You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
29 lines
733 B
29 lines
733 B
3 months ago
|
import jieba
|
||
|
|
import pandas
|
||
|
|
import openpyxl
|
||
|
|
#1.读取弹幕数据
|
||
|
|
f =open("总弹幕.txt",encoding='utf-8')
|
||
|
|
text =f.read()
|
||
|
|
|
||
|
|
#2.分词
|
||
|
|
text_list=jieba.lcut(text)
|
||
|
|
|
||
|
|
#3.去除标点符号（常见词）
|
||
|
|
f2=open('标点符号表.text',encoding='utf-8')
|
||
|
|
stopwords=f2.read()
|
||
|
|
text_clean=[word for word in text_list if word not in stopwords]
|
||
|
|
|
||
|
|
#4.生成词频字典
|
||
|
|
d_sict={}
|
||
|
|
for key in text_clean:
|
||
|
|
d_sict[key]=d_sict.get(key,0)+1
|
||
|
|
|
||
|
|
#5.获取字典的键和值作为excel的两个列表变量
|
||
|
|
key=list(d_sict.keys())
|
||
|
|
value=list(d_sict.values())
|
||
|
|
|
||
|
|
#6.写入excel表
|
||
|
|
result_excel=pandas.DataFrame()
|
||
|
|
result_excel["词"]=key
|
||
|
|
result_excel["词频"]=value
|
||
|
|
result_excel.to_excel('词频统计（去标点符号）.xlsx')
|