In [1]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score
# 당뇨병 환자의 데이터
diabetes = datasets.load_diabetes()
In [20]:
diabetes.data.shape , diabetes.data , len(diabetes.data)
Out[20]:
((442, 10), array([[ 0.03807591, 0.05068012, 0.06169621, ..., -0.00259226,
0.01990842, -0.01764613],
[-0.00188202, -0.04464164, -0.05147406, ..., -0.03949338,
-0.06832974, -0.09220405],
[ 0.08529891, 0.05068012, 0.04445121, ..., -0.00259226,
0.00286377, -0.02593034],
...,
[ 0.04170844, 0.05068012, -0.01590626, ..., -0.01107952,
-0.04687948, 0.01549073],
[-0.04547248, -0.04464164, 0.03906215, ..., 0.02655962,
0.04452837, -0.02593034],
[-0.04547248, -0.04464164, -0.0730303 , ..., -0.03949338,
-0.00421986, 0.00306441]]), 442)
In [21]:
diabetes_X = diabetes.data[:, 2].reshape(len(diabetes.data),1)
In [22]:
diabetes_X.shape , diabetes_X
Out[22]:
((442, 1), array([[ 0.06169621],
[-0.05147406],
[ 0.04445121],
[-0.01159501],
[-0.03638469],
[-0.04069594],
[-0.04716281],
[-0.00189471],
[ 0.06169621],
[ 0.03906215],
[-0.08380842],
[ 0.01750591],
[-0.02884001],
[-0.00189471],
[-0.02560657],
[-0.01806189],
[ 0.04229559],
[ 0.01211685],
[-0.0105172 ],
[-0.01806189],
[-0.05686312],
[-0.02237314],
[-0.00405033],
[ 0.06061839],
[ 0.03582872],
[-0.01267283],
[-0.07734155],
[ 0.05954058],
[-0.02129532],
[-0.00620595],
[ 0.04445121],
[-0.06548562],
[ 0.12528712],
[-0.05039625],
[-0.06332999],
[-0.03099563],
[ 0.02289497],
[ 0.01103904],
[ 0.07139652],
[ 0.01427248],
[-0.00836158],
[-0.06764124],
[-0.0105172 ],
[-0.02345095],
[ 0.06816308],
[-0.03530688],
[-0.01159501],
[-0.0730303 ],
[-0.04177375],
[ 0.01427248],
[-0.00728377],
[ 0.0164281 ],
[-0.00943939],
[-0.01590626],
[ 0.0250506 ],
[-0.04931844],
[ 0.04121778],
[-0.06332999],
[-0.06440781],
[-0.02560657],
[-0.00405033],
[ 0.00457217],
[-0.00728377],
[-0.0374625 ],
[-0.02560657],
[-0.02452876],
[-0.01806189],
[-0.01482845],
[-0.02991782],
[-0.046085 ],
[-0.06979687],
[ 0.03367309],
[-0.00405033],
[-0.02021751],
[ 0.00241654],
[-0.03099563],
[ 0.02828403],
[-0.03638469],
[-0.05794093],
[-0.0374625 ],
[ 0.01211685],
[-0.02237314],
[-0.03530688],
[ 0.00996123],
[-0.03961813],
[ 0.07139652],
[-0.07518593],
[-0.00620595],
[-0.04069594],
[-0.04824063],
[-0.02560657],
[ 0.0519959 ],
[ 0.00457217],
[-0.06440781],
[-0.01698407],
[-0.05794093],
[ 0.00996123],
[ 0.08864151],
[-0.00512814],
[-0.06440781],
[ 0.01750591],
[-0.04500719],
[ 0.02828403],
[ 0.04121778],
[ 0.06492964],
[-0.03207344],
[-0.07626374],
[ 0.04984027],
[ 0.04552903],
[-0.00943939],
[-0.03207344],
[ 0.00457217],
[ 0.02073935],
[ 0.01427248],
[ 0.11019775],
[ 0.00133873],
[ 0.05846277],
[-0.02129532],
[-0.0105172 ],
[-0.04716281],
[ 0.00457217],
[ 0.01750591],
[ 0.08109682],
[ 0.0347509 ],
[ 0.02397278],
[-0.00836158],
[-0.06117437],
[-0.00189471],
[-0.06225218],
[ 0.0164281 ],
[ 0.09618619],
[-0.06979687],
[-0.02129532],
[-0.05362969],
[ 0.0433734 ],
[ 0.05630715],
[-0.0816528 ],
[ 0.04984027],
[ 0.11127556],
[ 0.06169621],
