机器学习实战（5）逻辑回归

from numpy import *

def loadDataSet():
    dataMat=[];
    labelMat=[];
    fr=open('C:/Users/xuwei/Desktop/机器学习/机器学习实战(pdf版+源码)/machinelearninginaction/Ch05/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+exp(-inX))

def gradAscent(dataMatIn,classLabels):     #梯度下降算法
    dataMatrix=mat(dataMatIn)    #mat是转换为numpy的矩阵数据
    labelMat=mat(classLabels).transpose()  #矩阵转秩
    m,n=shape(dataMatrix)
    alpha=0.001
    maxCycles=500
    weights=ones((n,1))
    for k in range(maxCycles):
        h=sigmoid(dataMatrix*weights)   #h是一个列向量
        error=(labelMat-h)        #计算真实类别和预测类别的差值，按差值方向调整回归系数
        weights=weights+alpha*dataMatrix.transpose()*error
    return weights
'''
测试梯度下降
dataArr,labelMat=loadDataSet()
print(gradAscent(dataArr,labelMat))
'''

def plotBestFit(wei):
    import matplotlib.pyplot as plt
    #weights=wei.getA()                   #将matrix转换为array
    if type(wei).__name__==matrix:                 #第一个梯度下降算法中，传入的是matrix
        weights=wei.getA()
    else:
        weights=wei                             #改进的随机梯度下降算法中，传入的就是array
    dataMat,labelMat=loadDataSet()
    dataArr=array(dataMat)
    print(dataArr)
    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]      #y是个向量
    ax.plot(x,y)
    plt.xlabel('X1')
    plt.ylabel('X2')
    plt.show()
'''
画出决策边界实例
dataArr,labelMat=loadDataSet()
weights=gradAscent(dataArr,labelMat)
plotBestFit(weights)
            
'''
    
def stocGradAscent0(dataMatrix,classLabels):  #随机梯度下降算法
    #没有矩阵转换，所有数据类型都是numpy数组
    m,n=shape(dataMatrix)
    alpha=0.01
    weights=ones(n)
    for i in range(m): #遍历每一行求weights
        h=sigmoid(sum(dataMatrix[i]*weights))  #h是数值
        error=classLabels[i]-h                  #error是数值
        weights=weights+alpha*error*dataMatrix[i]
    return weights

def stocGradAscent1(dataMatrix,classLabels,numIter=150): #改进的随机梯度上升算法
    m,n=shape(dataMatrix)
    dataIndex=list(range(m))
    weights=ones(n)
    for j in range(numIter): 
        dataIndex=list(range(m))
        for i in range(m):
            alpha=4/(1.0+j+i)+0.01    #alpha每次迭代时调整
            randIndex=int(random.uniform(0,len(dataIndex)))
            h=sigmoid(sum(dataMatrix[randIndex]*weights))
            error=classLabels[randIndex]-h
            weights=weights+alpha*error*dataMatrix[randIndex]
            del(dataIndex[randIndex])
    return weights
'''
#测试改进的梯度下降算法
dataArr,labelMat=loadDataSet()
weights=stocGradAscent1(array(dataArr), labelMat)
plotBestFit(weights)
'''

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

def colicTest():   #病马死亡率测试
    frTrain=open('C:/Users/xuwei/Desktop/机器学习/机器学习实战(pdf版+源码)/machinelearninginaction/Ch05/horseColicTraining.txt')
    frTest=open('C:/Users/xuwei/Desktop/机器学习/机器学习实战(pdf版+源码)/machinelearninginaction/Ch05/horseColicTest.txt')
    trainingSet=[]
    trainingLabels=[]
    for line in frTrain.readlines():
        currLine=line.strip().split('\t')
        lineArr=[]
        for i in range(21):
            lineArr.append(float(currLine[i]))
        trainingSet.append(lineArr)
        trainingLabels.append(float(currLine[21]))
    trainWeights=stocGradAscent1(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 of this test is:%f" % errorRate)
    return errorRate

def multiTest():        #兵马死亡率多次测试
    numTests=10
    errorSum=0.0
    for k in range(numTests):
        errorSum+=colicTest()
    print("after %d iterations the average error rate is: %f" % (numTests,errorSum/float(numTests)))
    
# multiTest()
    
    

要注意的，numpy中的matrix和array的计算方式完全不同，必须注意区分