2019独角兽企业重金招聘Python工程师标准>>> 
阅读原文
一.Adaboost理论部分
1.1 adaboost运行过程
注释：算法是利用指数函数降低误差，运行过程通过迭代进行。其中函数的算法怎么来的，你不用知道！当然你也可以尝试使用其它的函数代替指数函数，看看效果如何。
1.2 举例说明算法流程
略，花几分钟就可以看懂的例子。见：《统计学习方法》李航大大
1.3 算法误差界的证明
注释：误差的上界限由Zm约束，然而Zm又是由Gm(xi)约束，所以选择适当的Gm(xi)可以加快误差的减小。
二.代码实现
注释：这里参考大神博客http://blog.csdn.net/guyuealian/article/details/70995333，举例子很详细。
2.1程序流程图
2.2基本程序实现
注释：真是倒霉玩意，本来代码全部注释好了，突然Ubuntu奔溃了，全部程序就GG了。。。下面的代码就是官网的代码，部分补上注释。现在使用Deepin桌面版了，其它方面都比Ubuntu好，但是有点点卡。
from numpy import *
def loadDataSet(fileName): #general function to parse tab -delimited floats
numFeat = len(open(fileName).readline().split('\t')) #get number of fields
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
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
def adaBoostTrainDS(dataArr,classLabels,numIt=40):
weakClassArr = []
m = shape(dataArr)[0]
D = mat(ones((m,1))/m) #init D to all equal
aggClassEst = mat(zeros((m,1)))
for i in range(numIt):
bestStump,error,classEst = buildStump(dataArr,classLabels,D)#build Stump
#print "D:",D.T
alpha = float(0.5*log((1.0-error)/max(error,1e-16)))#calc alpha, throw in max(error,eps) to account for error=0
bestStump['alpha'] = alpha
weakClassArr.append(bestStump) #store Stump Params in Array
#print "classEst: ",classEst.T
expon = multiply(-1*alpha*mat(classLabels).T,classEst) #exponent for D calc, getting messy
D = multiply(D,exp(expon)) #Calc New D for next iteration
D = D/D.sum()
#calc training error of all classifiers, if this is 0 quit for loop early (use break)
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,aggClassEst
def adaClassify(datToClass,classifierArr):
dataMatrix = mat(datToClass)#do stuff similar to last aggClassEst in adaBoostTrainDS
m = shape(dataMatrix)[0]
aggClassEst = mat(zeros((m,1)))
for i in range(len(classifierArr)):
classEst = stumpClassify(dataMatrix,classifierArr[i]['dim'],\
classifierArr[i]['thresh'],\
classifierArr[i]['ineq'])#call stump classify
aggClassEst += classifierArr[i]['alpha']*classEst
#print aggClassEst
return sign(aggClassEst)
def plotROC(predStrengths, classLabels):
import matplotlib.pyplot as plt
cur = (1.0,1.0) #cursor
ySum = 0.0 #variable to calculate AUC
numPosClas = sum(array(classLabels)==1.0)#标签等于1的和（也等于个数）
yStep = 1/float(numPosClas); xStep = 1/float(len(classLabels)-numPosClas)
sortedIndicies = predStrengths.argsort()#get sorted index, it's reverse
sortData = sorted(predStrengths.tolist()[0])
fig = plt.figure()
fig.clf()
ax = plt.subplot(111)
#loop through all the values, drawing a line segment at each point
for index in sortedIndicies.tolist()[0]:
if classLabels[index] == 1.0:
delX = 0; delY = yStep;
else:
delX = xStep; delY = 0;
ySum += cur[1]
#draw line from cur to (cur[0]-delX,cur[1]-delY)
ax.plot([cur[0],cur[0]-delX],[cur[1],cur[1]-delY], c='b')
cur = (cur[0]-delX,cur[1]-delY)
ax.plot([0,1],[0,1],'b--')
plt.xlabel('False positive rate'); plt.ylabel('True positive rate')
plt.title('ROC curve for AdaBoost horse colic detection system')
ax.axis([0,1,0,1])
plt.show()
print ("the Area Under the Curve is: ",ySum*xStep)
复制代码
注释：重点说明一下非均衡分类的图像绘制问题，想了很久才想明白！
都是相对而言的，其中本文说的曲线在左上方就为好，也是相对而言的，看你怎么定义个理解！
相关阅读: 十大经典数据挖掘算法——PageRank