Logistic回归Python实现

 

利用Logistic回归进行分类的主要思想是：根据现有数据对分类边界线建立回归公式，以此进行分类。

类似于下图中建立回归公式得到边界线，将红色和绿色的样本进行分类。

from numpy import *
import matplotlib.pyplot as plt

def loaddataset():
    dataMat=[]
    labelMat=[]
    fr=open('testSet.txt')#打开testSet数据集
    for line in fr.readlines():#读取文件中的每一行
        lineArr=line.strip().split()#将每一行的数据分开
        dataMat.append([1.0,float(lineArr[0]),float(lineArr[1])])#第一列和第二列作为特征数据集，添加1是构造常数项x0
        labelMat.append(int(lineArr[2]))#第三列作为标签
    return dataMat,labelMat

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

输入数据集和标签
def gradAscent(dataMatIn,classLabels):
    dataMatrix=mat(dataMatIn)#（m，n）
    labelMat=mat(classLabels).transpose()#转置后（m，1）
    m,n=shape(dataMatrix)
    alpha=0.001
    maxCycles=500
    weights=ones((n,1))#初始化回归系数，（n，1）
    for k in range(maxCycles):
        h=sigmoid(dataMatrix*weights)
        error=labelMat-h
        weights=weights+alpha*dataMatrix.transpose()*error#梯度上升法
    return weights

 

画图
def plotBestFit(wei):
    weights=wei.getA()
    dataMat,labelMat=loaddataset()
    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)
    plt.xlabel('X1')
    plt.ylabel('X2')
    plt.show()

dataArr,labelMat=loaddataset()
weights=gradAscent(dataArr,labelMat)

print(weights)
plotBestFit(weights)

 算法改进：

随机梯度上升：每次只使用一个数据样本点来更新回归系数，减少计算次数。

def sgdAscent(dataMatrix,classLabels):
    m,n=shape(dataMatrix)
    alpha=0.01
    weights=ones(n)
    for i in range(m):
        h=sigmoid(sum(dataMatrix[i]*weights))
        error=classLabels[i]-h
        weights=weights+alpha*error*dataMatrix[i]#数组和列表的乘法计算不一样，矩阵类型是numpy的matrix，按照矩阵的规则计算；列表按照数值规则计算。
    return weights

改进随机梯度上升法

def sgdAscent2(dataMatrix,classLabels,numIter=150):
    m,n=shape(dataMatrix)
    weights=ones(n)
    for j in range(numIter):
        dataIndex=range(m)
        for i in range(m):
            alpha=4/(1.0+j+i)+0.01#0.01是保证在多次迭代之后新数据仍有一定影响力
            randIndex=int(random.uniform(0,len(dataIndex)))#减少周期波动，随机选取更新
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * dataMatrix[randIndex] * error
            #del(dataIndex[randIndex])
    return weights

测试实例：
def classifyVector(inX,weights):
    prob=sigmoid(sum(inX*weights))
    if prob>0.5:
        return 1.0
    else:
        return 0.0

def colicTest():
    frTrain=open('horseColicTraining.txt')
    frTest=open('horseColicTest.txt')
    trainingSet=[]
    trainingLabels=[]
    for line in frTrain.readlines():
        currLine=line.strip().split('\t')
        lineArr=[]
        for i in range(21):#读取21个特征数据
            lineArr.append(float(currLine[i]))
        trainingSet.append(lineArr)
        trainingLabels.append(float(currLine[21]))
    trainWeights=sgdAscent2(array(trainingSet),trainingLabels,500)
    errorCount=0
    numTestVec=0.0
    for line in frTest.readlines():
        numTestVec+=1.0
        currLine=line.strip().split('\t')
        lineArr=[]
        for i in range(21):
            lineArr.append(float(currLine[i]))
        if int(classifyVector(array(lineArr),trainWeights))!=int(currLine[21]):
            errorCount+=1
    errorrate=float(errorCount)/numTestVec
    print('the error rate is {0}'.format(errorrate))
    return errorrate

def multiTest():#进行多次测试，此处即进行十次测试
    numTests=10
    errorSum=0.0
    for k in range(numTests):
        errorSum+=colicTest()
    print("after {0} iterations the average error rate is {1}".format(numTests,errorSum/float(numTests)))