## 吴裕雄 python 机器学习——岭回归

import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets, linear_model
from sklearn.model_selection import train_test_split

return train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)

#岭回归
def test_Ridge(*data):
X_train,X_test,y_train,y_test=data
regr = linear_model.Ridge()
regr.fit(X_train, y_train)
print('Coefficients:%s, intercept %.2f'%(regr.coef_,regr.intercept_))
print("Residual sum of squares: %.2f"% np.mean((regr.predict(X_test) - y_test) ** 2))
print('Score: %.2f' % regr.score(X_test, y_test))

# 产生用于回归问题的数据集
# 调用 test_Ridge
test_Ridge(X_train,X_test,y_train,y_test)

def test_Ridge_alpha(*data):
X_train,X_test,y_train,y_test=data
alphas=[0.01,0.02,0.05,0.1,0.2,0.5,1,2,5,10,20,50,100,200,500,1000]
scores=[]
for i,alpha in enumerate(alphas):
regr = linear_model.Ridge(alpha=alpha)
regr.fit(X_train, y_train)
scores.append(regr.score(X_test, y_test))
## 绘图
fig=plt.figure()
ax.plot(alphas,scores)
ax.set_xlabel(r"$\alpha$")
ax.set_ylabel(r"score")
ax.set_xscale('log')
ax.set_title("Ridge")
plt.show()

test_Ridge_alpha(X_train,X_test,y_train,y_test) # 调用 test_Ridge_alpha