机器学习6—SVM学习笔记
2018-01-29 16:15
597 查看
机器学习实战之SVM
三种SVM的对偶问题
拉格朗日乘子法和KKT条件
解密SVM系列(一):关于拉格朗日乘子法和KKT条件
【机器学习详解】SMO算法剖析
回顾初高中三角函数转换知识:1、诱导公式:
sin(-α) = -sinα; cos(-α) = cosα; sin(π/2-α) = cosα; cos(π/2-α) = sinα; sin(π/2+α) = cosα; cos(π/2+α) = -sinα;
sin(π-α) = sinα; cos(π-α) = -cosα; sin(π+α) = -sinα; cos(π+α) = -cosα;
tanA= sinA/cosA;
tan(π/2+α)=-cotα; tan(π/2-α)= cotα; tan(π-α)=-tanα; tan(π+α)=tanα
2、两角和差公式:
sin(AB) = sinAcosBcosAsinB cos(AB) = cosAcosBsinAsinB tan(AB) = (tanAtanB)/(1tanAtanB) cot(AB) = (cotAcotB1)/(cotBcotA)
3、倍角公式
sin2A=2sinA•cosA cos2A=cosA2-sinA2=1-2sinA2=2cosA2-1 tan2A=2tanA/(1-tanA2)=2cotA/(cotA2-1)
4、半角公式
tan(A/2)=(1-cosA)/sinA=sinA/(1+cosA); cot(A/2)=sinA/(1-cosA)=(1+cosA)/sinA.
sin^2(a/2)=(1-cos(a))/2 cos^2(a/2)=(1+cos(a))/2
tan(a/2)=(1-cos(a))/sin(a)=sin(a)/(1+cos(a))
5、和差化积
sinθ+sinφ = 2 sin[(θ+φ)/2] cos[(θ-φ)/2] sinθ-sinφ = 2 cos[(θ+φ)/2]sin[(θ-φ)/2]
cosθ+cosφ = 2 cos[(θ+φ)/2]cos[(θ-φ)/2] cosθ-cosφ = -2 sin[(θ+φ)/2]sin[(θ-φ)/2]
tanA+tanB=sin(A+B)/cosAcosB=tan(A+B)(1-tanAtanB) tanA-tanB=sin(A-B)/cosAcosB=tan(A-B)(1+tanAtanB)
6、积化和差
sinαsinβ = -1/2*[cos(α-β)-cos(α+β)] cosαcosβ = 1/2*[cos(α+β)+cos(α-β)]
sinαcosβ = 1/2*[sin(α+β)+sin(α-β)] cosαsinβ = 1/2*[sin(α+β)-sin(α-β)]万能公式
两条直线相互垂直的条件:
两条直线在同一平面内1、如果斜率为k1和k2,那么这两条直线垂直的充要条件是k1·k2=-1 , tanαtan(α+π/2) = tanα(-cotα) = -1
2、如果一直线不存在斜率,则两直线垂直时,一直线的斜率必然为零.
3、两直线(A1x+B1y+C1=0, A2x+B2y+C2=0)垂直的充要条件是:A1A2+B1B2=0.
向量1 (x1,y1),长度 L1 =√(x1²+y1²)
向量2 (x2,y2),长度 L2 =√(x2²+y2²)
(x1,y1)到(x2,y2)的距离:D=√[(x1 - x2)² + (y1 - y2)²]
两个向量垂直,根据勾股定理:L1² + L2² = D²
∴ (x1²+y1²) + (x2²+y2²) = (x1 - x2)² + (y1 - y2)²
∴ x1² + y1² + x2² + y2² = x1² -2x1x2 + x2² + y1² - 2y1y2 + y2²
∴ 0 = -2x1x2 - 2y1y2
∴ x1x2 + y1y2 = 0
该定理还可以扩展到三维向量:x1x2 + y1y2 + z1z2 = 0,那么向量(x1,y1,z1)和(x2,y2,z2)垂直
甚至扩展到更高维度的向量,两个向量L1,L2垂直的充分必要条件是:L1×L2=0
test6.py
#-*- coding:utf-8 import sys sys.path.append("svmMLiA.py") import svmMLiA from numpy import * dataArr, labelArr = svmMLiA.loadDataSet("testSet.txt") # b, alphas = svmMLiA.smoSimple(dataArr, labelArr, 0.6, 0.001, 40) b, alphas = svmMLiA.smoP(dataArr, labelArr, 0.6, 0.001, 40) ws = svmMLiA.calcWs(alphas, dataArr, labelArr) num, n = shape(alphas[alphas > 0]) print("num = %d, n = %d" % (num, n)) for i in list(range(100)): if alphas[i] > 0.0: print(dataArr[i], labelArr[i]) print("ws : ") print(ws) datMat = mat(dataArr) caculLabel = datMat[0]*mat(ws) + b print("caculLabel : ") print(caculLabel) print(labelArr[0]) svmMLiA.testRbf() svmMLiA.testDigits(("rbf", 20)) print("over!")
