Python实现岭回归

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

from sklearn.linear_model import RidgeCV
from sklearn.linear_model import Ridge
from statsmodels.stats.outliers_influence import variance_inflation_factor

sns.set_theme()# 设置风格
%config InlineBackend.figure_format = 'retina' # 让图片更清晰

df = pd.read_excel('D:/ml_data/auto-mpg.xlsx')# 导入数据
# print(df)

df_scaled = (df-df.mean())/(df.std())

xs = df_scaled.iloc[:,1:]
ys = df_scaled.iloc[:,0]

X = xs
vif=pd.DataFrame()
vif["VIF Factor"] = [variance_inflation_factor(X.values,i) for i in range(X.shape[1])]
vif["features"]=X.columns

print(vif.round(1))

VIF Factor features

0 10.7 Cylinders

1 21.8 Displacement

2 9.9 Horsepower

3 10.8 Weight

4 2.6 Acceleration

5 1.2 Model Year

6 1.8 Origin

coef=[]
alphas = np.linspace(0.1,300,300)

for a in alphas:
    ridgereg=Ridge(alpha=a)
    ridgereg.fit(xs,ys)
    coef.append(ridgereg.coef_)

fig=plt.figure()
ax=fig.add_subplot(111)
ax.plot(alphas,coef)
ax.set_xlabel('Alpha (Regularization Parameter)')
ax.set_ylabel('Beta (Predictor Coefficients)')
ax.set_title('Ridge Coefficients vs Regularization Parameters')
ax.axis('tight')
ax.legend(list(xs.keys()),loc='best')
plt.savefig("Ridge.png", dpi = 600, bbox_inches = 'tight')
plt.show()

regr_cv=RidgeCV(alphas = alphas)
model_cv=regr_cv.fit(xs,ys)
print(model_cv.alpha_)

2.106020066889632