python实现中文分词和词频统计-ag真人游戏

python2.7中实现中文分词，是引入了jieba中文分词库。再进行简单的词频统计。

import sys  
reload(sys)  
  
sys.setdefaultencoding('utf-8')  
  
import jieba  
import jieba.analyse  
import xlwt #写入excel表的库  
  
if __name__=="__main__":  
  
    wbk = xlwt.workbook(encoding = 'ascii')  
    sheet = wbk.add_sheet("wordcount")#excel单元格名字  
    word_lst = []  
    key_list=[]  
    for line in open('test.txt'):#test.txt是需要分词统计的文档  
  
        item = line.strip('\n\r').split('\t') #制表格切分  
        # print item  
        tags = jieba.analyse.extract_tags(item[0]) #jieba分词  
        for t in tags:  
            word_lst.append(t)  
  
    word_dict= {}  
    with open("wordcount.txt",'w') as wf2: #打开文件  
  
        for item in word_lst:  
            if item not in word_dict: #统计数量  
                word_dict[item] = 1  
            else:  
                word_dict[item]  = 1  
  
        orderlist=list(word_dict.values())  
        orderlist.sort(reverse=true)  
        # print orderlist  
        for i in range(len(orderlist)):  
            for key in word_dict:  
                if word_dict[key]==orderlist[i]:  
                    wf2.write(key ' ' str(word_dict[key]) '\n') #写入txt文档  
                    key_list.append(key)  
                    word_dict[key]=0  
      
      
    for i in range(len(key_list)):  
        sheet.write(i, 1, label = orderlist[i])  
        sheet.write(i, 0, label = key_list[i])  
    wbk.save('wordcount.xls') #保存为 wordcount.xls文件 

得到分词结果：