机器学习实战(5)--SVM(Support vector machine)(六)--Python实现
2016-03-27 20:54
609 查看
1,在通过一系列推导后,我们剩下如下公式:
通过SMO优化算法来计算公式中的
的值。
2,通过启发式算法,当第一次计算时对所有的
进行更新。之后的每次计算只选择
的系数进行更新(因为系数ai=0,ai=C,对应于点在两条间隔线的外面和里面的点,认为这些点系数一般不会改变),同时根据公式更新b的值。当所有系数的变化小于规定的值,或迭代次数小于规定的值时,运算结束,得到最终的
值,与b值。
3,计算
,如果新来了一个数据
,计算
,根据是否大于0,来判断属于哪一类。
Python实现
1,首先为了简单起见,在选择第二个![这里写图片描述](http://img.blog.csdn.net/20160327193536752)点时,先不采用启发式算法,而是用随机选择的算法。
2,下面对完整的SMO算法进行实现:
3,在此基础上还可以用核函数
testSet.txt: http://pan.baidu.com/s/1o83oKKM
testSetRBF.txt: http://pan.baidu.com/s/1nuC4aCD
testSetRBF2.txt: http://pan.baidu.com/s/1pKYeCUv
通过SMO优化算法来计算公式中的
的值。
2,通过启发式算法,当第一次计算时对所有的
进行更新。之后的每次计算只选择
的系数进行更新(因为系数ai=0,ai=C,对应于点在两条间隔线的外面和里面的点,认为这些点系数一般不会改变),同时根据公式更新b的值。当所有系数的变化小于规定的值,或迭代次数小于规定的值时,运算结束,得到最终的
值,与b值。
3,计算
,如果新来了一个数据
,计算
,根据是否大于0,来判断属于哪一类。
Python实现
1,首先为了简单起见,在选择第二个![这里写图片描述](http://img.blog.csdn.net/20160327193536752)点时,先不采用启发式算法,而是用随机选择的算法。
#加载数据,数据在文章末尾处可以下载 def loadDataSet(fileName): dataMat = []; labelMat = [] fr = open(fileName) for line in fr.readlines(): lineArr = line.strip().split('\t') dataMat.append([float(lineArr[0]), float(lineArr[1])]) labelMat.append(float(lineArr[2])) return dataMat,labelMat #在确定第一个数据点为i时,随机选择第二个数据点,但要保证不为i def selectJrand(i,m): j=i #we want to select any J not equal to i while (j==i): j = int(random.uniform(0,m)) return j #根据前面的推导,系数ai要在L与H之间,超过H时以H计算,超过L时以值L来计算,在L与H之间的,则不改变。 def clipAlpha(aj,H,L): if aj > H: aj = H if L > aj: aj = L return aj #简化版的SMO算法,返回系数值,与b值 def smoSimple(dataMatIn, classLabels, C, toler, maxIter): dataMatrix = mat(dataMatIn); labelMat = mat(classLabels).transpose() b = 0; m,n = shape(dataMatrix) alphas = mat(zeros((m,1))) iter = 0 while (iter < maxIter): #发生改变的系数对的数目 alphaPairsChanged = 0 for i in range(m): #计算w*xi+b fXi = float(multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[i,:].T)) + b #计算在当前系数ai的情况下,对应的误差 Ei = fXi - float(labelMat[i]) #if checks if an example violates KKT conditions if ((labelMat[i]*Ei < -toler) and (alphas[i] < C)) or ((labelMat[i]*Ei > toler) and (alphas[i] > 0)): #随机选择第二个系数点 j = selectJrand(i,m) fXj = float(multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[j,:].T)) + b Ej = fXj - float(labelMat[j]) alphaIold = alphas[i].copy(); alphaJold = alphas[j].copy(); #判断两个选择的系数对应的类别是否相同 if (labelMat[i] != labelMat[j]): L = max(0, alphas[j] - alphas[i]) H = min(C, C + alphas[j] - alphas[i]) else: L = max(0, alphas[j] + alphas[i] - C) H = min(C, alphas[j] + alphas[i]) if L==H: print "L==H"; continue #计算eta =2K(x1,x2)-k(x1,x1)-k(x2,x2),用来更新a2 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] -= labelMat[j]*(Ei - Ej)/eta alphas[j] = clipAlpha(alphas[j],H,L) if (abs(alphas[j] - alphaJold) < 0.00001): print "j not moving enough"; continue #update i by the same amount as j alphas[i] += labelMat[j]*labelMat[i]*(alphaJold - alphas[j]) #the update is in the oppostie direction 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
2,下面对完整的SMO算法进行实现:
