《机器学习第七章Adaboost实践》

import numpy as np
import matplotlib.pyplot as plt

def loadSimpData():
    datMat = np.matrix([[ 1. ,  2.1],
        [ 1.5 ,  1.6],
        [ 1.3,  1. ],
        [ 1. ,  1. ],
        [ 2. ,  1. ]])
    classLabels = [1.0, 1.0, -1.0, -1.0, 1.0]
    return datMat,classLabels

datMat,classLabels = loadSimpData()
##print(datMat)
##print(classLabels)


def showDataSet(dataMat, labelMat):
    data_plus = []                                  #正样本
    data_minus = []                                 #负样本
    for i in range(len(dataMat)):
        if labelMat[i] > 0:
            data_plus.append(dataMat[i])
        else:
            data_minus.append(dataMat[i])
    data_plus_np = np.array(data_plus)                                             #转换为numpy矩阵
    data_minus_np = np.array(data_minus)                                         #转换为numpy矩阵
    plt.scatter(np.transpose(data_plus_np)[0], np.transpose(data_plus_np)[1])        #正样本散点图
    plt.scatter(np.transpose(data_minus_np)[0], np.transpose(data_minus_np)[1])     #负样本散点图
    plt.show()

##showDataSet(datMat,classLabels)

def stumpClassify(dataMatrix,dimen,threshVal,threshIneq):#just classify the data
    retArray = np.ones((np.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 = np.mat(dataArr); labelMat = np.mat(classLabels).T
    m,n = np.shape(dataMatrix)
    numSteps = 10.0; bestStump = {}; bestClasEst = np.mat(np.zeros((m,1)))
    minError = np.inf #init error sum, to +infinity
    for i in range(n):#loop over all dimensions
        rangeMin = dataMatrix[:,i].min(); rangeMax = dataMatrix[:,i].max();
        stepSize = (rangeMax-rangeMin)/numSteps
        for j in range(-1,int(numSteps)+1):#loop over all range in current dimension
            for inequal in ['lt', 'gt']: #go over less than and greater than
                threshVal = (rangeMin + float(j) * stepSize)
                predictedVals = stumpClassify(dataMatrix,i,threshVal,inequal)#call stump classify with i, j, lessThan
                errArr = np.mat(np.ones((m,1)))
                errArr[predictedVals == labelMat] = 0
                weightedError = D.T*errArr  #calc total error multiplied by D
                #print ("split: dim %d, thresh %.2f, thresh ineqal: %s, the weighted error is %.3f" % (i, threshVal, inequal, weightedError))
                if weightedError < minError:
                    minError = weightedError
                    bestClasEst = predictedVals.copy()
                    bestStump['dim'] = i
                    bestStump['thresh'] = threshVal
                    bestStump['ineq'] = inequal
    return bestStump,minError,bestClasEst


##D = np.mat(np.ones((5,1))/5)
##buildStump(datMat,classLabels,D)


def adaBoostTrainDS(dataArr,classLabels,numIt=40):
    from numpy import log,exp,sign
    
    weakClassArr = []
    m = np.shape(dataArr)[0]
    D = np.mat(np.ones((m,1))/m)   #init D to all equal
    aggClassEst = np.mat(np.zeros((m,1)))
    for i in range(numIt):
        bestStump,error,classEst = buildStump(dataArr,classLabels,D)#build Stump
        #print ("D:",D.T)
        alpha = float(0.5*log((1.0-error)/max(error,1e-16)))#calc alpha, throw in max(error,eps) to account for error=0
        bestStump['alpha'] = alpha  
        weakClassArr.append(bestStump)                  #store Stump Params in Array
        #print "classEst: ",classEst.T
        expon = np.multiply(-1*alpha*np.mat(classLabels).T,classEst) #exponent for D calc, getting messy
        D = np.multiply(D,exp(expon))                              #Calc New D for next iteration
        D = D/D.sum()
        #calc training error of all classifiers, if this is 0 quit for loop early (use break)
        aggClassEst += alpha*classEst
        #print "aggClassEst: ",aggClassEst.T
        aggErrors = np.multiply(sign(aggClassEst) != np.mat(classLabels).T,np.ones((m,1)))
        errorRate = aggErrors.sum()/m
        #print ("total error: ",errorRate)
        if errorRate == 0.0: break
    return weakClassArr,aggClassEst


