# -*- coding: utf-8 -*- ''' Created on 2018年1月12日 @author: Jason.F @summary: Scikit-Learn庫(kù)邏輯斯蒂回歸分類算法 '''from sklearn import datasets import numpy as np from sklearn.cross_validation import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression from matplotlib.colors import ListedColormap import matplotlib.pyplot as plt #數(shù)據(jù)導(dǎo)入 iris=datasets.load_iris() X=iris.data[:,[2,3]] y=iris.target print (np.unique(y)) #訓(xùn)練集和測(cè)試集劃分 X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0) #標(biāo)準(zhǔn)化 sc=StandardScaler() sc.fit(X_train)#計(jì)算樣本的均值和標(biāo)準(zhǔn)差 X_train_std=sc.transform(X_train) X_test_std=sc.transform(X_test)#邏輯斯蒂回歸 lr=LogisticRegression(C=1000.0,random_state=0) lr.fit(X_train_std,y_train) #模型預(yù)測(cè) y_pred=lr.predict_proba(X_test_std[0,:]) print (y_pred[:,1]) #繪制決策邊界 def plot_decision_regions(X,y,classifier,test_idx=None,resolution=0.02):# 設(shè)置標(biāo)記點(diǎn)和顏色markers = ('s','x','o','^','v')colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')cmap = ListedColormap(colors[:len(np.unique(y))])# 繪制決策面x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),np.arange(x2_min, x2_max, resolution))Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)Z = Z.reshape(xx1.shape)plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)plt.xlim(xx1.min(), xx1.max())plt.ylim(xx2.min(), xx2.max())#繪制所有樣本X_test,y_test=X[test_idx,:],y[test_idx]for idx,cl in enumerate(np.unique(y)):plt.scatter(x=X[y==cl,0],y=X[y==cl,1],alpha=0.8,c=cmap(idx),marker=markers[idx],label=cl)#高亮預(yù)測(cè)樣本if test_idx:X_test,y_test =X[test_idx,:],y[test_idx]plt.scatter(X_test[:,0],X_test[:,1],c='',alpha=1.0,linewidths=1,marker='o',s=55,label='test set') X_combined_std=np.vstack((X_train_std,X_test_std)) y_combined=np.hstack((y_train,y_test)) plot_decision_regions(X=X_combined_std, y=y_combined, classifier=lr, test_idx=range(105,150)) plt.xlabel('petal length[standardized]') plt.ylabel('petal width[standardized]') plt.legend(loc='upper left') plt.show()#觀察正則化參數(shù)C的作用：減少正則化參數(shù)C的值相當(dāng)于增加正則化的強(qiáng)度 #觀察：減小參數(shù)C值，增加正則化強(qiáng)度，導(dǎo)致權(quán)重系數(shù)逐漸收縮 weights,params=[],[] for c in np.arange(-5,5,dtype=float):lr=LogisticRegression(C=10**c,random_state=0)lr.fit(X_train_std,y_train)weights.append(lr.coef_[1])params.append(10**c) weights=np.array(weights) plt.plot(params,weights[:,0],label='petal length') plt.plot(params,weights[:,1],label='petal width',linestyle='--') plt.ylabel('weight coefficient') plt.xlabel('C') plt.legend(loc='upper left') plt.xscale('log') plt.show()

結(jié)果：

總結(jié)

以上是生活随笔為你收集整理的【Python-ML】SKlearn库逻辑斯蒂回归(logisticregression) 使用的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。