adaboost算法Python

下面是一个简单的Adaboost算法的Python代码示例：

from numpy import *

def loadSimpData():
    dataMat = 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 dataMat,classLabels

def stumpClassify(dataMatrix,dimen,threshVal,threshIneq):
    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 
    for i in range(n):
        rangeMin = dataMatrix[:,i].min()
        rangeMax = dataMatrix[:,i].max()
        stepSize = (rangeMax-rangeMin)/numSteps
        for j in range(-1,int(numSteps)+1):
            for inequal in ['lt', 'gt']:
                threshVal = (rangeMin + float(j) * stepSize)
                predictedVals = stumpClassify(dataMatrix,i,threshVal,inequal)
                errArr = mat(ones((m,1)))
                errArr[predictedVals == labelMat] = 0
                weightedError = D.T*errArr  
                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)   
    aggClassEst = mat(zeros((m,1)))
    for i in range(numIt):
        bestStump,error,classEst = buildStump(dataArr,classLabels,D)
        alpha = float(0.5*log((1.0-error)/max(error,1e-16)))
        bestStump['alpha'] = alpha  
        weakClassArr.append(bestStump)                  
        expon = multiply(-1*alpha*mat(classLabels).T,classEst) 
        D = multiply(D,exp(expon))                              
        D = D/D.sum()
        aggClassEst += alpha*classEst
        aggErrors = multiply(sign(aggClassEst) != mat(classLabels).T,ones((m,1)))
        errorRate = aggErrors.sum()/m
        if errorRate == 0.0: break
    return weakClassArr,aggClassEst

dataMat,classLabels = loadSimpData()
classifierArray,aggClassEst = adaBoostTrainDS(dataMat,classLabels)
print(classifierArray)

该代码实现了简单数据集的Adaboost算法，其中buildStump函数实现了弱分类器的构建，adaBoostTrainDS函数实现了Adaboost模型的训练。