线性模型L2正则化——岭回归

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.datasets import load_diabetes
X,y=load_diabetes().data,load_diabetes().target
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=8)
lr=LinearRegression().fit(X_train,y_train)
print("the coefficient:{}".format(lr.coef_))
print('the intercept:{}'.format(lr.intercept_))
print("the score of this model:{:.3f}".format(lr.score(X_test,y_test)))

from sklearn.linear_model import Ridge
ridge=Ridge().fit(X_train,y_train)
print("the coefficient:{}".format(ridge.coef_))
print('the intercept:{}'.format(ridge.intercept_))
print("the score of this model:{:.3f}
".format(ridge.score(X_test,y_test)))

ridge10=Ridge(alpha=10).fit(X_train,y_train)
print("the coefficient:{}".format(ridge10.coef_))
print('the intercept:{}'.format(ridge10.intercept_))
print("the score of this model:{:.3f}
".format(ridge10.score(X_test,y_test)))

ridge01=Ridge(alpha=0.1).fit(X_train,y_train)
print("the coefficient:{}".format(ridge01.coef_))
print('the intercept:{}'.format(ridge01.intercept_))
print("the score of this model:{:.3f}
".format(ridge01.score(X_test,y_test)))

import matplotlib.pyplot as plt
plt.plot(ridge.coef_,'s',label='Ridge alpha=1')
plt.plot(ridge10.coef_,'^',label='Ridge alpha=10')
plt.plot(ridge01.coef_,'v',label='Ridge alpha=0.1')
plt.plot(lr.coef_,'o',label='Linear Regression')
plt.xlabel("coeffient index")
plt.ylabel("coeffient magnitude")
plt.hlines(0,0,len(lr.coef_))
plt.legend()
plt.show()

import numpy as np
from sklearn.model_selection import learning_curve,KFold
def plot_learning_curve(est,X,y):
    training_set_size,train_scores,test_scores=learning_curve(
        est,X,y,train_sizes=np.linspace(.1,1,20),cv=KFold(20,shuffle=True,random_state=1)
    )
    estimator_name=est.__class__.__name__
    line=plt.plot(training_set_size,train_scores.mean(axis=1),'--',label="training "+estimator_name)
    plt.plot(training_set_size,test_scores.mean(axis=1),'-',label="test "+estimator_name,c=line[0].get_color())
    plt.xlabel("Training set size")
    plt.ylabel("Score")
    plt.ylim(0,1.1)

plot_learning_curve(Ridge(alpha=1),X,y)
plot_learning_curve(LinearRegression(),X,y)
plt.legend(loc=(0,1.05),ncol=2,fontsize=11)
plt.show()