scikit-learn：逻辑回归

2

class sklearn.linear_model.LogisticRegression (penalty=’l2’,
												dual=False, 
												tol=0.0001, 
												C=1.0,
												fit_intercept=True, 
												intercept_scaling=1, 
												class_weight=None,
												random_state=None, 
												solver=’warn’, 
												max_iter=100,
												multi_class=’warn’, 
												verbose=0, 
												warm_start=False, 
												n_jobs=None
											)

可以看见，当我们选择L1正则化的时候，许多特征的参数都被设置为了0，这些特征在真正建模的时候，就不会出
现在我们的模型当中了，而L2正则化则是对所有的特征都给出了参数。
究竟哪个正则化的效果更好呢？还是都差不多？

l1 = []
l2 = []
l1test = []
l2test = []

Xtrain, Xtest, Ytrain, Ytest = train_test_split(X, y, test_size = 0.3, random_state=420)

for i in np.linspace(0.05,1,19):
    lrl1 = LR(penalty="l1",solver="liblinear",C=i,max_iter=1000)
    lrl2 = LR(penalty="l2",solver="liblinear",C=i,max_iter=1000)
    
    lrl1 = lrl1.fit(Xtrain,Ytrain)
    l1.append(accuracy_score(lrl1.predict(Xtrain),Ytrain))
    l1test.append(accuracy_score(lrl1.predict(Xtest),Ytest))
    
    lrl2 = lrl2.fit(Xtrain,Ytrain)
    l2.append(accuracy_score(lrl2.predict(Xtrain),Ytrain))
    l2test.append(accuracy_score(lrl2.predict(Xtest),Ytest))
    
graph = [l1,l2,l1test,l2test]
color = ["green","black","lightgreen","gray"]
label = ["L1","L2","L1test","L2test"]

plt.figure(figsize=(6,6))
for i in range(len(graph)):
    plt.plot(np.linspace(0.05,1,19),graph[i],color[i],label=label[i])
plt.legend(loc=4) #图例的位置在哪里?4表示，右下角
plt.show()

fullx = []
fsx = []
C=np.arange(0.01,10.01,0.5)
for i in C:
    LR_ = LR(solver="liblinear",C=i,random_state=420)
    fullx.append(cross_val_score(LR_,data.data,data.target,cv=10).mean())
    X_embedded = SelectFromModel(LR_,norm_order=1).fit_transform(data.data,data.target)
    fsx.append(cross_val_score(LR_,X_embedded,data.target,cv=10).mean())
    
print(max(fsx),C[fsx.index(max(fsx))])
plt.figure(figsize=(20,5))
plt.plot(C,fullx,label="full")
plt.plot(C,fsx,label="feature selection")
plt.xticks(C)
plt.legend()
plt.show()

继续细化学习曲线：

fullx = []
fsx = []
C=np.arange(6.05,7.05,0.005)
for i in C:
    LR_ = LR(solver="liblinear",C=i,random_state=420)
    fullx.append(cross_val_score(LR_,data.data,data.target,cv=10).mean())
    X_embedded = SelectFromModel(LR_,norm_order=1).fit_transform(data.data,data.target)
    fsx.append(cross_val_score(LR_,X_embedded,data.target,cv=10).mean())
    
print(max(fsx),C[fsx.index(max(fsx))])
plt.figure(figsize=(20,5))
plt.plot(C,fullx,label="full")
plt.plot(C,fsx,label="feature selection")
plt.xticks(C)
plt.legend()
plt.show()

来看看乳腺癌数据集下，max_iter的学习曲线：

l2 = []
l2test = []
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3,random_state=420)
for i in np.arange(1,201,10):
    lrl2 = LR(penalty="l2",solver="liblinear",C=0.9,max_iter=i)
    lrl2 = lrl2.fit(Xtrain,Ytrain)
    l2.append(accuracy_score(lrl2.predict(Xtrain),Ytrain))
    l2test.append(accuracy_score(lrl2.predict(Xtest),Ytest))
graph = [l2,l2test]
color = ["black","gray"]
label = ["L2","L2test"]
plt.figure(figsize=(20,5))
for i in range(len(graph)):
    plt.plot(np.arange(1,201,10),graph[i],color[i],label=label[i])
    
plt.legend(loc=4)
plt.xticks(np.arange(1,201,10))
plt.show(

#我们可以使用属性.n_iter_来调用本次求解中真正实现的迭代次数
lr = LR(penalty="l2",solver="liblinear",C=0.9,max_iter=300).fit(Xtrain,Ytrain)
lr.n_iter_

#array([25], dtype=int32)