今日练习作业

一、代码

1.所有代码

代码如下（示例）：

#python3.8
#@Time    :2020/12/7
#@Software:Pycharm
#@FileName:SupportVectorMachine
#@Author  :xuhaoyu
from numpy import *
#loadDataSet方法将数据集的数据部分和标签部分转化二维列表和一维列表（向量）
def loadDataSet(fileName):
    dataMatrix = []     #数据矩阵列表
    labelMatrix = []    #数据的标签tag列表
    fileOpen = open(fileName)
    for line in fileOpen.readlines():  #读取文件的每一行
        #strip()函数将文件的首位空格去掉（默认参数）
        #split()函数将每一行用'\t'作为分隔符，放到一个列表中
        lineArray = line.strip().split('\t')
        #append()函数用来在列表尾部追加元素(参数是一个元素，例如：元组，列表，等)
        dataMatrix.append([float(lineArray[0]),float(lineArray[1])])
        labelMatrix.append(float(lineArray[2]))
    return dataMatrix,labelMatrix

#SMO算法中的两个辅助函数
def selectJrand(alphaIndex,numberOfAlpha):
    j = alphaIndex
    while(j == alphaIndex):
        j = int(random.uniform(0,numberOfAlpha))
    return j

#用于调整alpha的值alpha大于highValue将highValue赋值给alpha，反之也赋值
def clipAlpha(alpha,highValue,lowValue):
    if alpha > highValue:
        alpha = highValue
    if alpha < lowValue:
        alpha = lowValue
    return alpha

def smoSimple(dataMatrixInput,classLabels,constantC,toleranceRate,maxIter):
    dataMatrix = mat(dataMatrixInput)
    labelMatrix = mat(classLabels).transpose()
    b = 0
    m,n = shape(dataMatrix)
    alphas = mat(zeros((m,1)))
    iter = 0
    while(iter < maxIter):
        alphaPairsChanged = 0
        for i in range(m):
            fXi = float(multiply(alphas,labelMatrix).T*(dataMatrix * dataMatrix[i,:].T)) + b
            Ei = fXi - float(labelMatrix[i])
            if((labelMatrix[i] * Ei < -toleranceRate)and (alphas[i] < constantC))or((labelMatrix[i] *Ei>toleranceRate)and(alphas[i]>0)):
                j = selectJrand(i,m)
                fXj = float(multiply(alphas,labelMatrix).T*(dataMatrix * dataMatrix[j,:].T)) + b
                Ej = fXj -float(labelMatrix[j])
                alphaIold = alphas[i].copy();alphaJold = alphas[j].copy();
                if(labelMatrix[i] != labelMatrix[j]):
                    L = max(0,alphas[j] - alphas[i])
                    H = min(constantC,constantC + alphas[j] - alphas[i])
                else:
                    L = max(0,alphas[j] + alphas[i] - constantC)
                    H = min(constantC,alphas[j] + alphas[i])
                if L == H:print("L == H");continue
                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
                alphas[j] -= labelMatrix[j] * (Ei - Ej)/eta
                alphas[j] = clipAlpha(alphas[j],H,L)
                if (abs(alphas[j] - alphaJold) < 0.00001):
                    print("j not moving enough")
                    continue
                alphas[i] += labelMatrix[j] * labelMatrix[i]*(alphaJold -alphas[j])
                b1 = b - Ei - labelMatrix[i] * (alphas[i] - alphaJold)*dataMatrix[i,:]*dataMatrix[i,:].T - labelMatrix[j]*(alphas[j] - alphaJold)*dataMatrix[i,:]*dataMatrix[j,:].T
                b2 = b - Ej - labelMatrix[i] * (alphas[i] - alphaJold)*dataMatrix[i,:] * dataMatrix[j,:].T - labelMatrix[j] * (alphas[j] - alphaJold) * dataMatrix[j,:] * dataMatrix[j,:].T
                if(0 < alphas[i]) and (constantC > alphas[i]):
                    b = b1
                elif (0 < alphas[j]) and (constantC > 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:{}".format(iter))
    return b,alphas

'''测试loadDataSet（）的语句'''
fileName = 'testSet.txt'
dataMatrix,labelVector = loadDataSet(fileName)
b,alphas = smoSimple(dataMatrix,labelVector,0.6,0.001,40)
#print(dataMatrix,labelVector)
print(b)
print(alphas[alphas>0])

def kernelTrans(X, A, kTup): #calc the kernel or transform data to a higher dimensional space
    m,n = shape(X)
    K = mat(zeros((m,1)))
    if kTup[0]=='lin': K = X * A.T   #linear kernel
    elif kTup[0]=='rbf':
        for j in range(m):
            deltaRow = X[j,:] - A
            K[j] = deltaRow*deltaRow.T
        K = exp(K/(-1*kTup[1]**2)) #divide in NumPy is element-wise not matrix like Matlab
    else: raise NameError('Houston We Have a Problem -- \
    That Kernel is not recognized')
    return K

