批量读取文件夹下的文件+数据合并+韦恩图

批量读取

import pandas as pd
from functools import reduce
import os

# 被下线过的id
data1 = pd.read_csv('/Users/bella/Downloads/20210125_video_offline_userid_uniq.txt',header=None)
data2 = pd.read_csv('/Users/bella/Downloads/20210127_video_offline_userid_uniq.txt',header=None)
data3 = pd.read_csv('/Users/bella/Downloads/20210201_video_offline_userid_uniq.txt',header=None)
data4 = pd.read_csv('/Users/bella/Downloads/20210205_videooffline_userid_uniq.txt',header=None)
data5 = pd.read_csv('/Users/bella/Downloads/20210209_video_offline_userid_uniq.txt',header=None)
# 或者，把上述文件放到一个文件夹，读取该文件夹就行
dfs = [data1,data2,data3,data4,data5]
offline = pd.concat(dfs,axis=0)
offline = offline.rename(columns={0:'offline_user_id'})
offline.head()

ups = pd.DataFrame(columns=['date','user_id'])
test = pd.DataFrame(columns=['date','user_id'])

dir = '/Users/bella/Downloads/20210120_20210213_video_publisher'
for info in os.listdir(dir):
    test = pd.read_csv(dir+'/'+info)
    test['date'] = info[:8]
    ups = pd.concat([test,ups],sort=False)
    #print(ups.shape)

韦恩图

from matplotlib_venn import venn2, venn2_circles
up_num = ups_all.shape[0] # 全部up的数量
offline_num = offline.shape[0] 
inner = inner_df.shape[0]
venn2(subsets=(up_num,offline_num,inner), set_labels=('0120~0213 Ups', '0125~0209 offline'))