
110 
111 
112     def main(self,readdoc):
113         # self.Zipin(readdoc,writedoc)
114         df = self.Cipin(readdoc)
115         #self.Ciyun(readdoc)
116         return df
117 
118 
119 if __name__ == ‘__main__‘:
120     hlm = Hlm()
121     hlm.Zipin("红楼梦.txt","红楼梦字频.txt")
122     df_hlm1 = hlm.main("红楼梦.txt")
123 --------------------- 
124 作者：Iovebecky 
125 来源：CSDN 
126 原文：https://blog.csdn.net/zhaohaibo_/article/details/81902456 
127 版权声明：本文为博主原创文章，转载请附上博文链接！