16.更多关于线性回归模型的讨论

Posted 2020-12-21 waterr

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

# 获取数据
boston = datasets.load_boston()
X = boston.data
y = boston.target

# 数据处理
X = X[y < 50.0]
y = y[y < 50.0]

 

from sklearn.linear_model import LinearRegression

# 求解多元线性方程
lin_reg = LinearRegression()
lin_reg.fit(X, y)

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)

lin_reg.coef_

array([-1.06715912e-01,  3.53133180e-02, -4.38830943e-02,  4.52209315e-01,
       -1.23981083e+01,  3.75945346e+00, -2.36790549e-02, -1.21096549e+00,
        2.51301879e-01, -1.37774382e-02, -8.38180086e-01,  7.85316354e-03,
       -3.50107918e-01])

 

np.argsort(lin_reg.coef_)

array([ 4,  7, 10, 12,  0,  2,  6,  9, 11,  1,  8,  3,  5], dtype=int64)

boston.feature_names[np.argsort(lin_reg.coef_)]

array([‘NOX‘, ‘DIS‘, ‘PTRATIO‘, ‘LSTAT‘, ‘CRIM‘, ‘INDUS‘, ‘AGE‘, ‘TAX‘,
       ‘B‘, ‘ZN‘, ‘RAD‘, ‘CHAS‘, ‘RM‘], dtype=‘<U7‘)