(转载请注明出处:http://blog.csdn.net/buptgshengod)
Adaboost是用元算法的思想进行分类的。
什么事元算法的思想呢?就是依据数据集的不同的特征在决定结果时所占的比重来划分数据集。就是要对每一个特征值都构建决策树,而且赋予他们不同的权值,最后集合起来比較。
这样就比0.5:0.5的权重来的更准确些。
ef 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):#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
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
{'dim': 0, 'ineq': 'lt', 'thresh': 1.3}——第一个特征值权重最大。阈值是1.3
[[ 0.2]]——错误率0.2,也就是五个错一个
[[-1.]————推断结果。第一个数据错误
[ 1.]
[-1.]
[-1.]
[ 1.]]
[1] machine learning in action,Peter Harrington