Bivariate (여러개의 변수) Visualization 방법¶

Scatterplots¶

In [246]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sb
%matplotlib inline

In [ ]:

# 두 컬럼간의 관계! 를 차트로 나타내는 방법

In [247]:

# 관계란??? 비례관계, 반비례관계, 아무관계 없음.. 이 3가지를 말한다.

In [248]:

pd.read_csv("../data/fuel_econ.csv")

Out[248]:

	id	make	model	year	VClass	drive	trans	fuelType	cylinders	displ	pv2	pv4	city	UCity	highway	UHighway	comb	co2	feScore	ghgScore
0	32204	Nissan	GT-R	2013	Subcompact Cars	All-Wheel Drive	Automatic (AM6)	Premium Gasoline	6	3.8	79	0	16.4596	20.2988	22.5568	30.1798	18.7389	471	4	4
1	32205	Volkswagen	CC	2013	Compact Cars	Front-Wheel Drive	Automatic (AM-S6)	Premium Gasoline	4	2.0	94	0	21.8706	26.9770	31.0367	42.4936	25.2227	349	6	6
2	32206	Volkswagen	CC	2013	Compact Cars	Front-Wheel Drive	Automatic (S6)	Premium Gasoline	6	3.6	94	0	17.4935	21.2000	26.5716	35.1000	20.6716	429	5	5
3	32207	Volkswagen	CC 4motion	2013	Compact Cars	All-Wheel Drive	Automatic (S6)	Premium Gasoline	6	3.6	94	0	16.9415	20.5000	25.2190	33.5000	19.8774	446	5	5
4	32208	Chevrolet	Malibu eAssist	2013	Midsize Cars	Front-Wheel Drive	Automatic (S6)	Regular Gasoline	4	2.4	0	95	24.7726	31.9796	35.5340	51.8816	28.6813	310	8	8
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3924	39882	Toyota	Prius Prime	2018	Midsize Cars	Front-Wheel Drive	Automatic (variable gear ratios)	Regular Gasoline	4	1.8	0	0	55.2206	78.8197	53.0000	73.6525	54.4329	78	10	10
3925	39898	Hyundai	Sonata Hybrid	2018	Midsize Cars	Front-Wheel Drive	Automatic (AM6)	Regular Gasoline	4	2.0	0	106	39.0000	55.9000	44.3066	64.0000	41.0000	217	9	9
3926	39899	Hyundai	Sonata Hybrid SE	2018	Midsize Cars	Front-Wheel Drive	Automatic (AM6)	Regular Gasoline	4	2.0	0	106	40.0000	56.0000	46.0000	64.0000	42.0000	212	9	9
3927	39900	Lexus	LS 500	2018	Midsize Cars	Rear-Wheel Drive	Automatic (S10)	Premium Gasoline	6	3.4	99	0	19.2200	24.2000	30.2863	43.4000	23.0021	387	5	5
3928	39901	Lexus	LS 500 AWD	2018	Midsize Cars	All-Wheel Drive	Automatic (S10)	Premium Gasoline	6	3.4	99	0	18.0431	22.6000	27.0000	39.3000	21.3945	417	4	4

3929 rows × 20 columns

In [249]:

df = pd.read_csv("../data/fuel_econ.csv")

In [250]:

df.shape

Out[250]:

(3929, 20)

In [252]:

# 자동차 모델은 실제로 몇개?
df['model'].nunique()

Out[252]:

In [254]:

df['make'].nunique()

Out[254]:

In [255]:

# 자동차 만드는 회사별로, 이 데이터 프레임에는 데이터가 몇개 있는지 시각화!

In [266]:

base_order = df['make'].value_counts().index

In [269]:

base_order

Out[269]:

Index(['BMW', 'Mercedes-Benz', 'Porsche', 'Ford', 'Chevrolet', 'MINI', 'Audi',
       'Volkswagen', 'Hyundai', 'Dodge', 'Lexus', 'Kia', 'Cadillac', 'Toyota',
       'Infiniti', 'Honda', 'Jaguar', 'Mazda', 'Nissan', 'Buick', 'Subaru',
       'Chrysler', 'Lincoln', 'Volvo', 'Acura', 'Bentley', 'Mitsubishi',
       'Rolls-Royce', 'Maserati', 'Scion', 'Fiat', 'Ferrari', 'Genesis',
       'Aston Martin', 'Suzuki', 'Roush Performance', 'Lotus', 'Alfa Romeo',
       'Karma'],
      dtype='object')

In [270]:

plt.figure(figsize=(10,12))
sb.countplot(data = df, y = "make", order = base_order)
plt.show()

In [271]:

# 두 컬럼간의 관계!!!!!

# 배기량(displ)과 연비(comb)의 관계 => 비례, 반비례, 관계없음

# 1. plt의 scatter 사용하는 방법

In [274]:

plt.scatter(data = df, x= "displ", y= "comb")
plt.title("Displ Vs Comb")
plt.xlabel("Displacement (L)")
plt.ylabel('Combined Fuel Eff (mpg)')
plt.show()

In [276]:

df

Out[276]:

	id	make	model	year	VClass	drive	trans	fuelType	cylinders	displ	pv2	pv4	city	UCity	highway	UHighway	comb	co2	feScore	ghgScore
0	32204	Nissan	GT-R	2013	Subcompact Cars	All-Wheel Drive	Automatic (AM6)	Premium Gasoline	6	3.8	79	0	16.4596	20.2988	22.5568	30.1798	18.7389	471	4	4
1	32205	Volkswagen	CC	2013	Compact Cars	Front-Wheel Drive	Automatic (AM-S6)	Premium Gasoline	4	2.0	94	0	21.8706	26.9770	31.0367	42.4936	25.2227	349	6	6
2	32206	Volkswagen	CC	2013	Compact Cars	Front-Wheel Drive	Automatic (S6)	Premium Gasoline	6	3.6	94	0	17.4935	21.2000	26.5716	35.1000	20.6716	429	5	5
3	32207	Volkswagen	CC 4motion	2013	Compact Cars	All-Wheel Drive	Automatic (S6)	Premium Gasoline	6	3.6	94	0	16.9415	20.5000	25.2190	33.5000	19.8774	446	5	5
4	32208	Chevrolet	Malibu eAssist	2013	Midsize Cars	Front-Wheel Drive	Automatic (S6)	Regular Gasoline	4	2.4	0	95	24.7726	31.9796	35.5340	51.8816	28.6813	310	8	8
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3924	39882	Toyota	Prius Prime	2018	Midsize Cars	Front-Wheel Drive	Automatic (variable gear ratios)	Regular Gasoline	4	1.8	0	0	55.2206	78.8197	53.0000	73.6525	54.4329	78	10	10
3925	39898	Hyundai	Sonata Hybrid	2018	Midsize Cars	Front-Wheel Drive	Automatic (AM6)	Regular Gasoline	4	2.0	0	106	39.0000	55.9000	44.3066	64.0000	41.0000	217	9	9
3926	39899	Hyundai	Sonata Hybrid SE	2018	Midsize Cars	Front-Wheel Drive	Automatic (AM6)	Regular Gasoline	4	2.0	0	106	40.0000	56.0000	46.0000	64.0000	42.0000	212	9	9
3927	39900	Lexus	LS 500	2018	Midsize Cars	Rear-Wheel Drive	Automatic (S10)	Premium Gasoline	6	3.4	99	0	19.2200	24.2000	30.2863	43.4000	23.0021	387	5	5
3928	39901	Lexus	LS 500 AWD	2018	Midsize Cars	All-Wheel Drive	Automatic (S10)	Premium Gasoline	6	3.4	99	0	18.0431	22.6000	27.0000	39.3000	21.3945	417	4	4

3929 rows × 20 columns

In [275]:

df.corr()

Out[275]:

	id	year	cylinders	displ	pv2	pv4	city	UCity	highway	UHighway	comb	co2	feScore	ghgScore
id	1.000000	0.985668	-0.060096	-0.074666	-0.006569	-0.021951	0.091800	0.091225	0.090593	0.095359	0.093803	-0.099717	-0.127873	-0.122321
year	0.985668	1.000000	-0.055313	-0.070424	0.006232	-0.033643	0.068050	0.066742	0.073290	0.077641	0.071993	-0.081165	-0.149829	-0.145141
cylinders	-0.060096	-0.055313	1.000000	0.933872	0.247571	-0.004264	-0.693103	-0.666029	-0.766275	-0.771503	-0.738023	0.848274	-0.783858	-0.781815
displ	-0.074666	-0.070424	0.933872	1.000000	0.259336	0.022072	-0.713479	-0.686166	-0.783984	-0.788457	-0.758397	0.855375	-0.793432	-0.791216
pv2	-0.006569	0.006232	0.247571	0.259336	1.000000	-0.665642	-0.278109	-0.272546	-0.296808	-0.298504	-0.290883	0.287200	-0.296088	-0.293156
pv4	-0.021951	-0.033643	-0.004264	0.022072	-0.665642	1.000000	0.035188	0.037869	0.074952	0.077442	0.047333	-0.050153	0.064876	0.065263
city	0.091800	0.068050	-0.693103	-0.713479	-0.278109	0.035188	1.000000	0.996377	0.915435	0.909658	0.989552	-0.904305	0.905681	0.898793
UCity	0.091225	0.066742	-0.666029	-0.686166	-0.272546	0.037869	0.996377	1.000000	0.899557	0.897814	0.981106	-0.885823	0.891297	0.884458
highway	0.090593	0.073290	-0.766275	-0.783984	-0.296808	0.074952	0.915435	0.899557	1.000000	0.992191	0.962757	-0.916456	0.914116	0.897585
UHighway	0.095359	0.077641	-0.771503	-0.788457	-0.298504	0.077442	0.909658	0.897814	0.992191	1.000000	0.956580	-0.912117	0.911355	0.894314
comb	0.093803	0.071993	-0.738023	-0.758397	-0.290883	0.047333	0.989552	0.981106	0.962757	0.956580	1.000000	-0.929399	0.928862	0.918807
co2	-0.099717	-0.081165	0.848274	0.855375	0.287200	-0.050153	-0.904305	-0.885823	-0.916456	-0.912117	-0.929399	1.000000	-0.940624	-0.944566
feScore	-0.127873	-0.149829	-0.783858	-0.793432	-0.296088	0.064876	0.905681	0.891297	0.914116	0.911355	0.928862	-0.940624	1.000000	0.994231
ghgScore	-0.122321	-0.145141	-0.781815	-0.791216	-0.293156	0.065263	0.898793	0.884458	0.897585	0.894314	0.918807	-0.944566	0.994231	1.000000

In [277]:

# 딱 두 컬럼! displ과 comb 만 상관계수를 가져와라

In [278]:

df[ ["displ", 'comb'] ]

Out[278]:

	displ	comb
0	3.8	18.7389
1	2.0	25.2227
2	3.6	20.6716
3	3.6	19.8774
4	2.4	28.6813
...	...	...
3924	1.8	54.4329
3925	2.0	41.0000
3926	2.0	42.0000
3927	3.4	23.0021
3928	3.4	21.3945

3929 rows × 2 columns

In [279]:

df[ ["displ", 'comb'] ].corr()

Out[279]:

	displ	comb
displ	1.000000	-0.758397
comb	-0.758397	1.000000

In [ ]:

In [280]:

# 두 컬럼간의 관계를 차트로 표시
# 2. seaborn 의 regplot 이용하는 방법

In [283]:

plt.scatter(data = df, x= "displ", y= "comb")
plt.title("Displ Vs Comb")
plt.xlabel("Displacement (L)")
plt.ylabel('Combined Fuel Eff (mpg)')
plt.show()

In [282]:

sb.regplot(data=df, x='displ', y='comb')
plt.show()

In [284]:

sb.regplot(data=df, x='displ', y='comb')
plt.title("Displ Vs Comb")
plt.xlabel("Displacement (L)")
plt.ylabel('Combined Fuel Eff (mpg)')
plt.show()

# reg의 뜻??? regression : 데이터에 fitting 한다는 의미.

In [ ]:

# 3. sb의 pairplot 을 이용하는 방법

In [287]:

sb.pairplot(data = df, vars= ["displ",'comb', 'co2'])
plt.show()

In [ ]:

Matplotlip Heat Maps : 밀도차트, 한글처리 (1)	2022.11.28
Matplotlip 히스토그램, 갯수범위지정, bins, subplot (0)	2022.11.28
Matplotlip&seaborn 기본적인 차트, 파이차트 (0)	2022.11.28

블로그안함

Matplotlip 두 컬럼간의 관계(비례,반비례,관계없음)

Bivariate (여러개의 변수) Visualization 방법¶

Scatterplots¶

'DataScience > Matplotlip' 카테고리의 다른 글

티스토리툴바

Matplotlip 두 컬럼간의 관계(비례,반비례,관계없음)

Bivariate (여러개의 변수) Visualization 방법¶

Scatterplots¶

'DataScience > Matplotlip' 카테고리의 다른 글

관련글

티스토리툴바