机器学习：Logistic回归原理浅析

from numpy import *
import matplotlib.pyplot as plt

def loadDataSet(fileName):
    dataMat = []; labelMat = []
    fr = open(fileName)
    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 mat(dataMat), mat(labelMat)

def sigmoid(inX):   #定义Sigmoid函数
    return 1.0/(1+exp(-inX))

def gradAscent(dataMatIn, classLabels):
    labelMat = classLabels.transpose() 
    m,n = shape(dataMatIn)
    alpha = 0.001   #学习速率
    maxCycles = 1000   #迭代次数
    weights = ones((n, 1))
    for k in range(maxCycles):              
        h = sigmoid(dataMatIn*weights)     
        error = (labelMat - h)              #预测类别与真实类别之间的误差
        weights = weights + alpha * dataMatIn.transpose() * error  #通过梯度上升法更新w
    return weights

def plotBestFit(dataMat, labelMat, weights):
    dataArr = array(dataMat)
    n = shape(dataArr)[0]
    xcord1 = []; ycord1 = []
    xcord2 = []; ycord2 = []
    for i in range(n):
        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='red', marker='s')
    ax.scatter(xcord2, ycord2, s=30, c='green')
    x = arange(-3.0, 3.0, 0.1)
    y = (-weights[0]-weights[1]*x)/weights[2]
    ax.plot(x, y.T, linewidth=3)
    plt.xlabel('X1'); plt.ylabel('X2');
    plt.show()

if __name__=="__main__":
    dataMat, labelMat = loadDataSet("testSet.txt")
    weights = gradAscent(dataMat, labelMat)
    plotBestFit(dataMat, labelMat.T, weights)