[Pandas][DataFrame]S2_06_Column_ADDING_DELETING

bank customers.csv

0.65MB

 

 

In [1]:

import pandas as pd

 

In [2]:

bank_df = pd.read_csv('bank customers.csv')
bank_df

 

Out[2]:

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
0	1	15634602	Hargrave	619	France	Female	42	2	0.00	1	1	1	101348.88	1
1	2	15647311	Hill	608	Spain	Female	41	1	83807.86	1	0	1	112542.58	0
2	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1
3	4	15701354	Boni	699	France	Female	39	1	0.00	2	0	0	93826.63	0
4	5	15737888	Mitchell	850	Spain	Female	43	2	125510.82	1	1	1	79084.10	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9995	9996	15606229	Obijiaku	771	France	Male	39	5	0.00	2	1	0	96270.64	0
9996	9997	15569892	Johnstone	516	France	Male	35	10	57369.61	1	1	1	101699.77	0
9997	9998	15584532	Liu	709	France	Female	36	7	0.00	1	0	1	42085.58	1
9998	9999	15682355	Sabbatini	772	Germany	Male	42	3	75075.31	2	1	0	92888.52	1
9999	10000	15628319	Walker	792	France	Female	28	4	130142.79	1	1	0	38190.78	0

10000 rows × 14 columns

 

In [3]:

# example
bank_df = bank_df[:10].copy()
bank_df

 

Out[3]:

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
0	1	15634602	Hargrave	619	France	Female	42	2	0.00	1	1	1	101348.88	1
1	2	15647311	Hill	608	Spain	Female	41	1	83807.86	1	0	1	112542.58	0
2	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1
3	4	15701354	Boni	699	France	Female	39	1	0.00	2	0	0	93826.63	0
4	5	15737888	Mitchell	850	Spain	Female	43	2	125510.82	1	1	1	79084.10	0
5	6	15574012	Chu	645	Spain	Male	44	8	113755.78	2	1	0	149756.71	1
6	7	15592531	Bartlett	822	France	Male	50	7	0.00	2	1	1	10062.80	0
7	8	15656148	Obinna	376	Germany	Female	29	4	115046.74	4	1	0	119346.88	1
8	9	15792365	He	501	France	Male	44	4	142051.07	2	0	1	74940.50	0
9	10	15592389	H?	684	France	Male	27	2	134603.88	1	1	1	71725.73	0

 

In [4]:

# add a new column to the dataframe
bank_df['Years with Bank'] = [9,12,15,5,7,2,20,25,12,10]

 

 

dataframe.insert(location, column= , value=[])

 

In [5]:

# insert a new column in a given position
bank_df.insert(0, column = 'Postal Code', 
                value=['N94 3M0','N8S 14K','S1T 4E6','N7T 3E6','K8N 5H6','J7H 3HY','K8Y 3M8','J8Y 3M0','M6U 5U7','K2D 4M9'])
bank_df

 

Out[5]:

	Postal Code	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited	Years with Bank
0	N94 3M0	1	15634602	Hargrave	619	France	Female	42	2	0.00	1	1	1	101348.88	1	9
1	N8S 14K	2	15647311	Hill	608	Spain	Female	41	1	83807.86	1	0	1	112542.58	0	12
2	S1T 4E6	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1	15
3	N7T 3E6	4	15701354	Boni	699	France	Female	39	1	0.00	2	0	0	93826.63	0	5
4	K8N 5H6	5	15737888	Mitchell	850	Spain	Female	43	2	125510.82	1	1	1	79084.10	0	7
5	J7H 3HY	6	15574012	Chu	645	Spain	Male	44	8	113755.78	2	1	0	149756.71	1	2
6	K8Y 3M8	7	15592531	Bartlett	822	France	Male	50	7	0.00	2	1	1	10062.80	0	20
7	J8Y 3M0	8	15656148	Obinna	376	Germany	Female	29	4	115046.74	4	1	0	119346.88	1	25
8	M6U 5U7	9	15792365	He	501	France	Male	44	4	142051.07	2	0	1	74940.50	0	12
9	K2D 4M9	10	15592389	H?	684	France	Male	27	2	134603.88	1	1	1	71725.73	0	10

 

In [6]:

# Delete a column from a DataFrame
del bank_df['Postal Code']
bank_df

 

Out[6]:

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited	Years with Bank
0	1	15634602	Hargrave	619	France	Female	42	2	0.00	1	1	1	101348.88	1	9
1	2	15647311	Hill	608	Spain	Female	41	1	83807.86	1	0	1	112542.58	0	12
2	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1	15
3	4	15701354	Boni	699	France	Female	39	1	0.00	2	0	0	93826.63	0	5
4	5	15737888	Mitchell	850	Spain	Female	43	2	125510.82	1	1	1	79084.10	0	7
5	6	15574012	Chu	645	Spain	Male	44	8	113755.78	2	1	0	149756.71	1	2
6	7	15592531	Bartlett	822	France	Male	50	7	0.00	2	1	1	10062.80	0	20
7	8	15656148	Obinna	376	Germany	Female	29	4	115046.74	4	1	0	119346.88	1	25
8	9	15792365	He	501	France	Male	44	4	142051.07	2	0	1	74940.50	0	12
9	10	15592389	H?	684	France	Male	27	2	134603.88	1	1	1	71725.73	0	10

 

In [7]:

# Remove a column
# column is axis = 1
bank_df.drop(labels=['RowNumber','Balance'], axis = 1, inplace = True)
bank_df

 

Out[7]:

	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited	Years with Bank
0	15634602	Hargrave	619	France	Female	42	2	1	1	1	101348.88	1	9
1	15647311	Hill	608	Spain	Female	41	1	1	0	1	112542.58	0	12
2	15619304	Onio	502	France	Female	42	8	3	1	0	113931.57	1	15
3	15701354	Boni	699	France	Female	39	1	2	0	0	93826.63	0	5
4	15737888	Mitchell	850	Spain	Female	43	2	1	1	1	79084.10	0	7
5	15574012	Chu	645	Spain	Male	44	8	2	1	0	149756.71	1	2
6	15592531	Bartlett	822	France	Male	50	7	2	1	1	10062.80	0	20
7	15656148	Obinna	376	Germany	Female	29	4	4	1	0	119346.88	1	25
8	15792365	He	501	France	Male	44	4	2	0	1	74940.50	0	12
9	15592389	H?	684	France	Male	27	2	1	1	1	71725.73	0	10

 

In [8]:

# Remove a column from a DataFrame and store it somwhere else
Years_with_bank = bank_df.pop('Years with Bank')
Years_with_bank

 

Out[8]:

0     9
1    12
2    15
3     5
4     7
5     2
6    20
7    25
8    12
9    10
Name: Years with Bank, dtype: int64