单层决策树python_【机器学习算法-python实现】Adaboost的实现(1)-单层决策树(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

最后是构建二叉树函数，通过循环比較得到最佳特征值和它的阈值。D是初始矩阵的权重。

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

3.结果