简单的SVM

#学习自机器学习实战
from numpy import *
def loadDataSet(filename):
    dataMat=[];labelMat=[]#initilize
    fr=open(filename)#open the file
    for line in fr.readlines():#process the readline
        lineArr=line.strip().split(' ')#the disperation of the data
        #print(lineArr[0])
        dataMat.append([float(lineArr[0]),float(lineArr[1])])#the value of the data
        labelMat.append(float(lineArr[2]))
    return dataMat,labelMat#return value
def selectJrand(i,m):#fine the j which is different from i
    j=i
    while(j==i):
        j=int(random.uniform(0,m))#random produce
    return j
def clipAlpha(aj,H,L):
    if aj>H:#make the newaj in the edge
        aj=H
    if L>aj:
        aj=L
    return aj
def smoSimple(dataMatIn,classLabels,C,toler,maxIter):
    dataMatrix=mat(dataMatIn);labelMat=mat(classLabels).transpose()#copy
    b=0;m,n=shape(dataMatrix)#m the number of data n the column of data
    alphas=mat(zeros((m,1)))#initilize the alphas alphas 's volumn is equal to dataMat .m
    iter=0#initilize the iteration record
    while(iter<maxIter):#weather is achieve the maxiteration
        alphaPairsChanged=0#havn't be changed
        for i in range(m):#circle
            fxi=float(multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[i,:].T))+b#columns dot +bias is the function value
            ei=fxi-float(labelMat[i])
            if((labelMat[i]*ei<-toler)and(alphas[i]<C))or((labelMat[i]*ei>toler) and(alphas[i]>0)):#if the value have much differencefrom the real it needs ptimize
                j=selectJrand(i,m)
                fxj=float(multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[j,:].T))+b
                ej=fxj-float(labelMat[j])#the difference of the prcdict and the real
                alphaIold=alphas[i].copy()#save the old value
                alphaJold=alphas[j].copy()
                if(labelMat[i]!=labelMat[j]):#if not a same class
                    L=max(0,alphas[j]-alphas[i])#the edge
                    H=min(C,C+alphas[j]-alphas[i])#a-b 's slope is 1
                else:
                    L=max(0,alphas[j]+alphas[i]-C)
                    H=min(C,alphas[j]+alphas[i])
                if L==H: print("L==H");continue#don't have num
                eta=2.0*dataMatrix[i,:]*dataMatrix[j,:].T-dataMatrix[i,:]*dataMatrix[i,:].T-dataMatrix[j,:]*dataMatrix[j,:].T
                if eta>=0: print("eta>=0");continue#if we decide the ai aj and the other a is constance and the  let it in the w find the least
                alphas[j]-=labelMat[j]*(ei-ej)/eta#new aj
                alphas[j]=clipAlpha(alphas[j],H,L)
                if(abs(alphas[j]-alphaJold)<toler): print("j not  moving enough");continue;
                alphas[i]+=labelMat[j]*labelMat[i]*(alphaJold-alphas[j])#new ai and then new b
                b1=b-ei-labelMat[i]*(alphas[i]-alphaIold)*dataMatrix[i,:]*dataMatrix[i,:].T-labelMat[j]*(alphas[j]-alphaJold)*dataMatrix[i,:]*dataMatrix[j,:].T
                b2=b-ej-labelMat[i]*(alphas[i]-alphaIold)*dataMatrix[i,:]*dataMatrix[j,:].T-labelMat[j]*(alphas[j]-alphaJold)*dataMatrix[j,:]*dataMatrix[j,:].T
                if (0<alphas[i]) and (C>alphas[i]) :b=b1
                elif(0<alphas[j]) and (C>alphas[j]) :b=b2
                else :b=(b1+b2)/2.0
                alphaPairsChanged+=1
                print("iter:%d,i %d pairs changed %d"%(iter,i,alphaPairsChanged))
            if alphaPairsChanged ==0: iter+=1
            else:iter=0
            print("iteration number:%d"%iter)
    return b,alphas
if __name__=='__main__':
    x,y=loadDataSet("testSet.txt")
   # print("data" ,x,"\nlabel" ,y)
    b,alpha=smoSimple(x,y,0.6,0.001,10)
    print("b" ,b,"\nalphas" ,alpha)