[Pandas][DataFrame]S2_08_integer_index_Based_elements_selection

bank customers.csv

0.65MB

 

 

In [23]:

import pandas as pd

 

In [25]:

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

 

Out[25]:

	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 [26]:

# Access rows with their numeric index using iloc
bank_df.iloc[9]

 

Out[26]:

RowNumber                 10
CustomerId          15592389
Surname                   H?
CreditScore              684
Geography             France
Gender                  Male
Age                       27
Tenure                     2
Balance            134603.88
NumOfProducts              1
HasCrCard                  1
IsActiveMember             1
EstimatedSalary     71725.73
Exited                     0
Name: 9, dtype: object

 

 

iloc는 마지막 요소를 포함하지 않는다!

 

In [27]:

# Access multiple rows with their numeric index 
# ★ iloc is exclusive, meaning that you did not include the last element
bank_df.iloc[2:5]

 

Out[27]:

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
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

 

In [28]:

# All up until and not including index 5
bank_df.iloc[:5]

 

Out[28]:

	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

 

In [29]:

# Multiple elements are selected using a list of indexes
bank_df.iloc[[2,5,10]]

 

Out[29]:

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
2	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1
5	6	15574012	Chu	645	Spain	Male	44	8	113755.78	2	1	0	149756.71	1
10	11	15767821	Bearce	528	France	Male	31	6	102016.72	2	0	0	80181.12	0

 

In [30]:

# Slicing 
bank_df.iloc[5,0:3]

 

Out[30]:

RowNumber            6
CustomerId    15574012
Surname            Chu
Name: 5, dtype: object