文本词频统计

代码挺简单的，能够生成excel表格

import re
import jieba
import pandas as pd
import openpyxl

txt=open("C:/Users/Elegantmadman/Desktop/1.txt",'r').read()
words=jieba.lcut(txt)
count={}
sum = len(words)
for word in words:
    if len(word)==1:
        continue
    else:
        count[word]=count.get(word,0)+1
items=list(count.items())
items.sort(key=lambda x:x[-1],reverse=True)
list_word = []
list_num = []
list_sum = []
sum_count=0
for word, count  in items:
    list_word.append(word)
    list_num.append(count)
    sum_count += count
    #print("{0:<10}{1:>5}".format(word,count))
result = pd.DataFrame({'word': pd.Categorical(list_word),
                       'num':pd.Series(list_num, dtype='int'),
                       'frequency_sum':pd.Series([i/sum*100 for i in list_num] , dtype='float32'),
                       'frequency':pd.Series([i/sum_count*100 for i in list_num], dtype='float32',)})
result.to_excel('C:/Users/Elegantmadman/Desktop/6.xlsx', sheet_name='Sheet1')