def testRbf(k1=1.3):
dataArr, labelArr = svmMLiA.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 = svmMLiA.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))
ws = svmMLiA.calcWs(alphas, dataArr, labelArr)
x0 = []
y0 = []
x1 = []
y1 = []
x_sv = []
y_sv = []
fig = plt.figure()
ax = fig.add_subplot(111)
for i in range(100):
if alphas[i] > 0.0:
x_sv.append(dataArr[i][0])
y_sv.append(dataArr[i][1])
elif labelArr[i] > 0.0:
x0.append(dataArr[i][0])
y0.append(dataArr[i][1])
else:
x1.append(dataArr[i][0])
y1.append(dataArr[i][1])
ax.scatter(x0, y0, color='r')
ax.scatter(x1, y1, color='g')
ax.scatter(x_sv, y_sv, color='b')
# X = linspace(2, 6, 1000)
# Y = [(float(ws[0]) * x + float(b)) / -float(ws[1]) for x in X]
# ax.plot(X, Y)
plt.show()
def titanicBysvm(filename,k1=1.3):
trainingdataarr,traininglabelarr,testdataarr,testlaeblarr = loadDataSet(filename)
# C = 200 , toler = 0.0001 , maxiteration = 10000
# b,alphas = svm.smoSimple(trainingdataarr,traininglabelarr,100,0.001,10000)
b,alphas = svm.smoP(trainingdataarr,traininglabelarr, 200, 0.0001, 10000, ('rbf', k1))
# w f(x) = w.T*x + b
w = svm.calcWs(alphas,trainingdataarr,traininglabelarr)
dataMat = mat(trainingdataarr); labelmat = mat(traininglabelarr).transpose()
# svInd is the index of support vector,sVs is the support vectors,labelSV is the support vector labels
svInd = nonzero(alphas.A > 0)[0]
sVs = dataMat[svInd]
labelSV = labelmat[svInd]
print "there are %d Support Vectors" % shape(sVs)[0]
m,n = shape(trainingdataarr)
errorCount = 0
for i in range(m):
kernelEval = svm.kernelTrans(sVs,dataMat[i,:], ('rbf',k1))
predict = kernelEval.T * multiply(labelSV,alphas[svInd]) + b
# predict = trainingdataarr[i,:] * mat(w) + b
# print predict
# print trainingdataarr[i,:]
# print " "
# print predict
# print "\n"
if sign(predict) != sign(traininglabelarr[i]):
errorCount += 1
print "the number of errors is %d" % errorCount
print "the training accuracy rate is: %f" % (1 - (float)(errorCount) / m)
# test data running
testErrorCount = 0
dataMat = mat(testdataarr); testlabelMat = mat(testlaeblarr).transpose()
m,n = shape(testdataarr)
for i in range(m):
kernelEval = svm.kernelTrans(sVs,dataMat[i,:],('rbf',k1))
predict = kernelEval.T * multiply(labelSV,alphas[svInd]) + b
if sign(predict) != sign(testlaeblarr[i]):
testErrorCount += 1
print "the test accuracy rate is %.3f" % (1 - float(testErrorCount) / m)
def printsvm(Mat, label, alphas, b):
fig = plt.figure()
ax = fig.add_subplot(111)
print 'to print scatter'
i = 0
for dot in Mat:
if alphas[i] > 0.0:
ax.scatter(dot[0], dot[1], c='r', marker='o')
else:
ax.scatter(dot[0], dot[1])
i+=1
print 'to print line'
ws = svmMLiA.calcWs(alphas, Mat, label)
x = arange(0:3:2)
print 'x=',x
y = ws*x+b
print y
ax.plot(x, y)
plt.show()
import svmMLiA
from numpy import *
dataArr, labelArr = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoP(dataArr, labelArr, 0.6, 0.001, 40)
ws = svmMLiA.calcWs(alphas, dataArr, labelArr)
print ws
datMat = mat(dataArr)
print datMat[0]*mat(ws)+b
print labelArr[0]
print datMat[1]*mat(ws)+b
print labelArr[1]
print datMat[2]*mat(ws)+b
print labelArr[2]
from numpy import *
import svmMLiA
dataArr, labelArr = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoP(dataArr, labelArr, 0.6, 0.001, 40)