##classifierArray,aggClassEst = adaBoostTrainDS(datMat,classLabels,9)
##print(classifierArray)
##print(aggClassEst)

def adaClassify(datToClass,classifierArr):
    dataMatrix = np.mat(datToClass)#do stuff similar to last aggClassEst in adaBoostTrainDS
    m = np.shape(dataMatrix)[0]
    aggClassEst = np.mat(np.zeros((m,1)))
    for i in range(len(classifierArr)):
        classEst = stumpClassify(dataMatrix,classifierArr[i]['dim'],\
                                 classifierArr[i]['thresh'],\
                                 classifierArr[i]['ineq'])#call stump classify
        #print(classEst)
        aggClassEst += classifierArr[i]['alpha']*classEst
        #print (aggClassEst)
    return np.sign(aggClassEst)

##print(adaClassify([0,0],classifierArray))

def loadDataSet(fileName):
    numFeat = len((open(fileName).readline().split('\t')))
    dataMat = []; labelMat = []
    fr = open(fileName)
    for line in fr.readlines():
        lineArr = []
        curLine = line.strip().split('\t')
        for i in range(numFeat - 1):
            lineArr.append(float(curLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(curLine[-1]))
    return dataMat, labelMat


datArr,labelArr = loadDataSet('horseColicTraining2.txt')
##print(np.shape(datArr))
##print(np.shape(labelArr))
#过拟合，过学习
##classifierArray,aggClassEst = adaBoostTrainDS(datArr,labelArr,1000)
classifierArray,aggClassEst = adaBoostTrainDS(datArr,labelArr,10)
##print(classifierArray)

testArr,testLabelArr = loadDataSet('horseColicTest2.txt')
##prediction1000 = adaClassify(testArr,classifierArray)
prediction10 = adaClassify(testArr,classifierArray)
errArr = np.mat(np.ones((67,1)))
##print(errArr[prediction1000 != np.mat(testLabelArr).T].sum())
##print("error rate:",errArr[prediction1000 != np.mat(testLabelArr).T].sum()/67)
print(errArr[prediction10 != np.mat(testLabelArr).T].sum())
print("error rate:",errArr[prediction10 != np.mat(testLabelArr).T].sum()/67)

def plotROC(predStrengths, classLabels):
    import matplotlib.pyplot as plt
    cur = (1.0,1.0) #cursor
    ySum = 0.0 #variable to calculate AUC
    numPosClas = sum(np.array(classLabels)==1.0)
    yStep = 1/float(numPosClas); xStep = 1/float(len(classLabels)-numPosClas)
    sortedIndicies = predStrengths.argsort()#get sorted index, it's reverse
    fig = plt.figure()
    fig.clf()
    ax = plt.subplot(111)
    #loop through all the values, drawing a line segment at each point
    for index in sortedIndicies.tolist()[0]:
        if classLabels[index] == 1.0:
            delX = 0; delY = yStep;
        else:
            delX = xStep; delY = 0;
            ySum += cur[1]
        #draw line from cur to (cur[0]-delX,cur[1]-delY)
        ax.plot([cur[0],cur[0]-delX],[cur[1],cur[1]-delY], c='b')
        cur = (cur[0]-delX,cur[1]-delY)
        #print(cur)
    ax.plot([0,1],[0,1],'b--')
    plt.xlabel('False positive rate'); plt.ylabel('True positive rate')
    plt.title('ROC curve for AdaBoost horse colic detection system')
    ax.axis([0,1,0,1])
    plt.show()
    print ("the Area Under the Curve is: ",ySum*xStep)

plotROC(aggClassEst.T,labelArr)