机器学习实战读书笔记----利用Adaboost元算法提高分类性能

总结一下boosting与bagging：boosting是一种通过串行训练得到的分类器，每个新分类器都根据已经训练出的分类器性能进行训练，boosting是集中关注被已有分类器错分的那些数据来获得的新的分类器。由于boosting分类的结果是基于所有分类起的加权求和结果的，因此二者不太一样。bagging中的分类器权重是相等的，而boosting中的分类器权重不相等，每个权重代表的是其对应分类器在上一轮迭代中的成功度。

下面附上利用决策树桩构造的Adaboost算法代码：

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

#这里使用的分类器为决策树桩（Decision Stump）
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
#利用三个循环选择在当前数据权值D下最好的分类器
#第一个循环用来遍历所有的特征，确定特征的上界和下界，根据设置的步数算出每一步的长度
#第二个循环用来遍历当前特征下用来分类的阈值，相当于在N个样本中插入N+1个点
#第三个循环用来遍历判断方向，是大于阈值判断为正例还是小于阈值判断为正例，
#调用stumpClassify()函数返回预测结果并与实际结果比较，结合权重向量D计算出损失代价，选择循环中是损失代价最小的决策树桩
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
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

#初始权重设为1/N，设置停止条件为达到最大分类器个数或errorRate为0
#每次增加错误分类样本的权重，减少正确分类样本的权重
#正确率高的分类器权重分配大，错误率高的分类器权重分配小
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)))
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 = multiply(-1*alpha*mat(classLabels).T,classEst) #exponent for D calc, getting messy
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: break
return weakClassArr,aggClassEst

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)