[Pandas][DataFrame][concat]S3_02_concatenation_with_multi_indexing

 

 

 

In [1]:

import pandas as pd

 

In [2]:

raw_data = {'Bank Client ID': ['1', '2', '3', '4', '5'],
            'First Name': ['Robert', 'Benedict', 'Mark', 'Tom', 'Ryan'], 
            'Last Name': ['Downey', 'Cumberbatch', 'Ruffalo', 'Holland', 'Reynolds']}

bank1_df = pd.DataFrame(raw_data, columns = ['Bank Client ID', 'First Name', 'Last Name'])

 

In [3]:

raw_data = {'Bank Client ID': ['6', '7', '8', '9', '10'],
            'First Name': ['Keanu', 'Vin', 'Chris', 'Tom', 'Dave'], 
            'Last Name': ['Reeves', 'Diesel', 'Pratt', 'Cruise', 'Batista']}

bank2_df = pd.DataFrame(raw_data, columns = ['Bank Client ID', 'First Name', 'Last Name'])

 

In [4]:

# use multi-indexing
bank_all_df = pd.concat([bank1_df, bank2_df], keys=['Customers Group 1','Customers Group 2'])
bank_all_df

 

Out[4]:

		Bank Client ID	First Name	Last Name
Customers Group 1	0	1	Robert	Downey
	1	2	Benedict	Cumberbatch
	2	3	Mark	Ruffalo
	3	4	Tom	Holland
	4	5	Ryan	Reynolds
Customers Group 2	0	6	Keanu	Reeves
	1	7	Vin	Diesel
	2	8	Chris	Pratt
	3	9	Tom	Cruise
	4	10	Dave	Batista

 

In [6]:

# accesss elements
bank_all_df.loc['Customers Group 1', :]

 

Out[6]:

	Bank Client ID	First Name	Last Name
0	1	Robert	Downey
1	2	Benedict	Cumberbatch
2	3	Mark	Ruffalo
3	4	Tom	Holland
4	5	Ryan	Reynolds

 

In [7]:

bank_all_df.loc['Customers Group 1', 0]

 

Out[7]:

Bank Client ID         1
First Name        Robert
Last Name         Downey
Name: (Customers Group 1, 0), dtype: object

 

In [14]:

bank_all_df.loc['Customers Group 2','First Name']

 

Out[14]:

0    Keanu
1      Vin
2    Chris
3      Tom
4     Dave
Name: First Name, dtype: object

 

In [16]:

bank_all_df.loc['Customers Group 2','First Name'][0]

 

Out[16]:

'Keanu'