机器学习实战之AdaBoost

最新推荐文章于 2022-10-29 15:00:00 发布

steph_curry

最新推荐文章于 2022-10-29 15:00:00 发布

阅读量288

点赞数

分类专栏：机器学习

本文链接：https://blog.youkuaiyun.com/steph_curry/article/details/79657532

版权

机器学习专栏收录该内容

16 篇文章

订阅专栏

本文介绍了一个使用AdaBoost算法进行分类预测的Python实现案例。通过加载训练数据集并应用AdaBoost训练得到弱分类器集合，再利用该集合对测试数据进行分类，并计算错误率。文章详细展示了每一步的代码实现。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import numpy
from numpy import *
import matplotlib.pyplot as plt
def loadSimpleData():
    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={};bestClassEst=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;
                predictVals=stumpClassify(dataMatrix,i,threshVal,inequal)
                errArr=mat(ones((m,1)))
                errArr[predictVals==labelMat]=0
                weightedError=D.T*errArr
                print("split:dim %d,thresh %.2f,thresh inequal:%s,the weighted error is %.3f"%\
                      (i,threshVal,inequal,weightedError))
                if weightedError<minError:
                    minError=weightedError
                    bestStump['dim']=i
                    bestStump['threshVal']=threshVal
                    bestStump['ineq']=inequal
                    bestClassEst=predictVals.copy()
    return bestStump,minError,bestClassEst

def adaBoostTrainDS(dataArr,classLabels,nunIt=40):
    weakClassArr=[]
    m=shape(dataArr)[0]
    D=mat(ones((m,1))/m)
    aggClassEst=mat(zeros((m,1)))
    for i in range(nunIt):
        bestStump,error,classEst=buildStump(dataArr,classLabels,D)
        print('D:',D.T)
        alpha=float(0.5*log((1.0-error)/max(error,1e-16)))
        bestStump['alpha']=alpha
        weakClassArr.append(bestStump)
        print('classEst:',classEst.T)
        expon=multiply(-1*alpha*mat(classLabels).T,classEst)
        D=multiply(D,exp(expon))
        D=D/D.sum()
        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

def adaClassify(datToClass,classifierArr):
    dataMatrix=mat(datToClass)
    m=shape(dataMatrix)[0]
    aggClassEst=mat(zeros((m,1)))
    for i in range(len(classifierArr)):
        classEst=stumpClassify(dataMatrix,classifierArr[i]['dim'],\
                               classifierArr[i]['threshVal'],\
                               classifierArr[i]['ineq'])
        aggClassEst+=classifierArr[i]['alpha']*classEst
        print(aggClassEst)
    return sign(aggClassEst)

def loadDataSet(filename):
    numFeat=len(open(filename).readline().split('\t'))
    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

        
data,labels=loadDataSet(r'C:/Users/huashuo111/Desktop/python/machinelearninginaction/Ch07/horseColicTraining2.txt')
weakClassArr=adaBoostTrainDS(data,labels,1)
testArr,testLabelArr=loadDataSet(r'C:/Users/huashuo111/Desktop/python/machinelearninginaction/Ch07/horseColicTest2.txt')
prediction1=adaClassify(testArr,weakClassArr)
errArr=mat(ones((67,1)))
a=errArr[prediction1!=mat(testLabelArr).T].sum()
print(a)