#设计一个对象 class optStructK: def __init__(self,dataMatIn, classLabels, C, toler): # 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 #计算误差值 def calcEkK(oS, k): fXk = float(multiply(oS.alphas,oS.labelMat).T*(oS.X*oS.X[k,:].T)) + oS.b Ek = fXk - float(oS.labelMat[k]) return Ek #this is the second choice -heurstic, and calcs Ej #用启发式算法,选择第二个系数 def selectJK(i, oS, Ei): maxK = -1; maxDeltaE = 0; Ej = 0 #将第i个数据算出来的误差存入误差数组中,1代表数据有效 oS.eCache[i] = [1,Ei] #set valid #choose the alpha that gives the maximum delta E #.A运算表示,将矩阵转换为arrary;nonzero是返回,在eCache数组中每一行第一位不为0的行的系数,与对应的列数 validEcacheList = nonzero(oS.eCache[:,0].A)[0] if (len(validEcacheList)) > 1: #loop through valid Ecache values and find the one that maximizes delta E #根据启发式的原理,第二个数据点的选择是选取具有最大|E1-E2|的数据点,因为迭代步长正比于|E1-E2|。 for k in validEcacheList: 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 #in this case (first time around) we don't have any valid eCache values #在第一次,一般对于第二个数据点采用随机的方式 else: j = selectJrand(i, oS.m) Ej = calcEk(oS, j) return j, Ej #更新误差数组 def updateEkK(oS, k):#after any alpha has changed update the new value in the cache Ek = calcEk(oS, k) oS.eCache[k] = [1,Ek] #根据第一个点,调用上面的方法选择第二个点,并对系数进行更新,返回是否更新了数据对 def innerLK(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.X[i,:]*oS.X[j,:].T - oS.X[i,:]*oS.X[i,:].T - oS.X[j,:]*oS.X[j,:].T 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.X[i,:]*oS.X[i,:].T - oS.labelMat[j]*(oS.alphas[j]-alphaJold)*oS.X[i,:]*oS.X[j,:].T b2 = oS.b - Ej- oS.labelMat[i]*(oS.alphas[i]-alphaIold)*oS.X[i,:]*oS.X[j,:].T - oS.labelMat[j]*(oS.alphas[j]-alphaJold)*oS.X[j,:]*oS.X[j,:].T 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 #SMO算法 def smoPK(dataMatIn, classLabels, C, toler, maxIter): #full Platt SMO oS = optStruct(mat(dataMatIn),mat(classLabels).transpose(),C,toler) iter = 0 entireSet = True; alphaPairsChanged = 0 #第一次运行时entireSet = True 表示,第一次要对所有的系数进行更新 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 #只更alphas.A > 0且alphas.A < C的系数,(oS.alphas.A > 0) * (oS.alphas.A < C)是两个布尔值相乘,为0或为1 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
3,在此基础上还可以用核函数
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 #根据系数值计算w 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 #用RBF核函数 def testRbf(k1=1.3): dataArr,labelArr = loadDataSet('testSetRBF.txt') b,alphas = smoP(dataArr, labelArr, 200, 0.0001, 10000, ('rbf', k1)) #C=200 important datMat=mat(dataArr); labelMat = mat(labelArr).transpose() svInd=nonzero(alphas.A>0)[0] sVs=datMat[svInd] #get matrix of only support vectors labelSV = labelMat[svInd]; print "there are %d Support Vectors" % shape(sVs)[0] m,n = shape(datMat) errorCount = 0 for i in range(m): kernelEval = kernelTrans(sVs,datMat[i,:],('rbf', k1)) predict=kernelEval.T * multiply(labelSV,alphas[svInd]) + b if sign(predict)!=sign(labelArr[i]): errorCount += 1 print "the training error rate is: %f" % (float(errorCount)/m) dataArr,labelArr = loadDataSet('testSetRBF2.txt') errorCount = 0 datMat=mat(dataArr); labelMat = mat(labelArr).transpose() m,n = shape(datMat) for i in range(m): kernelEval = kernelTrans(sVs,datMat[i,:],('rbf', k1)) predict=kernelEval.T * multiply(labelSV,alphas[svInd]) + b if sign(predict)!=sign(labelArr[i]): errorCount += 1 print "the test error rate is: %f" % (float(errorCount)/m)
testSet.txt: http://pan.baidu.com/s/1o83oKKM
testSetRBF.txt: http://pan.baidu.com/s/1nuC4aCD
testSetRBF2.txt: http://pan.baidu.com/s/1pKYeCUv
相关文章推荐
- Python基础2:反射、装饰器、JSON,接口
- Leetcode 3. Longest Substring Without Repeating Characters(python)
- Python 生成器 匿名生成器
- Leetcode 2. Add Two Numbers(python)
- Python3.x学习笔记(一)
- Leetcode 1. Two Sum(python)
- 我的Python学习之路之基本语法-函数
- 树莓派瞎玩~5~控制GPIO之Python
- 简单的抓取淘宝关键字信息、图片的Python爬虫|Python3中级玩家:淘宝天猫商品搜索爬虫自动化工具(第二篇)
- python filter, map, reduce, lamda
- 解决im.show()不能显示图片问题
- Python3基本数据类型
- Numpy 初试
- Python回顾与整理7:文件和输入输出
- Python回顾与整理7:文件和输入输出
- 【爬虫】python requests模拟登录知乎
- python轻量级爬虫的编写
- Python图像处理之伪彩色增强
- Python图像处理之边缘检测
- python绘图示例