In [23]:

    

import pandas as pd


    

In [31]:

    

dir_ship_info = "./dataset/shop_info.txt"
dir_user_pay = "./dataset/user_pay.txt"
dir_user_view = "./dataset/user_view.txt"
shop_info = pd.read_csv(dir_ship_info, sep=',', names=["shop_id","city_name","location_id","per_pay","score","comment_cnt","shop_level","cate_1_name","cate_2_name","cate_3_name"])
user_pay = pd.read_csv(dir_user_pay, sep=",", names=["user_id","shop_id","time_stamp"])
user_view = pd.read_csv(dir_user_view, sep=",", names=["user_id","shop_id","time_stamp"])


# dir_ouput= "./result.txt"
# output=pd.DataFrame()
# output.to_csv(dir_ouput, sep=",", names= ["shop_id","day1","..."])


    

In [25]:

    

shop_info.head()


    

    
Out[25]:






  

    

      

      
shop_id
      
city_name
      
location_id
      
per_pay
      
score
      
comment_cnt
      
shop_level
      
cate_1_name
      
cate_2_name
      
cate_3_name
    
  
  

    

      
0
      
1
      
湖州
      
885
      
8
      
4.0
      
12.0
      
2
      
美食
      
休闲茶饮
      
饮品/甜点
    
    

      
1
      
2
      
哈尔滨
      
64
      
19
      
NaN
      
NaN
      
1
      
超市便利店
      
超市
      
NaN
    
    

      
2
      
3
      
南昌
      
774
      
5
      
3.0
      
2.0
      
0
      
美食
      
休闲茶饮
      
奶茶
    
    

      
3
      
4
      
天津
      
380
      
18
      
NaN
      
NaN
      
1
      
超市便利店
      
超市
      
NaN
    
    

      
4
      
5
      
杭州
      
263
      
2
      
2.0
      
2.0
      
0
      
美食
      
休闲食品
      
生鲜水果
    
  

In [29]:

    

user_pay.head()


    

    
Out[29]:






  

    

      

      
user_id
      
shop_id
      
time_stamp
    
  
  

    

      
0
      
22127870
      
1862
      
2015-12-25 17:00:00
    
    

      
1
      
3434231
      
1862
      
2016-10-05 11:00:00
    
    

      
2
      
16955285
      
1862
      
2016-02-10 15:00:00
    
    

      
3
      
13799128
      
1862
      
2016-01-13 14:00:00
    
    

      
4
      
13799128
      
1862
      
2016-07-05 12:00:00
    
  

In [27]:

    

user_view.head()


    

    
Out[27]:






  

    

      

      
user_id
      
shop_id
      
time_stamp
    
  
  

    

      
0
      
13201967
      
1197
      
2016-10-21 18:00:00
    
    

      
1
      
19461365
      
1197
      
2016-06-28 23:00:00
    
    

      
2
      
15022321
      
1197
      
2016-07-16 19:00:00
    
    

      
3
      
5440872
      
1197
      
2016-07-15 07:00:00
    
    

      
4
      
12594529
      
1197
      
2016-08-07 16:00:00
    
  

In [ ]: