Python Sklearn load_boston

from sklearn.linear_model import LinearRegression # Linear : 선형, Regression : 회귀

from sklearn.model_selection import train_test_split # train : 학습용, test : 검증용

from sklearn.datasets import load_boston # 집 정보

예제

# 문제, 정답을 가진 데이터 : 지도학습을 위한 데이터 준비

boston = load_boston()

# Data Frame 생성

import pandas as pd

sample_boston = pd.DataFrame(boston.data,columns=boston.feature_names)

sample_boston['target'] = pd.DataFrame(boston.target)

sample_boston

CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0.0	0.469	7.185	61.1	4.9671	2.0	242.0	17.8	392.83	4.03	34.7
3	0.03237	0.0	2.18	0.0	0.458	6.998	45.8	6.0622	3.0	222.0	18.7	394.63	2.94	33.4
4	0.06905	0.0	2.18	0.0	0.458	7.147	54.2	6.0622	3.0	222.0	18.7	396.90	5.33	36.2
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
501	0.06263	0.0	11.93	0.0	0.573	6.593	69.1	2.4786	1.0	273.0	21.0	391.99	9.67	22.4
502	0.04527	0.0	11.93	0.0	0.573	6.120	76.7	2.2875	1.0	273.0	21.0	396.90	9.08	20.6
503	0.06076	0.0	11.93	0.0	0.573	6.976	91.0	2.1675	1.0	273.0	21.0	396.90	5.64	23.9
504	0.10959	0.0	11.93	0.0	0.573	6.794	89.3	2.3889	1.0	273.0	21.0	393.45	6.48	22.0
505	0.04741	0.0	11.93	0.0	0.573	6.030	80.8	2.5050	1.0	273.0	21.0	396.90	7.88	11.9

# 결측치 확인

sample_boston.isnull().sum()

CRIM       0
ZN         0
INDUS      0
CHAS       0
NOX        0
RM         0
AGE        0
DIS        0
RAD        0
TAX        0
PTRATIO    0
B          0
LSTAT      0
target     0
dtype: int64

# 이상치 확인

sample_boston.boxplot()

# 상관 분석

sample_boston.corr().sort_values('target',ascending=False)

CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
target	-0.388305	0.360445	-0.483725	0.175260	-0.427321	0.695360	-0.376955	0.249929	-0.381626	-0.468536	-0.507787	0.333461	-0.737663	1.000000
RM	-0.219247	0.311991	-0.391676	0.091251	-0.302188	1.000000	-0.240265	0.205246	-0.209847	-0.292048	-0.355501	0.128069	-0.613808	0.695360
ZN	-0.200469	1.000000	-0.533828	-0.042697	-0.516604	0.311991	-0.569537	0.664408	-0.311948	-0.314563	-0.391679	0.175520	-0.412995	0.360445
B	-0.385064	0.175520	-0.356977	0.048788	-0.380051	0.128069	-0.273534	0.291512	-0.444413	-0.441808	-0.177383	1.000000	-0.366087	0.333461
DIS	-0.379670	0.664408	-0.708027	-0.099176	-0.769230	0.205246	-0.747881	1.000000	-0.494588	-0.534432	-0.232471	0.291512	-0.496996	0.249929
CHAS	-0.055892	-0.042697	0.062938	1.000000	0.091203	0.091251	0.086518	-0.099176	-0.007368	-0.035587	-0.121515	0.048788	-0.053929	0.175260
AGE	0.352734	-0.569537	0.644779	0.086518	0.731470	-0.240265	1.000000	-0.747881	0.456022	0.506456	0.261515	-0.273534	0.602339	-0.376955
RAD	0.625505	-0.311948	0.595129	-0.007368	0.611441	-0.209847	0.456022	-0.494588	1.000000	0.910228	0.464741	-0.444413	0.488676	-0.381626
CRIM	1.000000	-0.200469	0.406583	-0.055892	0.420972	-0.219247	0.352734	-0.379670	0.625505	0.582764	0.289946	-0.385064	0.455621	-0.388305
NOX	0.420972	-0.516604	0.763651	0.091203	1.000000	-0.302188	0.731470	-0.769230	0.611441	0.668023	0.188933	-0.380051	0.590879	-0.427321
TAX	0.582764	-0.314563	0.720760	-0.035587	0.668023	-0.292048	0.506456	-0.534432	0.910228	1.000000	0.460853	-0.441808	0.543993	-0.468536
INDUS	0.406583	-0.533828	1.000000	0.062938	0.763651	-0.391676	0.644779	-0.708027	0.595129	0.720760	0.383248	-0.356977	0.603800	-0.483725
PTRATIO	0.289946	-0.391679	0.383248	-0.121515	0.188933	-0.355501	0.261515	-0.232471	0.464741	0.460853	1.000000	-0.177383	0.374044	-0.507787
LSTAT	0.455621	-0.412995	0.603800	-0.053929	0.590879	-0.613808	0.602339	-0.496996	0.488676	0.543993	0.374044	-0.366087	1.000000	-0.737663

# 산점도

plt.scatter(sample_boston['target'],sample_boston['RM'])

plt.show()

# 도면

plt.plot(sample_boston['target'],sample_boston['RM'])

plt.show()

# 라인차트

plt.bar(sample_boston['target'],sample_boston['RM'])

plt.show()

# 쌍 도면

import seaborn as sns

sns.pairplot(sample_boston, hue='target') # pastel, bright, deep, muted, colorblind, dark

plt.show()

# 결론 : 집의 방의 숫자(RM)가 집 값에 영향을 많이 끼친다

# 데이터 만들기

X_train, X_test, y_train, y_test = train_test_split(boston['data'], boston['target'], test_size=.20, random_state=123)

# 데이터 행과 열

X_train.shape # (404, 13)

X_test.shape # (102, 13)

y_train.shape # (404,)

y_test.shape # (102,)

# 모델 만들기

model = LinearRegression()

model

# 모델을 학습 시키기

model.fit(X_train,y_train)

# 가중치 알아내기

model.coef_

array([-9.87931696e-02,  4.75027102e-02,  6.69491841e-02,  1.26954150e+00,
       -1.54697747e+01,  4.31968412e+00, -9.80167937e-04, -1.36597953e+00,
        2.84521838e-01, -1.27533606e-02, -9.13487599e-01,  7.22553507e-03,
       -5.43790245e-01])

# 편향치 알아내기

model.intercept_ # 31.835164121206343

# 결정계수

model.score(X_train, y_train) # 0.7559380876016175, 1에 가까울 수록 정확

# 추정하기

pred = model.predict(X_test)

plt.scatter(y_test, pred)

plt.title("모델이 추정한 값과 실제값의 차이")

plt.xlabel("y_test")

plt.ylabel("pred")

plt.show()

# 45도에 가까울 수록 정확한 것

plt.plot(range(0,len(y_test)),y_test,range(0,len(pred)),pred)

plt.show()