# SVM支持向量机-核函数python实现（7）

filename = 'testSetRBF.txt'
fr = open(filename)
X1 = [];y1 = []
X2 = [];y2 = []
lineArr = line.strip().split('\t')
if float(lineArr[-1]) == 1:
X1.append(lineArr[0])
y1.append(lineArr[1])
elif float(lineArr[-1]) == -1:
X2.append(lineArr[0])
y2.append(lineArr[1])
plt.scatter(X1[:],y1[:],c='r',s=50)
plt.scatter(X2[:],y2[:],c='b',s=50)
plt.show()

from numpy import *
from time import sleep
import matplotlib.pyplot as plt

dataMat = []; labelMat = []
fr = open(fileName)
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 #希望alpha的标号不同
while (j==i):
j = int(random.uniform(0,m))
return j 

selectJrand函数根据i，选择与i不同的角标作为另一个alpha的角标.

def clipAlpha(aj,H,L):
if aj > H:
aj = H
if L > aj:
aj = L
return aj

def kernelTrans(X, A, kTup): #通过数据计算转换后的核函数
m,n = shape(X)
K = mat(zeros((m,1)))
if kTup[0]=='lin': #线性核函数
K = X * A.T

elif kTup[0]=='rbf':#高斯核
for j in range(m):
deltaRow = X[j,:] - A
K[j] = deltaRow*deltaRow.T
K = exp(K/(-1*kTup[1]**2))

elif kTup[0] == 'laplace':#拉普拉斯核
for j in range(m):
deltaRow = X[j,:] - A
K[j] = deltaRow*deltaRow.T
K[j] = sqrt(K[j])
K = exp(-K/kTup[1])

elif kTup[0] == 'poly':#多项式核
K = X * A.T
for j in range(m):
K[j] = K[j]**kTup[1]

elif kTup[0] == 'sigmoid':#Sigmoid核
K = X * A.T
for j in range(m):
K[j] = tanh(kTup[1]*K[j]+kTup[2])

else: raise NameError('执行过程出现问题 -- \
核函数无法识别')
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):
maxK = -1; maxDeltaE = 0; Ej = 0
oS.eCache[i] = [1,Ei]
validEcacheList = nonzero(oS.eCache[:,0].A)[0]
# print(validEcacheList)
if (len(validEcacheList)) > 1:
for k in validEcacheList:
if k == i: continue
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):
Ek = calcEk(oS, k)
oS.eCache[k] = [1,Ek]

SMO算法

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)
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]
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)
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])
updateEk(oS, i)
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=('rbf', 1.3)):
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:
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:
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
elif (alphaPairsChanged == 0): entireSet = True
print ("iteration number: %d" % iter)
return oS.b,oS.alphas

def calculateW(alphas,dataArr,labelArr):
alphas, dataMat, labelMat = array(alphas), array(dataArr), array(labelArr)
sum = 0
for i in range(shape(dataMat)[0]):
sum += alphas[i]*labelMat[i]*dataMat[i].T
print(sum)
return sum

def testRbf(k1=1.3):
b,alphas = smoP(dataArr, labelArr, 200, 0.0001, 10000, ('rbf', k1))

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,:],('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))

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))

def plot_point(filename,alphas,dataMat):
filename = filename
fr = open(filename)
X1 = [];y1 = []
X2 = [];y2 = []
lineArr = line.strip().split('\t')
if float(lineArr[-1]) == 1:
X1.append(lineArr[0])
y1.append(lineArr[1])
elif float(lineArr[-1]) == -1:
X2.append(lineArr[0])
y2.append(lineArr[1])
plt.scatter(X1[:],y1[:],c='y',s=50)
plt.scatter(X2[:],y2[:],c='b',s=50)

for i, alpha in enumerate(alphas):
if abs(alpha) > 0:
x, y = dataMat[i]
plt.scatter(x, y, s=100, c = '', alpha=0.5, linewidth=1.5, edgecolor='red')

plt.show()

if __name__ == "__main__":
b,alphas = smoP(dataArr,labelArr,0.6,0.001,40)
testRbf()
plot_point('testSetRBF.txt',alphas,dataArr)
calculateW(alphas,dataArr,labelArr)

there are 31 Support Vectors
the training error rate is: 0.020000
the test error rate is: 0.030000
w = [-0.1685502 -0.1276386]
[Finished in 18.8s]

there are 31 Support Vectors
the training error rate is: 0.000000
the test error rate is: 0.200000
w = [-0.436887  -0.9289236]
[Finished in 24.4s]

there are 69 Support Vectors
the training error rate is: 0.330000
the test error rate is: 0.490000
w = [ 0.0532572 -0.3009696]
[Finished in 19.1s]