[ 0.01427248],
[ 0.04768465],
[ 0.01211685],
[ 0.00564998],
[ 0.04660684],
[ 0.12852056],
[ 0.05954058],
[ 0.09295276],
[ 0.01535029],
[-0.00512814],
[ 0.0703187 ],
[-0.00405033],
[-0.00081689],
[-0.04392938],
[ 0.02073935],
[ 0.06061839],
[-0.0105172 ],
[-0.03315126],
[-0.06548562],
[ 0.0433734 ],
[-0.06225218],
[ 0.06385183],
[ 0.03043966],
[ 0.07247433],
[-0.0191397 ],
[-0.06656343],
[-0.06009656],
[ 0.06924089],
[ 0.05954058],
[-0.02668438],
[-0.02021751],
[-0.046085 ],
[ 0.07139652],
[-0.07949718],
[ 0.00996123],
[-0.03854032],
[ 0.01966154],
[ 0.02720622],
[-0.00836158],
[-0.01590626],
[ 0.00457217],
[-0.04285156],
[ 0.00564998],
[-0.03530688],
[ 0.02397278],
[-0.01806189],
[ 0.04229559],
[-0.0547075 ],
[-0.00297252],
[-0.06656343],
[-0.01267283],
[-0.04177375],
[-0.03099563],
[-0.00512814],
[-0.05901875],
[ 0.0250506 ],
[-0.046085 ],
[ 0.00349435],
[ 0.05415152],
[-0.04500719],
[-0.05794093],
[-0.05578531],
[ 0.00133873],
[ 0.03043966],
[ 0.00672779],
[ 0.04660684],
[ 0.02612841],
[ 0.04552903],
[ 0.04013997],
[-0.01806189],
[ 0.01427248],
[ 0.03690653],
[ 0.00349435],
[-0.07087468],
[-0.03315126],
[ 0.09403057],
[ 0.03582872],
[ 0.03151747],
[-0.06548562],
[-0.04177375],
[-0.03961813],
[-0.03854032],
[-0.02560657],
[-0.02345095],
[-0.06656343],
[ 0.03259528],
[-0.046085 ],
[-0.02991782],
[-0.01267283],
[-0.01590626],
[ 0.07139652],
[-0.03099563],
[ 0.00026092],
[ 0.03690653],
[ 0.03906215],
[-0.01482845],
[ 0.00672779],
[-0.06871905],
[-0.00943939],
[ 0.01966154],
[ 0.07462995],
[-0.00836158],
[-0.02345095],
[-0.046085 ],
[ 0.05415152],
[-0.03530688],
[-0.03207344],
[-0.0816528 ],
[ 0.04768465],
[ 0.06061839],
[ 0.05630715],
[ 0.09834182],
[ 0.05954058],
[ 0.03367309],
[ 0.05630715],
[-0.06548562],
[ 0.16085492],
[-0.05578531],
[-0.02452876],
[-0.03638469],
[-0.00836158],
[-0.04177375],
[ 0.12744274],
[-0.07734155],
[ 0.02828403],
[-0.02560657],
[-0.06225218],
[-0.00081689],
[ 0.08864151],
[-0.03207344],
[ 0.03043966],
[ 0.00888341],
[ 0.00672779],
[-0.02021751],
[-0.02452876],
[-0.01159501],
[ 0.02612841],
[-0.05901875],
[-0.03638469],
[-0.02452876],
[ 0.01858372],
[-0.0902753 ],
[-0.00512814],
[-0.05255187],
[-0.02237314],
[-0.02021751],
[-0.0547075 ],
[-0.00620595],
[-0.01698407],
[ 0.05522933],
[ 0.07678558],
[ 0.01858372],
[-0.02237314],
[ 0.09295276],
[-0.03099563],
[ 0.03906215],
[-0.06117437],
[-0.00836158],
[-0.0374625 ],
[-0.01375064],
[ 0.07355214],
[-0.02452876],
[ 0.03367309],
[ 0.0347509 ],
[-0.03854032],
[-0.03961813],
[-0.00189471],
[-0.03099563],
[-0.046085 ],
[ 0.00133873],
[ 0.06492964],
[ 0.04013997],
[-0.02345095],
[ 0.05307371],
[ 0.04013997],
[-0.02021751],
[ 0.01427248],
[-0.03422907],
[ 0.00672779],
[ 0.00457217],
[ 0.03043966],
[ 0.0519959 ],
[ 0.06169621],
[-0.00728377],
[ 0.00564998],
[ 0.05415152],
[-0.00836158],
[ 0.114509 ],
[ 0.06708527],
[-0.05578531],
[ 0.03043966],
[-0.02560657],
[ 0.10480869],
[-0.00620595],
[-0.04716281],
[-0.04824063],
[ 0.08540807],
