結巴中文詞頻分析

 

 

結果保存在result.txt文檔內

# -*- coding: utf-8 -*-


import jieba
import sys
from collections import Counter
import jieba.analyse
filename="招聘分析.txt"

def fenci(filename) :
    f = open(filename,'r+')
    file_list = f.read()
    f.close()

    seg_list = list(jieba.cut(file_list,cut_all=True))
    tf={}
    for seg in seg_list :
        #print seg
        seg = ''.join(seg.split())
        if (seg != '' and seg != "\n" and seg != "\n\n") :
            if seg in tf :
                tf[seg] += 1
            else :
                tf[seg] = 1

    f = open("result.txt","w+")
    for item in tf:
        #print item
        f.write(item+"  "+str(tf[item])+"\n")
    f.close()


fenci(filename)

 

https://study.163.com/provider/400000000398149/index.htm?share=2&shareId=400000000398149（博主視頻教學主頁）