最大公共子序列 动态规划算法 可参考http://blog.csdn.net/HerosOfEarth/article/category/6364820
基于单层决策树构建弱分类器
相关函数
from numpy import *
def loadSimpData(): #读取数据集
datMat = 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 datMat,classLabels
def stumpClassify(dataMatrix,dimen,threshVal,threshIneq):#just classify the data 将在阈值一边的分到1，另一边的分到-1
retArray = ones((shape(dataMatrix)[0],1)) #先将数组的全部元素设置为1
if threshIneq == 'lt': #这句话？less than
retArray[dataMatrix[:,dimen] <= threshVal] = -1.0
else:
retArray[dataMatrix[:,dimen] > threshVal] = -1.0
return retArray #需要注意了，这里的标签是 +1 和 -1 两类-----和SVM一样
def buildStump(dataArr,classLabels,D): #这里的D是权重向量,也是Adaboost和分类器交互的关键系数!!!
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 初始化为无穷大
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 #代表从-1到int(numSteps)+1(不包含int(numSteps)+1)
for inequal in ['lt', 'gt']: #go over less than and greater than
threshVal = (rangeMin + float(j) * stepSize) #阈值
predictedVals = stumpClassify(dataMatrix,i,threshVal,inequal)#call stump classify with i, j, lessThan
errArr = mat(ones((m,1))) #如果分类错误则为1----误差函数
errArr[predictedVals == labelMat] = 0 #如果分类正确则为0
weightedError = D.T*errArr #calc total error multiplied by D----权重误差函数
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 #首先是第几维
bestStump['thresh'] = threshVal #其实是阈值的设置
bestStump['ineq'] = inequal #在者就是大于 还是 小于
return bestStump,minError,bestClasEst #这样就可以得到一个最佳的单层决策树,注意了，这里的bestStump是一个字典
测试代码
import adaboost from numpy import * dataMat, classLabels = adaboost.loadSimpData() D = mat(ones((5,1))/5) print adaboost.buildStump(dataMat, classLabels, D)
结果
split: dim 0, thresh 0.90, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 0.90, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.00, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 1.00, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.10, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 1.10, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.20, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 1.20, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.30, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.30, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.40, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.40, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.50, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.50, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.60, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.60, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.70, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.70, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.80, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.80, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.90, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.90, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 2.00, thresh ineqal: lt, the weighted error is 0.600
split: dim 0, thresh 2.00, thresh ineqal: gt, the weighted error is 0.400
split: dim 1, thresh 0.89, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 0.89, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.00, thresh ineqal: lt, the weighted error is 0.200
split: dim 1, thresh 1.00, thresh ineqal: gt, the weighted error is 0.800
split: dim 1, thresh 1.11, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.11, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.22, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.22, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.33, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.33, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.44, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.44, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.55, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.55, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.66, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.66, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.77, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.77, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.88, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.88, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.99, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.99, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 2.10, thresh ineqal: lt, the weighted error is 0.600
split: dim 1, thresh 2.10, thresh ineqal: gt, the weighted error is 0.400
({'dim': 0, 'ineq': 'lt', 'thresh': 1.3}, matrix([[ 0.2]]), array([[-1.],
[ 1.],
[-1.],
[-1.],
[ 1.]]))