svmMLiA.py
''' Created on Nov 4, 2010 Chapter 5 source file for Machine Learing in Action @author: Peter ''' import matplotlib.pyplot as plt from numpy import * from time import sleep 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 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 def clipAlpha(aj,H,L): if aj > H: aj = H if L > aj: aj = L return aj 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): alphaPairsChanged = 0 for i in range(m): fXi = float(multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[i,:].T)) + b 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)): 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(); 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 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 alphas[i] += labelMat[j]*labelMat[i]*(alphaJold - alphas[j])#update i by the same amount as 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 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 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) # 添加绘图部分 xcord0 = [] ycord0 = [] xcord1 = [] ycord1 = [] 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 if sign(predict) == 1: xcord0.extend(datMat[i, :].tolist()) else: xcord1.extend(datMat[i, :].tolist()) print("the test error rate is: %f" % (float(errorCount) / m)) fig = plt.figure() ax = fig.add_subplot(111) s0 = shape(xcord0)[0] for i in range(s0): ax.scatter(xcord0[i][0], xcord0[i][1], marker='o', s=20, c='blue') s1 = shape(xcord1)[0] for i in range(s1): ax.scatter(xcord1[i][0], xcord1[i][1], marker='v', s=35, c='red') plt.show() # 上绘图部分 def img2vector(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]) return returnVect def loadImages(dirName): from os import listdir hwLabels = [] trainingFileList = listdir(dirName) #load the training set m = len(trainingFileList) trainingMat = zeros((m,1024)) for i in range(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)) return trainingMat, hwLabels def testDigits(kTup=('rbf', 10)): dataArr,labelArr = loadImages('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 = 0 for i in range(m): kernelEval = kernelTrans(sVs,datMat[i,:],kTup) 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 = loadImages('testDigits') errorCount = 0 datMat=mat(dataArr); labelMat = mat(labelArr).transpose() m,n = shape(datMat) for i in range(m): kernelEval = kernelTrans(sVs,datMat[i,:],kTup) 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)) '''#######******************************** Non-Kernel VErsions below '''#######******************************** 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 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 def selectJK(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 updateEkK(oS, k):#after any alpha has changed update the new value in the cache Ek = calcEk(oS, k) oS.eCache[k] = [1,Ek] 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 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 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
相关文章推荐
- 机器学习-支持向量机SVM学习笔记二
- 机器学习:SVM学习笔记(三)
- 机器学习基石--学习笔记01--linear hard SVM
- 机器学习:SVM学习笔记
- 机器学习入门学习笔记:(4.2)SVM的核函数和软间隔
- [matlab]机器学习及SVM工具箱学习笔记
- 机器学习-支持向量机SVM学习笔记一
- 机器学习基石--学习笔记02--Hard Dual SVM
- 机器学习笔记——SVM(2)
- [机器学习]Scikit-Learn模块学习笔记——数据集模块datasets
- TensorsFlow学习笔记4----面向机器学习专家的深度MNIST教程(Deep MNIST for Experts)
- [机器学习入门] 李宏毅机器学习笔记-37 (Deep Reinforcement Learning;深度增强学习入门)
- 台湾大学林轩田机器学习技法课程学习笔记5 -- Kernel Logistic Regression
- 机器学习(十四)Libsvm学习笔记
- [机器学习] Coursera ML笔记 - 监督学习(Supervised Learning) - Representation
- 【机器学习-斯坦福】学习笔记2 - 监督学习应用与梯度下降
- Coursera 机器学习(by Andrew Ng)课程学习笔记 Week 5——神经网络(二)
- 斯坦福机器学习-week 3 学习笔记(1)
- SVM的学习笔记
- 机器学习技法课程学习笔记2 -- Dual Support Vector Machine