08 ML AdaBoost

from: ML In Action

'''
Created on Nov 28, 2010
Adaboost is short for Adaptive Boosting
@author: Peter
'''
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 loadDataSet(fileName):      #general function to parse tab -delimited floats
    numFeat = len(open(fileName).readline().split('\t')) #get number of fields 
    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

def stumpClassify(dataMatrix,dimen,threshVal,threshIneq):#just classify the data
    retArray = ones((shape(dataMatrix)[0],1))
    if threshIneq == 'lt':
        retArray[dataMatrix[:,dimen] <= threshVal] = -1.0
    else:
        retArray[dataMatrix[:,dimen] > threshVal] = -1.0
    return retArray
    
# 计算最佳单层决策树
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): # 在数据集的所有特征上遍历
        rangeMin = dataMatrix[:,i].min(); 
        rangeMax = dataMatrix[:,i].max();

        stepSize = (rangeMax-rangeMin)/numSteps

        # 再在这些值上遍历
        for j in range(-1,int(numSteps)+1):#loop over all range in current dimension

            # 大于小于之间切换不等式
            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
                weightedError = D.T*errArr  # 计算加权错误率

                #print "split: dim %d, thresh %.2f, thresh ineqal: %s, the weighted error is %.3f" % (i, threshVal, inequal, weightedError)
                # 低于最低错误率 则将当前最佳单层决策树设为最佳
                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)   #init D to all equal
    aggClassEst = mat(zeros((m,1)))

    # 不断训练直到调整权重后 训练错误率为0或者达到用户指定的数为止
    for i in range(numIt):
        # 找到最佳的单层决策树
        bestStump,error,classEst = buildStump(dataArr,classLabels,D)#build Stump
        #print "D:",D.T

        # alpha 为每个分类器的权重
        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  

        # 添加到弱分类器组中
        weakClassArr.append(bestStump)                  #store Stump Params in Array
        #print "classEst: ",classEst.T
        
        expon = multiply(-1*alpha*mat(classLabels).T, classEst) #exponent for D calc, getting messy
        
        # 计算新的权重向量D 正确分类的样本权重变低 错误的变高
        D = 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 = multiply(sign(aggClassEst) != mat(classLabels).T,ones((m,1)))
        errorRate = aggErrors.sum()/m
        print "total error: ",errorRate

        if errorRate == 0.0: # 错误率为0
            break
    return weakClassArr

def adaClassify(datToClass,classifierArr):
    dataMatrix  = mat(datToClass)#do stuff similar to last aggClassEst in adaBoostTrainDS
    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'])#call stump classify
        
        aggClassEst += classifierArr[i]['alpha']*classEst
        print aggClassEst

    return sign(aggClassEst)

def plotROC(predStrengths, classLabels):
    import matplotlib.pyplot as plt
    cur = (1.0,1.0) #cursor
    ySum = 0.0 #variable to calculate AUC
    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