机器学习实战：逻辑回归示例----从疝气病症预测病马的死亡率

1. 准备数据：处理缺失值

2. 逻辑回归算法：

算法来自：机器学习实战：逻辑回归 Logistic Regression

def stocGradAscent1(dataMatrix,classLabels,numIter=150):
    m,n=np.shape(dataMatrix)
    weights=np.ones(n)
    for j in range(numIter):
        dataIndex=list(range(m))
        for i in range(m):
            alpha=4/(1.0+j+i)+0.01
            randIndex=int(np.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

3.用Logistic回归进行分类

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


def colicTest():
    frTrain=open('/Users/xxxx/Downloads/machinelearninginaction-master/Ch05/horseColicTraining.txt')
    frTest=open('/Users/xxxx/Downloads/machinelearninginaction-master/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(np.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(np.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():
    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)))