机器学习实战（7） ——利用AdaBoost元算法提高分类性能（python实现）

这是学习机器学习算法实战这本书时，写的代码实战。让自己对各个算法有更直观的了解，不能一直不写啊。不管简单还是不简单都亲自一行一行的敲一遍啊。

具体的源码和和数据链接：https://pan.baidu.com/s/1G2S2pb5gfBnxGNNTFgTkEA 密码：fov0

下面是是第七章写的adaboost.py程序

# -*- coding: utf-8 -*-
# author: Yufeng Song
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 #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 = mat(ones((m,1)))
                errArr[predictedVals == labelMat] = 0
                print ("predictedVals",predictedVals.T,"errArr",errArr.T)
                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

def adaBoostTrainDS(dataArr,classLabels,numIt=40):
    weakClassArr = []
    m = shape(dataArr)[0]
    D = mat(ones((m,1))/m)
    aggClassEst = mat(zeros((m,1)))
    for i in range(numIt):
        bestStump,error,classEst = buildStump(dataArr,classlabels,D)
        print("D:",D.T)
        alpha = float(0.5*log((1.0-error)/max(error,1e-16)))
        bestStump['alpha'] = alpha
        weakClassArr.append(bestStump)
        print("classEst:",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 eror:",errorRate,"\n")
        if errorRate == 0.0: break
    return weakClassArr

def adaClassify(datToClass,classifierArr):
    dataMatrix = mat(datToClass)
    m = shape(dataMatrix)[0]
    aggClassEst = mat(zeros((m,1)))
    for i in range(len(classifierArr)):
        classEst = stumpClassify(dataMatrix,classifierArr[i]['dim'],
                                 classifierArr[i]['thresh'],
                                 classifierArr[i]['ineq'])
        aggClassEst += classifierArr[i]['alpha']*classEst
        print(aggClassEst)
    return sign(aggClassEst)

def loadDataSet(fileName):
    numFeat = len(open(fileName).readlines().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(float(curLine[-1]))
        labelMat.append(float(curLine[-1]))
    return dataMat,labelMat

def plotROC(predStrengths,classLabels):
    import matplotlib.pyplot as plt
    cur = (1.0,1.0)
    ySum = 0.0
    numPosClas = sum(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)
    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)
if __name__ == '__main__':
    dataMatrix,classlabels=loadSimpData()
    # print(dataMatrix)
    # print(stumpClassify(dataMatrix,0,1.4,'lt'))
    D = mat(ones((5,1))/5)
    print(D)
    print(buildStump(dataMatrix,classlabels,D))
    print(adaBoostTrainDS(dataMatrix,classlabels,9))