perform pandas aggregation whiles keeping the date column intact

Question

user = {\'id\':[\'abab23\', \'abab21\', \'abab22\', \'abab25\', \'abab24\', \'abab30\', \'abab252\', \'abab15\'],
        \'dob\':[\'10-10-1990\',\'1-12-1993\', \'12-12-         


        

Answer 1

Try this:

activities = {'sentconn':['abab35', 'abab15', 'abab25', 'abab23','abab22', 'abab15'],
             'receiveconn': ['abab24', 'abab24', 'abab21', 'abab35', 'abab252', 'abab30'],
              'sentdate':['2-10-2020', '2-10-2020','4-10-2020', '5-10-2020', '10-10-2020', '11-10-2020'],
               'receivedDate':['2-10-2020', '2-10-2020','4-10-2020', '5-10-2020', '10-10-2020', '11-10-2020']}

user = {'id':['abab23', 'abab21', 'abab22', 'abab25', 'abab24', 'abab30', 'abab252', 'abab15'],
        'dob':['10-10-1990','1-12-1993', '12-12-2000', '2-10-1999', '2-10-1999', '2-10-1999', '2-10-1999', '2-10-1999']}

usr_df = pd.DataFrame(user)
df = pd.DataFrame(activities)

#group by the required columns to get the count.
df1 = df.groupby(['sentdate','sentconn']).agg({'sentconn':'count'})
df2 = df.groupby(['receivedDate','receiveconn']).agg({'receiveconn':'count'})

#rename the axis so that you get common columns to concat
df1 = df1.rename_axis(['date','user'])
df2 = df2.rename_axis(['date','user'])

df = pd.concat([df1, df2],axis=1)\
        .fillna(0)\
        .reset_index()
#filter the user id not present is user df as required.
df = df.loc[df['user'].isin(usr_df['id'])]\
        .set_index(['date','user'])
print(df)

outputs:

                   sentconn  receiveconn
date       user                          
10-10-2020 abab22        1.0          0.0
           abab252       0.0          1.0
11-10-2020 abab15        1.0          0.0
           abab30        0.0          1.0
2-10-2020  abab15        1.0          0.0
           abab24        0.0          2.0
4-10-2020  abab21        0.0          1.0
           abab25        1.0          0.0
5-10-2020  abab23        1.0          0.0