from?numpy?import?*
import?string

#parse?files?function?every?data?is?a?integer
def?loadDataSet（filename）:
????numFeat?=?len（open（filename）.readline（）.split（‘‘））
????dataMat?=?[]
????labelMat=[]
????fr?=?open（filename）
????for?line?in?fr.readlines（）:
????????lineArr=?[]
????????curLine?=?line.strip（‘\n‘）.split（‘‘）
????????for?i?in?range（1?numFeat）:
????????????lineArr.append（int（curLine[i]））
????????dataMat.append（lineArr）
????????labelMat.append（curLine[0]）
????fr.close（）
????return?dataMat?labelMat
‘‘‘‘‘
purpose:?data?classify?by?compare?to?threshold
‘‘‘
def?stumpClassify（dataMatrix?dimen?threshVal?threshIneq）:
????retArray?=?ones（（shape（dataMatrix）[0]1））
????if?threshIneq?==?‘lt‘:
????????retArray[dataMatrix[:dimen]????else:
????????retArray[dataMatrix[:dimen]????return?retArray
‘‘‘‘‘
purpose:?single?level?decision?tree?create?function（weak?classify?device）
input:??dataArr:?dataSet?classLabels:class?label?D:data?weight
output:??bestStump:?single?level?decision?tree?having?min?error?rate?minError:?min?Error?rate
?????????bestClassEst:?estimate?class?labels
‘‘‘
def?buildStump（dataArrclassLabelsD）:
????dataMatrix?=?mat（dataArr）;?labelMat?=?mat（classLabels）.T
????mn?=?shape（dataMatrix）
????numSteps?=?10.0
????#?define?a?empty?dictionary?for?store?Dthe?better?single?level?tree?info
????bestStump?=?{}
????bestClasEst?=?mat（zeros（（m1）））
????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（-1int（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（dataMatrixithreshValinequal）#call?stump?classify?with?i?j?lessThan
????????????????errArr?=?mat（ones（（m1）））?#?create?error?array
????????????????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?=?weightedError
????????????????????bestClasEst?=?predictedVals.copy（）
????????????????????bestStump[‘dim‘]?=?i
????????????????????bestStump[‘thresh‘]?=?threshVal
????????????????????bestStump[‘ineq‘]?=?inequal
????return?bestStumpminErrorbestClasEst

‘‘‘‘‘
purpose:whole?AdaBoost?algorithm
input?parameter:
dataArr:data?set
classLabels:class?labels
numIt:die?dai?number?（only?one?parameter?needed?user?to?specified）
output?parameter:
weakClassArr:seve