[-0.01267283],
[-0.03315126],
[-0.00728377],
[-0.01375064],
[ 0.05954058],
[ 0.02181716],
[ 0.01858372],
[-0.01159501],
[-0.00297252],
[ 0.01750591],
[-0.02991782],
[-0.02021751],
[-0.05794093],
[ 0.06061839],
[-0.04069594],
[-0.07195249],
[-0.05578531],
[ 0.04552903],
[-0.00943939],
[-0.03315126],
[ 0.04984027],
[-0.08488624],
[ 0.00564998],
[ 0.02073935],
[-0.00728377],
[ 0.10480869],
[-0.02452876],
[-0.00620595],
[-0.03854032],
[ 0.13714305],
[ 0.17055523],
[ 0.00241654],
[ 0.03798434],
[-0.05794093],
[-0.00943939],
[-0.02345095],
[-0.0105172 ],
[-0.03422907],
[-0.00297252],
[ 0.06816308],
[ 0.00996123],
[ 0.00241654],
[-0.03854032],
[ 0.02612841],
[-0.08919748],
[ 0.06061839],
[-0.02884001],
[-0.02991782],
[-0.0191397 ],
[-0.04069594],
[ 0.01535029],
[-0.02452876],
[ 0.00133873],
[ 0.06924089],
[-0.06979687],
[-0.02991782],
[-0.046085 ],
[ 0.01858372],
[ 0.00133873],
[-0.03099563],
[-0.00405033],
[ 0.01535029],
[ 0.02289497],
[ 0.04552903],
[-0.04500719],
[-0.03315126],
[ 0.097264 ],
[ 0.05415152],
[ 0.12313149],
[-0.08057499],
[ 0.09295276],
[-0.05039625],
[-0.01159501],
[-0.0277622 ],
[ 0.05846277],
[ 0.08540807],
[-0.00081689],
[ 0.00672779],
[ 0.00888341],
[ 0.08001901],
[ 0.07139652],
[-0.02452876],
[-0.0547075 ],
[-0.03638469],
[ 0.0164281 ],
[ 0.07786339],
[-0.03961813],
[ 0.01103904],
[-0.04069594],
[-0.03422907],
[ 0.00564998],
[ 0.08864151],
[-0.03315126],
[-0.05686312],
[-0.03099563],
[ 0.05522933],
[-0.06009656],
[ 0.00133873],
[-0.02345095],
[-0.07410811],
[ 0.01966154],
[-0.01590626],
[-0.01590626],
[ 0.03906215],
[-0.0730303 ]]))
In [29]:
# 트레이닝 데이터와 테스트 데이터를 나눔.
diabetes_X_train = diabetes_X[:-20] #앞의 전체-20개
diabetes_X_test = diabetes_X[-20:] #뒤의 20개
diabetes_y_train = diabetes.target[:-20]
diabetes_y_test = diabetes.target[-20:]
In [ ]:
#위와 같이 데이터가 준비가 되었습니다.
#그러면 모델을 만들고 훈련을 시켜봅시다. 어떻게 하면 될까요?
In [38]:
#모델을 만듭니다.
regr = linear_model.LinearRegression()
In [40]:
#모델을 훈련을 시킵니다.
regr.fit(diabetes_X_train, diabetes_y_train)
Out[40]:
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
In [43]:
#예측은 어떻게 하면 될까요?
In [44]:
diabetes_y_pred = regr.predict(diabetes_X_test)
diabetes_y_pred
Out[44]:
array([225.9732401 , 115.74763374, 163.27610621, 114.73638965,
120.80385422, 158.21988574, 236.08568105, 121.81509832,
99.56772822, 123.83758651, 204.73711411, 96.53399594,
154.17490936, 130.91629517, 83.3878227 , 171.36605897,
137.99500384, 137.99500384, 189.56845268, 84.3990668 ])
In [45]:
print('Coefficients: \n', regr.coef_)
Coefficients: [938.23786125]
In [47]:
#R^2은 어떻게 구하면 될까요?
#다음과 같이 하면 됩니다.
In [48]:
print('Variance score: %.2f' % r2_score(diabetes_y_test, diabetes_y_pred))
Variance score: 0.47
In [49]:
plt.scatter(diabetes_X_test, diabetes_y_test, color='black')
plt.plot(diabetes_X_test, diabetes_y_pred, color='blue', linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()
In [ ]:
'데이터분석 > 파이썬' 카테고리의 다른 글
| 의사결정나무 (0) | 2021.08.08 |
|---|---|
| 의사결정 나무 연습문제 (0) | 2021.08.08 |