pythonでのサポートベクトル実装
8782 ワード
コードは主に机械を参考にして実戦のあの本を勉强して、ベクトル机を支持して过程の个人がすべてのアルゴリズムの中で使う数学の知识の最も多い1种のアルゴリズムだと思って、理解して一定の难易度があって、下のコードの中でただ核の関数の実现がないことを実现して、核の関数のがあるのは少し修正するだけでいいです
具体的なコードは以下の通りです.
具体的なコードは以下の通りです.
#encoding:utf-8
'''
Created on 2015 9 16
@author: ZHOUMEIXU204
'''
path=u'D:\\Users\\zhoumeixu204\\Desktop\\python \\ python\\ \\machinelearninginaction\\Ch06\\'
import numpy as np
import matplotlib.pyplot as plt
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
while(j==i):
j=int(np.random.uniform(0,m))
return j
def clipAlpha(aj,H,L):
if aj>H:
aj=H
if L>aj:
aj=L
return aj
#multiply a*b multiply(a,b)
#ultiply numpy ufunc , , ,
# matlab , , , a 5 5
def smoSimple(dataMatIn, classLabels, C, toler, maxIter):
# 、 、 C、 、
dataMatrix =np.mat(dataMatIn); labelMat = np.mat(classLabels).transpose()
b = 0; m,n =np.shape(dataMatrix)
alphas = np.mat(np.zeros((m,1)))
iter = 0
while (iter < maxIter):
alphaPairsChanged = 0
for i in range(m):
fXi = float(np.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(np.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
dataArr,labelArr=loadDataSet(path+'testSet.txt')
print(labelArr)
# 、 、 C、 、
b,alphas=smoSimple(dataArr, labelArr, 0.6, 0.001, 40)
# print(b)
# print(alphas)
print(alphas[alphas>0])
for i in range(100):
if alphas[i]>0.0:
print(dataArr[i],labelArr[i])
def kernelTrans(X,A,kTup):
m,n=np.shape(X)
K=np.mat(np.zeros((m,1)))
if kTup[0]=='lin':K=X*A.T
elif kTup[0]=='rbf':
for j in range(m):
deltaRow=X[j,:]-A
K[j]=deltaRow*deltaRow.T
K=np.exp(K/(-1*kTup[1]**2))
else:
raise NameError('Houston we hava a problem the kernel is not recognized')
return K
# PlattSMO
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 =np.shape(dataMatIn)[0]
self.alphas =np.mat(np.zeros((self.m,1)))
self.b = 0
self.eCache =np.mat(np.zeros((self.m,2))) #first column is valid flag
self.K =np.mat(np.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(np.multiply(oS.alphas,oS.labelMat).T*(oS.X*oS.X[k,:].T))+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=np.nonzero(oS.eCache[:,0].A)[0]
if (len(validEcacheList))>1:
for k in validEcacheList:
if k==i:continue
Ek=calcEk(oS, k)
deltaE=np.abs(Ei-Ek)
if (deltaE>maxDeltaE):
maxK=k;maxDeltaE=deltaE;Ej=Ek
return maxK,Ej
else:
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]
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(np.mat(dataMatIn),np.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 =np.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
b,alphas=smoP(dataArr,labelArr,0.6,0.01,40)
print(b)
print(alphas)
#