class optStruct:
    def __init__(self,dataMatIn, classLabels, C, toler, kTup):  # Initialize the structure with the parameters
        self.X = dataMatIn
        self.labelMat = classLabels
        self.C = C
        self.tol = toler
        self.m = shape(dataMatIn)[0]
        self.alphas = mat(zeros((self.m,1)))
        self.b = 0
        self.eCache = mat(zeros((self.m,2))) #first column is valid flag
        self.K = mat(zeros((self.m,self.m)))
        for i in range(self.m):
            self.K[:,i] = kernelTrans(self.X, self.X[i,:], kTup)

def calcEk(oS, k):
    fXk = float(multiply(oS.alphas,oS.labelMat).T*oS.K[:,k] + oS.b)
    Ek = fXk - float(oS.labelMat[k])
    return Ek

def selectJ(i, oS, Ei):         #this is the second choice -heurstic, and calcs Ej
    maxK = -1; maxDeltaE = 0; Ej = 0
    oS.eCache[i] = [1,Ei]  #set valid #choose the alpha that gives the maximum delta E
    validEcacheList = nonzero(oS.eCache[:,0].A)[0]
    if (len(validEcacheList)) > 1:
        for k in validEcacheList:   #loop through valid Ecache values and find the one that maximizes delta E
            if k == i: continue #don't calc for i, waste of time
            Ek = calcEk(oS, k)
            deltaE = abs(Ei - Ek)
            if (deltaE > maxDeltaE):
                maxK = k; maxDeltaE = deltaE; Ej = Ek
        return maxK, Ej
    else:   #in this case (first time around) we don't have any valid eCache values
        j = selectJrand(i, oS.m)
        Ej = calcEk(oS, j)
    return j, Ej

def updateEk(oS, k):#after any alpha has changed update the new value in the cache
    Ek = calcEk(oS, k)
    oS.eCache[k] = [1,Ek]

def innerL(i, oS):
    Ei = calcEk(oS, i)
    if ((oS.labelMat[i]*Ei < -oS.tol) and (oS.alphas[i] < oS.C)) or ((oS.labelMat[i]*Ei > oS.tol) and (oS.alphas[i] > 0)):
        j,Ej = selectJ(i, oS, Ei) #this has been changed from selectJrand
        alphaIold = oS.alphas[i].copy(); alphaJold = oS.alphas[j].copy();
        if (oS.labelMat[i] != oS.labelMat[j]):
            L = max(0, oS.alphas[j] - oS.alphas[i])
            H = min(oS.C, oS.C + oS.alphas[j] - oS.alphas[i])
        else:
            L = max(0, oS.alphas[j] + oS.alphas[i] - oS.C)
            H = min(oS.C, oS.alphas[j] + oS.alphas[i])
        if L==H: print("L==H"); return 0
        eta = 2.0 * oS.K[i,j] - oS.K[i,i] - oS.K[j,j] #changed for kernel
        if eta >= 0: print("eta>=0"); return 0
        oS.alphas[j] -= oS.labelMat[j]*(Ei - Ej)/eta
        oS.alphas[j] = clipAlpha(oS.alphas[j],H,L)
        updateEk(oS, j) #added this for the Ecache
        if (abs(oS.alphas[j] - alphaJold) < 0.00001): print("j not moving enough"); return 0
        oS.alphas[i] += oS.labelMat[j]*oS.labelMat[i]*(alphaJold - oS.alphas[j])#update i by the same amount as j
        updateEk(oS, i) #added this for the Ecache                    #the update is in the oppostie direction
        b1 = oS.b - Ei- oS.labelMat[i]*(oS.alphas[i]-alphaIold)*oS.K[i,i] - oS.labelMat[j]*(oS.alphas[j]-alphaJold)*oS.K[i,j]
        b2 = oS.b - Ej- oS.labelMat[i]*(oS.alphas[i]-alphaIold)*oS.K[i,j]- oS.labelMat[j]*(oS.alphas[j]-alphaJold)*oS.K[j,j]
        if (0 < oS.alphas[i]) and (oS.C > oS.alphas[i]): oS.b = b1
        elif (0 < oS.alphas[j]) and (oS.C > oS.alphas[j]): oS.b = b2
        else: oS.b = (b1 + b2)/2.0
        return 1
    else: return 0

def 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 = 0
    while (iter < maxIter) and ((alphaPairsChanged > 0) or (entireSet)):
        alphaPairsChanged = 0
        if entireSet:   #go over all
            for i in range(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 < C))[0]
            for i in nonBoundIs:
                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 = True
        print("iteration number: %d" % iter)
    return oS.b,oS.alphas

def calcWs(alphas,dataArr,classLabels):
    X = mat(dataArr); labelMat = mat(classLabels).transpose()
    m,n = shape(X)
    w = zeros((n,1))
    for i in range(m):
        w += multiply(alphas[i]*labelMat[i],X[i,:].T)
    return w