ws = svmMLiA.calcWs(alphas, dataArr, labelArr)
print(ws)
dataMat = mat(dataArr)
print(dataMat[0] * mat(ws) + b)
print(labelArr[0])
print(dataMat[2] * mat(ws) + b)
print(labelArr[2])
print(dataMat[1] * mat(ws) + b)
print(labelArr[1])
def fit(self, dataArr, LabelArr):
self.b, self.alphas = smoPK(dataArr, LabelArr, self.C, self.toler,
self.maxIter)
self.weights = calcWs(self.alphas, dataArr, LabelArr)
iter: 30 i:17, pairs changed 1
j not moving enough
iteration number: 0
j not moving enough
iteration number: 1
b: matrix([[-3.8486163]])
alphas[alphas>0] = matrix([[0.09313378, 0.27456007, 0.04445935, 0.3232345 ]])
"""
# To see which points of our dataset are support vectors
for i in range(100):
if alphas[i] > 0.0:
print(dataArr[i], labelArr[i])
"""
output:
[4.658191, 3.507396] -1.0
[3.457096, -0.082216] -1.0
[2.893743, -1.643468] -1.0
[6.080573, 0.418886] 1.0
"""
""" optimised SMOP """
b, alphas = SVM.smoP(dataArr, labelArr, 0.6, 0.001, 40)
""" get alpha for supporting vectors """
ws = SVM.calcWs(alphas, dataArr, labelArr)
""" test rbf kernel """
SVM.testRbf()
""" testdigits classification using rbf kernel """
SVM.testDigits(('rbf', 20))
def fit(self, dataMatIn, classLabels):
b, alphas = smoPK(dataMatIn, classLabels, 0.6, 0.001, 40)
ws = calcWs(alphas, dataMatIn, classLabels)
return b, alphas, ws
dm, ls = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoSimple(dm, ls, 0.6, 0.001, 40) # 简版smo算法
alphas[alphas > 0]
shape(alphas[alphas > 0])
svMat = []
for i in range(100):
if alphas[i] > 0.0:
svMat.append(dm[i])
print dm[i], ls[i] # 支持向量
svmMLiA.plot(dm, ls, svMat)
import svmMLiA
dm, ls = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoP(dm, ls, 0.6, 0.001, 40)
ws = svmMLiA.calcWs(alphas, dm, ls)
mat(dm)[0] * mat(ws) + b # 对第0个数据分类
ls[0]
import svmMLiA
dm, ls = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoP(dm, ls, 0.6, 0.001, 40)
svMat = []
for i in range(100):
if alphas[i] > 0.0:
svMat.append(dm[i])
ws = svmMLiA.calcWs(alphas, dm, ls)
svmMLiA.plot(dm, ls, svMat, ws, float(b))
import svmMLiA
if sign(predict)!=sign(labelArr[i]): errorCount += 1
print("the training error rate is: %f" % (float(errorCount)/m))
'''进行测试'''
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,oS.alphas[svInd]) + oS.b #加权求和，结果为一个数
if sign(predict)!=sign(labelArr[i]): errorCount += 1
print("the test error rate is: %f" % (float(errorCount)/m) )
'''result'''
ws = calcWs(oS.alphas,dataArr,labelArr)
print( 'aphas = ' + str(oS.alphas[oS.alphas>0]) )
print( 'b = ' + str(oS.b) )
print( 'w = ' + str(ws.T) )
a=oS.eCache
al = oS.alphas
#dataMatIn[0]*mat(ws)+b #判断一个数据点的分类
'''plot'''
xcord0 = [];ycord0 = []
xcord1 = [];ycord1 = []
fr = open(filename)#this file was generated by 2normalGen.py
for line in fr.readlines():
'''操作list类型读取txt'''
lineSplit = line.strip().split('\t')
xPt = float(lineSplit[0])
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)
'''result'''
ws = calcWs(oS.alphas, dataMatIn, classLabels)
print('aphas = ' + str(oS.alphas[oS.alphas > 0]))
print('b = ' + str(oS.b))
print('w = ' + str(ws.T))
a = oS.eCache
#dataMatIn[0]*mat(ws)+b #判断一个数据点的分类
plotResult(filename, dataMatIn, classLabels, oS, ws)
svmData = []
svmLabel = []
m, n = shape(dataMatIn)
for i in range(m):
if oS.alphas[i] > 0.0:
svmData.append(dataMatIn[i])
svmLabel.append(classLabels[i])