完整AdaBoost算法的实现
训练
相关函数
def adaBoostTrainDS(dataArr,classLabels,numIt=40): #基于单层决策树的AdaBoost训练过程
weakClassArr = [] #弱分类器数组
m = shape(dataArr)[0] #指代样本个数
D = mat(ones((m,1))/m) #init D to all equal 权重向量的值初始化为相等。
aggClassEst = mat(zeros((m,1))) #记录每个数据点的类别估计累计值,初始化为0
for i in range(numIt): #开始迭代进程
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 防止出现错误率为0的情况
bestStump['alpha'] = alpha
weakClassArr.append(bestStump) #store Stump Params in Array 字典存储到若分类器列表中
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))) #python sign()函数
errorRate = aggErrors.sum()/m #得到错误率
print "total error: ",errorRate
if errorRate == 0.0: break
return weakClassArr,aggClassEst
测试函数
#AdaBoost算法的训练 classifierArray = adaboost.adaBoostTrainDS(dataMat,classLabels,numIt=40) print classifierArray结果
split: dim 0, thresh 0.90, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 0.90, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.00, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 1.00, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.10, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 1.10, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.20, thresh ineqal: lt, the weighted error is 0.400
split: dim 0, thresh 1.20, thresh ineqal: gt, the weighted error is 0.600
split: dim 0, thresh 1.30, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.30, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.40, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.40, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.50, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.50, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.60, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.60, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.70, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.70, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.80, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.80, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 1.90, thresh ineqal: lt, the weighted error is 0.200
split: dim 0, thresh 1.90, thresh ineqal: gt, the weighted error is 0.800
split: dim 0, thresh 2.00, thresh ineqal: lt, the weighted error is 0.600
split: dim 0, thresh 2.00, thresh ineqal: gt, the weighted error is 0.400
split: dim 1, thresh 0.89, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 0.89, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.00, thresh ineqal: lt, the weighted error is 0.200
split: dim 1, thresh 1.00, thresh ineqal: gt, the weighted error is 0.800
split: dim 1, thresh 1.11, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.11, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.22, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.22, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.33, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.33, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.44, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.44, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.55, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.55, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.66, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.66, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.77, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.77, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.88, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.88, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 1.99, thresh ineqal: lt, the weighted error is 0.400
split: dim 1, thresh 1.99, thresh ineqal: gt, the weighted error is 0.600
split: dim 1, thresh 2.10, thresh ineqal: lt, the weighted error is 0.600
split: dim 1, thresh 2.10, thresh ineqal: gt, the weighted error is 0.400
D: [[ 0.2 0.2 0.2 0.2 0.2]]
classEst: [[-1. 1. -1. -1. 1.]]
aggClassEst: [[-0.69314718 0.69314718 -0.69314718 -0.69314718 0.69314718]]
total error: 0.2
split: dim 0, thresh 0.90, thresh ineqal: lt, the weighted error is 0.250
split: dim 0, thresh 0.90, thresh ineqal: gt, the weighted error is 0.750
split: dim 0, thresh 1.00, thresh ineqal: lt, the weighted error is 0.625
split: dim 0, thresh 1.00, thresh ineqal: gt, the weighted error is 0.375
split: dim 0, thresh 1.10, thresh ineqal: lt, the weighted error is 0.625
split: dim 0, thresh 1.10, thresh ineqal: gt, the weighted error is 0.375
split: dim 0, thresh 1.20, thresh ineqal: lt, the weighted error is 0.625
split: dim 0, thresh 1.20, thresh ineqal: gt, the weighted error is 0.375
split: dim 0, thresh 1.30, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.30, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 1.40, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.40, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 1.50, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.50, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 1.60, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.60, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 1.70, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.70, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 1.80, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.80, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 1.90, thresh ineqal: lt, the weighted error is 0.500
split: dim 0, thresh 1.90, thresh ineqal: gt, the weighted error is 0.500
split: dim 0, thresh 2.00, thresh ineqal: lt, the weighted error is 0.750
split: dim 0, thresh 2.00, thresh ineqal: gt, the weighted error is 0.250
split: dim 1, thresh 0.89, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 0.89, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.00, thresh ineqal: lt, the weighted error is 0.125
split: dim 1, thresh 1.00, thresh ineqal: gt, the weighted error is 0.875
split: dim 1, thresh 1.11, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.11, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.22, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.22, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.33, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.33, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.44, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.44, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.55, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.55, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.66, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.66, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.77, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.77, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.88, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.88, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 1.99, thresh ineqal: lt, the weighted error is 0.250
split: dim 1, thresh 1.99, thresh ineqal: gt, the weighted error is 0.750
split: dim 1, thresh 2.10, thresh ineqal: lt, the weighted error is 0.750
split: dim 1, thresh 2.10, thresh ineqal: gt, the weighted error is 0.250
D: [[ 0.5 0.125 0.125 0.125 0.125]]
classEst: [[ 1. 1. -1. -1. -1.]]
