机器学习sklearn（57）：算法实例（十四）分类（七）逻辑回归（二）linear_model.LogisticRegression(一) 重要参数

from sklearn.linear_model import LogisticRegression as LR
from sklearn.datasets import load_breast_cancer
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
data = load_breast_cancer()
X = data.data
y = data.target
data.data.shape
lrl1 = LR(penalty="l1",solver="liblinear",C=0.5,max_iter=1000)
lrl2 = LR(penalty="l2",solver="liblinear",C=0.5,max_iter=1000) #逻辑回归的重要属性coef_，查看每个特征所对应的参数
lrl1 = lrl1.fit(X,y)
lrl1.coef_
(lrl1.coef_ != 0).sum(axis=1)
lrl2 = lrl2.fit(X,y)
lrl2.coef_

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()

from sklearn.linear_model import LogisticRegression as LR
from sklearn.datasets import load_breast_cancer
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_score
from sklearn.feature_selection import SelectFromModel
data = load_breast_cancer()
data.data.shape
LR_ = LR(solver="liblinear",C=0.9,random_state=420)
cross_val_score(LR_,data.data,data.target,cv=10).mean()
X_embedded = SelectFromModel(LR_,norm_order=1).fit_transform(data.data,data.target)
X_embedded.shape
cross_val_score(LR_,X_embedded,data.target,cv=10).mean()

fullx = []
fsx = []
threshold = np.linspace(0,abs((LR_.fit(data.data,data.target).coef_)).max(),20) k=0
for i in threshold:
    X_embedded = SelectFromModel(LR_,threshold=i).fit_transform(data.data,data.target)
    fullx.append(cross_val_score(LR_,data.data,data.target,cv=5).mean())
    fsx.append(cross_val_score(LR_,X_embedded,data.target,cv=5).mean())
    print((threshold[k],X_embedded.shape[1]))
    k+=1
    
plt.figure(figsize=(20,5))
plt.plot(threshold,fullx,label="full")
plt.plot(threshold,fsx,label="feature selection")
plt.xticks(threshold)
plt.legend()
plt.show()