svm手写数字识别python_吴裕雄--天生自然python机器学习：基于支持向量机SVM的手写数字识别...

from numpy import *

defimg2vector(filename):

returnVect= zeros((1,1024))

fr=open(filename)for i in range(32):

lineStr=fr.readline()for j in range(32):

returnVect[0,32*i+j] =int(lineStr[j])returnreturnVectdefloadImages(dirName):from os importlistdir

hwLabels=[]

trainingFileList= listdir(dirName) #load the training set

m =len(trainingFileList)

trainingMat= zeros((m,1024))for i inrange(m):

fileNameStr=trainingFileList[i]

fileStr= fileNameStr.split('.')[0] #take off .txt

classNumStr = int(fileStr.split('_')[0])if classNumStr == 9: hwLabels.append(-1)else: hwLabels.append(1)

trainingMat[i,:]= img2vector('%s/%s' %(dirName, fileNameStr))returntrainingMat, hwLabelsdef smoP(dataMatIn, classLabels, C, toler, maxIter,kTup=('lin', 0)): #full Platt SMO

oS =optStruct(mat(dataMatIn),mat(classLabels).transpose(),C,toler, kTup)

iter=0

entireSet=True

alphaPairsChanged=0while (iter < maxIter) and ((alphaPairsChanged > 0) or(entireSet)):

alphaPairsChanged=0if entireSet: #go over all

for i inrange(oS.m):

alphaPairsChanged+=innerL(i,oS)print("fullSet, iter: %d i:%d, pairs changed %d" %(iter,i,alphaPairsChanged))

iter+= 1

else:#go over non-bound (railed) alphas

nonBoundIs = nonzero((oS.alphas.A > 0) * (oS.alphas.A

alphaPairsChanged+=innerL(i,oS)print("non-bound, iter: %d i:%d, pairs changed %d" %(iter,i,alphaPairsChanged))

iter+= 1

if entireSet: entireSet = False #toggle entire set loop

elif (alphaPairsChanged == 0): entireSet =Trueprint("iteration number: %d" %iter)returnoS.b,oS.alphasdef testDigits(kTup=('rbf', 10)):

dataArr,labelArr= loadImages('F:\machinelearninginaction\Ch06\trainingDigits')

b,alphas= smoP(dataArr, labelArr, 200, 0.0001, 10000, kTup)

datMat=mat(dataArr)

labelMat=mat(labelArr).transpose()

svInd=nonzero(alphas.A>0)[0]

sVs=datMat[svInd]

labelSV=labelMat[svInd];print("there are %d Support Vectors" %shape(sVs)[0])

m,n=shape(datMat)

errorCount=0for i inrange(m):

kernelEval=kernelTrans(sVs,datMat[i,:],kTup)

predict=kernelEval.T * multiply(labelSV,alphas[svInd]) +bif sign(predict)!=sign(labelArr[i]):

errorCount+= 1

print("the training error rate is: %f" % (float(errorCount)/m))

dataArr,labelArr= loadImages('F:\machinelearninginaction\Ch06\testDigits')

errorCount=0

datMat=mat(dataArr)

labelMat=mat(labelArr).transpose()

m,n=shape(datMat)for i inrange(m):

kernelEval=kernelTrans(sVs,datMat[i,:],kTup)

predict=kernelEval.T * multiply(labelSV,alphas[svInd]) +bif sign(predict)!=sign(labelArr[i]):

errorCount+= 1

print("the test error rate is: %f" % (float(errorCount)/m))