def testRbf(k1=100):
dataArr,labelArr = svm.loadDataSet('../data/test1.txt')
dataMat = mat(dataArr)
#print dataMat
b,alphas = svm.smoP(dataArr, labelArr, 200, 0.01, 10000, ('rbf', k1)) #C=200 important
datMat=mat(dataArr); labelMat = mat(labelArr).transpose()
#print alphas.A>0
svInd=nonzero(alphas.A>0)[0]
sVs=datMat[svInd] #get matrix of only support vectors
#print dataMat
#ax.scatter(sVs[:,0], sVs[:,1], s=30, c='green', marker='s')
#ax.scatter(sVs[:,0], sVs[:,1])
labelSV = labelMat[svInd];
print "there are %d Support Vectors" % shape(sVs)[0]
m,n = shape(datMat)
errorCount = 0
for i in range(m):
kernelEval = svm.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 = svm.loadDataSet('../data/test2.txt')
errorCount = 0
datMat=mat(dataArr); labelMat = mat(labelArr).transpose()
m,n = shape(datMat)
fig = plt.figure()
ax = fig.add_subplot(111)
#print sVs
for i in range(m):
kernelEval = svm.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) > 0:
#c = [int((0.2/float(predict))) for cc in range(0, 60)]
#ax.scatter(range(0, 60), array(datMat[i,:]), array(c), array(c))
ax.scatter(range(0, 60), array(datMat[i,:]), s=20, c='green', marker='s')
#print datMat[i,:], sign(predict), sign(labelArr[i])
continue
else:
ax.scatter(range(0, 60), array(datMat[i,:]), s=20, c='red', marker='s')
#print datMat[i,:], sign(predict), sign(labelArr[i])
continue
for i in range(shape(sVs)[0]):
ax.scatter(range(0, 60), array(sVs[i]), s=10, c='yellow', marker='s')
continue
plt.show()
print "the test error rate is: %f" % (float(errorCount)/m)
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]
import svmMLiA
dataMat, labelMat = svmMLiA.loadDataSet(
"E:\Desktop\machinelearninginaction\Ch06/testSet.txt")
print dataMat
print labelMat
b, alphas = svmMLiA.smoSimple(dataMat, labelMat, 0.6, 0.001, 40)
print b
print alphas[alphas > 0]
for i in range(100):
if alphas[i] > 0.0: print dataMat[i], labelMat[i]
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
'6.4 machine learning in action'
__author__ = 'lxp'
import svmMLiA
import numpy as np
dataArr, labelArr = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoPNew(dataArr, labelArr, 0.6, 0.001, 40)
ws = svmMLiA.calcWs(alphas, dataArr, labelArr)
datMat = np.mat(dataArr)
'''
i = input("要检验的数据编号\n")
print(datMat[0] * np.mat(ws) + b)
print(labelArr[0])
'''
count = 0
m = np.shape(dataArr)[0]
for i in range(m):
if np.sign(datMat[i] * np.mat(ws) + b) != labelArr[i]:
count += 1
print(count / m)
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
'''data & parameter'''
filename = 'testSet.txt'
dataMatIn, classLabels = loadDataSet(filename)
toler = 0.001
C = 0.6
maxIter = 40
'''PlattSMO算法'''
#def smoP(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" %
def test_smo_all():
dataArr, labelArr = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoP(dataArr, labelArr, 0.6, 0.001, 40)
print(b)
print(alphas[alphas > 0])
def test_4():
dataArr, labelArr = svmMLiA.loadDataSet('testSet.txt')
b, alphas = svmMLiA.smoP(dataArr, labelArr, 0.6, 0.001, 40)
print shape(alphas[alphas > 0])
for i in range(100):
if alphas[i] > 0.0: print dataArr[i], labelArr[i]
def test_1():
dataArr, labelArr = svmMLiA.loadDataSet('testSet.txt')
print labelArr
