adaboost元算法(代码片段)

from numpy import *
def loadSimpData():
    datMat = matrix([[ 1. ,  2.1],
        [ 2. ,  1.1],
        [ 1.3,  1. ],
        [ 1. ,  1. ],
        [ 2. ,  1. ]])
    classLabels = [1.0, 1.0, -1.0, -1.0, 1.0]
    return datMat,classLabels
def stumpClassify(dataMatrix,dimen,threshVal,threshIneq):
    retArray=ones((shape(dataMatrix)[0],1))
    if threshIneq==‘lt‘:
        retArray[dataMatrix[:,dimen]<=threshVal]=-1.0
    else:
        retArray[dataMatrix[:,dimen]>threshVal]=-1.0
    return retArray
def buildStump(dataArr,classLabels,D):
    dataMatrix=mat(dataArr)
    labelMat=mat(classLabels).T
    m,n=shape(dataMatrix)
    numSteps=10.0
    bestStump=
    bestClasEst=mat(zeros((m,1)))
    minError=inf
    for i in range(n):
        rangeMin=dataMatrix[:,i].min()
        rangeMax=dataMatrix[:,i].max()
        stepSize=(rangeMax-rangeMin)/numSteps
        for j in range(-1,int(numSteps)+1):
            for inequal in [‘lt‘,‘gt‘]:
                threshVal=(rangeMin+float(j)*stepSize)
                predictVals=stumpClassify(dataMatrix,i,threshVal,inequal)
                errArr=mat(ones((m,1)))
                errArr[predictVals==labelMat]=0
                weightedError=D.T*errArr        #1*m m*1 ==>标量
                print(‘split:dim %d,thresh:%.2f,thresh inequal:%s,the weighted error is %.3f‘%(i,threshVal,inequal,weightedError))
                if weightedError<minError:
                    minError=weightedError
                    bestClasEst=predictVals.copy()
                    bestStump[‘dim‘]=i
                    bestStump[‘thresh‘]=threshVal
                    bestStump[‘ineq‘]=inequal
    return bestStump,minError,bestClasEst
if __name__==‘__main__‘:
    D=mat(ones((5,1))/5)
    datMat, classLabels=loadSimpData()
    buildStump(datMat,classLabels,D)
    

def adaBoostTrainDS(dataArr,classLabels,numIter=40):
    weakClassArr=[]
    m=shape(dataArr)[0]
    D=mat(ones((m,1))/m)    #每个样本的权重均初始化为1/m
    aggClassEst=mat(zeros((m,1)))
    for i in range(numIter):
        beatStump,error,classEst=buildStump(dataArr,classLabels,D)
        print(‘D:‘,D.T)
        alpha=float(0.5*log((1.0-error)/max(error,e-16)))
        print(‘alpha:‘,alpha)
        beatStump[‘alpha‘]=alpha
        weakClassArr.append(beatStump)
        print(‘分类估计：‘,classEst.T)
        expon=multiply(-1*alpha*mat(classLabels).T,classEst)
        D=multiply(D,exp(expon))
        D=D/D.sum()
        aggClassEst+=alpha*classEst
        print(‘aggClassEst:‘,aggClassEst.T)
        aggErrors=multiply(sign(aggClassEst)!=mat(classLabels).T,ones((m,1)))
        errorRate=aggErrors.sum()/m
        print(‘total error:‘,errorRate,‘
‘)
        if errorRate==0.0:
            break
    return weakClassArr

if __name__==‘__main__‘:
    D=mat(ones((5,1))/5)
    datMat, classLabels=loadSimpData()
    classifyArray=adaBoostTrainDS(datMat,classLabels,9)
    print(classifyArray)

D: [[0.2 0.2 0.2 0.2 0.2]]
alpha: 0.6931471805599453
分类估计： [[-1.  1. -1. -1.  1.]]
aggClassEst: [[-0.69314718  0.69314718 -0.69314718 -0.69314718  0.69314718]]
total error: 0.2 

D: [[0.5   0.125 0.125 0.125 0.125]]
alpha: 0.9729550745276565
分类估计： [[ 1.  1. -1. -1. -1.]]
aggClassEst: [[ 0.27980789  1.66610226 -1.66610226 -1.66610226 -0.27980789]]
total error: 0.2 

D: [[0.28571429 0.07142857 0.07142857 0.07142857 0.5       ]]
alpha: 0.8958797346140273
分类估计： [[1. 1. 1. 1. 1.]]
aggClassEst: [[ 1.17568763  2.56198199 -0.77022252 -0.77022252  0.61607184]]
total error: 0.0 

[‘alpha‘: 0.6931471805599453, ‘dim‘: 0, ‘ineq‘: ‘lt‘, ‘thresh‘: 1.3, ‘alpha‘: 0.9729550745276565, ‘dim‘: 1, ‘ineq‘: ‘lt‘, ‘thresh‘: 1.0, ‘alpha‘: 0.8958797346140273, ‘dim‘: 0, ‘ineq‘: ‘lt‘, ‘thresh‘: 0.9]

if __name__==‘__main__‘:
    D=mat(ones((5,1))/5)
    datMat, classLabels=loadSimpData()
    classifyArray=adaBoostTrainDS(datMat,classLabels,9)
    result=adaClassify([[5,5],[0,0]],classifyArray)
    print(‘最终分类结果为：‘,result)

aggClassEst: [[ 0.69314718]
 [-0.69314718]]
aggClassEst: [[ 1.66610226]
 [-1.66610226]]
aggClassEst: [[ 2.56198199]
 [-2.56198199]]
最终分类结果为： [[ 1.]
 [-1.]]

def loadDataSet(filename):
    numFeatures = len(open(filename).readline().split(‘	‘)) - 1
    dataMat = []
    labelMat = []
    f = open(filename)
    for line in f.readlines():
        lineArr=[]
        curLine=line.strip().split(‘	‘)
        for i in range(0,numFeatures):
            lineArr.append(float(curLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(curLine[-1]))
    return dataMat,labelMat

if __name__==‘__main__‘:
    dataArr,labelArr=loadDataSet(‘horseColicTraining2.txt‘)
    classifyArray=adaBoostTrainDS(dataArr,labelArr,10)
    testArr,testLabelArr=loadDataSet(‘horseColicTest2.txt‘)
    prediction10=adaClassify(testArr,classifyArray)
    errArr=mat(ones((67,1)))
    count=errArr[prediction10!=mat(testLabelArr).T].sum()
    print(prediction10)
    print(count)