基于Logistic回归的Sigmoid函数分类算法的python代码实现

import numpy as np
import matplotlib.pyplot as plt

def loadDataSet():
    dataMat = []; labelMat = []
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
        labelMat.append(int(lineArr[2]))
    return dataMat,labelMat

def sigmoid(inX):
    return 1.0/(1+np.exp(-inX))

def gradAscent(dataMatIn,classLabels):
    dataMatrix=np.mat(dataMatIn)
    labelMat=np.mat(classLabels).transpose()
    m,n=np.shape(dataMatrix)
    alpha=0.001
    maxCycles=500
    weigths=np.ones((n,1))
    for k in range(maxCycles):
        h=sigmoid(np.dot(dataMatrix,weigths))
        error=(labelMat-h)
        weigths=weigths+alpha*dataMatrix.transpose()*error
    return weigths

def plotBestFit(weights):
    dataMat, labelMat=loadDataSet()
    dataArr=np.array(dataMat)
    n=np.shape(dataArr)[0]
    xcord1=[];ycord1=[]
    xcord2=[];ycord2=[]
    m=np.shape(dataArr)[0]
    for i in range(m):
        if int(labelMat[i])==1:
            xcord1.append(dataArr[i,1]);ycord1.append(dataArr[i,2])
        else:
            xcord2.append(dataArr[i,1]);ycord2.append(dataArr[i,2])
    fig=plt.figure()
    ax=fig.add_subplot(111)
    ax.scatter(xcord1,ycord1,s=30,c='orange',marker='s')
    ax.scatter(xcord2,ycord2,s=30)
    x=np.mat(np.arange(-3.0,3.0,0.1)).tolist()
    y=np.mat((-weights[0]-weights[1]*x)/weights[2]).tolist()
    ax.plot(x[0],y[0])
    plt.xlabel('x1');plt.ylabel('x2')
    plt.show()

if __name__=='__main__':
    dataMat, labelMat=loadDataSet()
    plotBestFit(gradAscent(dataMat,labelMat))

最佳拟合直线如下所示：