aggClassEst: [[ 0.27980789 1.66610226 -1.66610226 -1.66610226 -0.27980789]]
total error: 0.2
split: dim 0, thresh 0.90, thresh ineqal: lt, the weighted error is 0.143
split: dim 0, thresh 0.90, thresh ineqal: gt, the weighted error is 0.857
split: dim 0, thresh 1.00, thresh ineqal: lt, the weighted error is 0.357
split: dim 0, thresh 1.00, thresh ineqal: gt, the weighted error is 0.643
split: dim 0, thresh 1.10, thresh ineqal: lt, the weighted error is 0.357
split: dim 0, thresh 1.10, thresh ineqal: gt, the weighted error is 0.643
split: dim 0, thresh 1.20, thresh ineqal: lt, the weighted error is 0.357
split: dim 0, thresh 1.20, thresh ineqal: gt, the weighted error is 0.643
split: dim 0, thresh 1.30, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.30, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 1.40, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.40, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 1.50, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.50, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 1.60, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.60, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 1.70, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.70, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 1.80, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.80, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 1.90, thresh ineqal: lt, the weighted error is 0.286
split: dim 0, thresh 1.90, thresh ineqal: gt, the weighted error is 0.714
split: dim 0, thresh 2.00, thresh ineqal: lt, the weighted error is 0.857
split: dim 0, thresh 2.00, thresh ineqal: gt, the weighted error is 0.143
split: dim 1, thresh 0.89, thresh ineqal: lt, the weighted error is 0.143
split: dim 1, thresh 0.89, thresh ineqal: gt, the weighted error is 0.857
split: dim 1, thresh 1.00, thresh ineqal: lt, the weighted error is 0.500
split: dim 1, thresh 1.00, thresh ineqal: gt, the weighted error is 0.500
split: dim 1, thresh 1.11, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.11, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.22, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.22, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.33, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.33, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.44, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.44, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.55, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.55, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.66, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.66, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.77, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.77, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.88, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.88, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 1.99, thresh ineqal: lt, the weighted error is 0.571
split: dim 1, thresh 1.99, thresh ineqal: gt, the weighted error is 0.429
split: dim 1, thresh 2.10, thresh ineqal: lt, the weighted error is 0.857
split: dim 1, thresh 2.10, thresh ineqal: gt, the weighted error is 0.143
D: [[ 0.28571429 0.07142857 0.07142857 0.07142857 0.5 ]]
classEst: [[ 1. 1. 1. 1. 1.]]
aggClassEst: [[ 1.17568763 2.56198199 -0.77022252 -0.77022252 0.61607184]]
total error: 0.0
([{'dim': 0, 'ineq': 'lt', 'thresh': 1.3, 'alpha': 0.6931471805599453}, {'dim': 1, 'ineq': 'lt', 'thresh': 1.0, 'alpha': 0.9729550745276565}, {'dim': 0, 'ineq': 'lt', 'thresh': 0.90000000000000002, 'alpha': 0.8958797346140273}], matrix([[ 1.17568763],
[ 2.56198199],
[-0.77022252],
[-0.77022252],
[ 0.61607184]]))
基于AdaBoost的分类
是
相关函数
def adaClassify(datToClass,classifierArr):
dataMatrix = mat(datToClass)#do stuff similar to last aggClassEst in adaBoostTrainDS
m = shape(dataMatrix)[0] #待分类样本个数
aggClassEst = mat(zeros((m,1))) #类别向量
for i in range(len(classifierArr)): #指代弱分类器数量
classEst = stumpClassify(dataMatrix,classifierArr[i]['dim'],\
classifierArr[i]['thresh'],\
classifierArr[i]['ineq'])#call stump classify 计算每个弱分类器的输出类别向量
aggClassEst += classifierArr[i]['alpha']*classEst #进行加权求和
print aggClassEst
return sign(aggClassEst) #输出为标准的-1 +1测试代码
print adaboost.adaClassify([0,0], classifierArray)结果
[[-0.69314718]]
[[-1.66610226]]
[[-2.56198199]]
[[-1.]]
在一个难数据集上应用AdaBoost
训练代码
#测试马的疾病
dataArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray = adaboost.adaBoostTrainDS(dataArr, labelArr, 10)
结果：
0.20691998 0.49937436 1.13595343 -0.01293737 -0.29542349 0.84485519
0.83188488 0.34364609 0.54030781 0.95675902 0.90429525 0.83188488
-0.65208904 -0.40165729 -1.58160132 0.38313956 -0.32924692 0.69768794
1.47224468 1.22748297 0.83188488 1.42269911 -0.65827656 -0.35372918
-0.01293737 1.53203035 0.95841088 -1.04249592 0.23749438 0.5606821
1.20719077 0.91726555 -0.10329743 -0.57967867 0.27123572 1.69342306
0.05809528 -0.65208904 -1.02662219 0.27123572 0.5606821 ]]
total error: 0.230769230769
测试代码
testArr, testLabelArr = adaboost.loadDataSet('horseColicTest2.txt')
prediction = adaboost.adaClassify(testArr, classifierArray)
errArr = mat(ones((67,1)))
print errArr[prediction != mat(testLabelArr).T].sum()/67
结果
0.238805970149