【统计词频】python+excel +jieba

https://www.cnblogs.com/WeyneChen/p/6675355.html 参考：

python简单词频统计——简单统计一个小说中哪些个汉字出现的频率最高

参考：https://www.cnblogs.com/jiayongji/p/7119065.html | 

好玩的分词——python jieba分词模块的基本用法

-------------------------------------------------------------------------------------

>>> import jieba
>>> from collections import Counter
>>> santi_text = open('E:/西方哲学史.txt').read()

>>> santi_words = [x for x in jieba.cut(santi_text) if len(x) >= 2]
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\oil\AppData\Local\Temp\jieba.cache
Loading model cost 0.882 seconds.
Prefix dict has been built succesfully.
>>> c = Counter(santi_words).most_common(20)
>>> print(c)
[('他们', 51), ('哲学', 48), ('一种', 46), ('一个', 43), ('对于', 34), ('教会', 25), ('我们', 25), ('哲学家', 24), ('如 果', 24), ('这种', 24), ('时代', 21), ('就是', 21), ('世纪', 20), ('但是', 20), ('任何', 20), ('社会', 19), ('方面', 17), ('这些', 16), ('罗马', 16), ('没有', 16)]

>>>

----------------------------------------------------------------------------------

参考文章：python jieba分词并统计词频后输出结果到Excel和txt文档 

----------------------------------------------------------------------------------

>>> import jieba
>>> import jieba.analyse
>>> import xlwt
>>>

>>> 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('E:/西方哲学史.txt'):
...     item = line.strip('\n\r').split('\t')
...     tags = jieba.analyse.extract_tags(item[0])
...     for t in tags:
...       word_lst.append(t)
...   word_dict= {}
...   with open("E:/wordCount.txt",'w') as wf2:
...     for item in word_lst:
...       if item not in word_dict:
...         word_dict[item] = 1
...       else:
...         word_dict[item] += 1
...     orderList=list(word_dict.values())
...     orderList.sort(reverse=True)
...     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')
...            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')
...
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\oil\AppData\Local\Temp\jieba.cache
Loading model cost 1.548 seconds.

Prefix dict has been built succesfully.

#!/usr/bin/python  
# -*- coding:utf-8 -*-  

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('1.txt'):#1.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

---------------------------------------------------------------------------------------------