系列文章目录
文章目录
提示：参考书籍图灵程序设计丛书《机器学习实战》
一、寻找最大间隔
二、SMO高效优化算法
1.应用简化版SMO算法处理小规模数据集
from numpy import *
from time import sleep
#SMO算法中的辅助函数
def loadDataSet(fileName): # 得到类标签和数据矩阵
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): # i是第一个alpha的下标，m是所有alpha的数量,确保i和j是不一样的
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): # 用于调整alpha的值
if aj > H:
aj = H
if L > aj:
aj = L
return aj
#简化版SMO算法
def smoSimple(dataMatIn, classLabels, C, toler, maxIter): # SMO的一个有效的简化版本
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 # 预测类别
Ei = fXi - float(labelMat[i]) # if checks if an example violates KKT condition 计算误差
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 # alpha的最优修改量
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
if __name__ == '__main__':
dataArr, labelArr = loadDataSet('testSet.txt')
# print labelArr
b, alphas = smoSimple(dataArr, labelArr, 0.6, 0.001, 40)
print(b)
print(alphas[alphas > 0])
print(shape(alphas[alphas > 0]))
for i in range(100):
if alphas[i] > 0.0:
print (dataArr[i], labelArr[i])
测试结果
2.利用完整Platt SMO算法加快优化
#完整版Platt SMO的支持函数
class optStruct: # 建立一个数据结构
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)
#误差缓存
def calcEk(oS, k): # 计算E值
fXk = float(multiply(oS.alphas, oS.labelMat).T * oS.K[:, k] + oS.b)
Ek = fXk - float(oS.labelMat[k])
return Ek
#内循环的启发式方法
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): #选择具有最大步长的j
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): # 完整SMO算法中的优化例程
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 第二个alpha选择中的启发式方法
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
#完整版Platt SMO的外循环代码
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): #根据alphas计算W
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
if __name__ == '__main__':
dataArr, labelArr = loadDataSet('testSet.txt')
#测试完整版的smo算法
b, alphas = smoP(dataArr, labelArr, 0.6, 0.001, 40)
print (b)
print (alphas[alphas>0])
print (shape(alphas[alphas>0]))
for i in range(100):
if alphas[i]>0.0:
print (dataArr[i], labelArr[i])
测试结果
2.在复杂数据上应用核函数
#核转换函数
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
#完整版Platt SMO的支持函数
class optStruct: # 建立一个数据结构
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)
2.在测试中使用核函数
#利用核函数进行分类的径向基测试函数
def testRbf(k1=1.3): #在测试中使用核函数
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))
if __name__ == '__main__':
testRbf()
测试结果
