def testPrc(kTup=('rbf', 10)):
dataArr, labelArr = loadDataSet('201404')
print 'load data done'
b, alphas = smoP(dataArr, labelArr, 200, 0.0001, 10000, kTup)
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]
saveSVM(svInd, sVs, labelSV, alphas[svInd]) #保存支持向量
m, n = shape(datMat)
errorCount = 0
for i in range(m):
kernelEval = kernelTrans(sVs, datMat[i, :], kTup)
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)
def handwritingIndentify(kTup):
featureList,labelList = loadImage('digits/trainingDigits')
print featureList
print labelList
b, alphas = svm.smoP(array(featureList),labelList,200,0.0001,10000,kTup)
print "b:",b, "alpha:",alphas
svInd = nonzero(alphas.A > 0)[0]
sVs = mat(array(featureList))[svInd]
labelSV= mat(labelList).T[svInd]
print "there a %s Support Vectors."%shape(sVs)[0]
featureMat = mat(array(featureList));labelMat = mat(labelList).T
m,n = shape(featureMat)
errorCount = 0
for i in range(m):
kernelMat = svm.kernelTrans(sVs, featureMat[i,:], kTup)
predict = kernelMat.T * multiply(labelSV,alphas[svInd]) + b
if sign(predict) != sign(labelMat[i]):
errorCount += 1
print "the training data error rate is %s"%(float(errorCount)/m)
def handwritingIndentify(kTup):
featureList, labelList = loadImage('digits/trainingDigits')
print featureList
print labelList
b, alphas = svm.smoP(array(featureList), labelList, 200, 0.0001, 10000,
kTup)
print "b:", b, "alpha:", alphas
svInd = nonzero(alphas.A > 0)[0]
sVs = mat(array(featureList))[svInd]
labelSV = mat(labelList).T[svInd]
print "there a %s Support Vectors." % shape(sVs)[0]
featureMat = mat(array(featureList))
labelMat = mat(labelList).T
m, n = shape(featureMat)
errorCount = 0
for i in range(m):
kernelMat = svm.kernelTrans(sVs, featureMat[i, :], kTup)
predict = kernelMat.T * multiply(labelSV, alphas[svInd]) + b
if sign(predict) != sign(labelMat[i]):
errorCount += 1
print "the training data error rate is %s" % (float(errorCount) / m)
# -*- coding: utf-8 -*-
"""
Created on Wed Sep 5 15:22:26 2018
@author: weixw
"""
import svm as sm
#通过训练数据计算 b, alphas
dataArr, labelArr = sm.loadDataSet('train.txt')
b, alphas = sm.smoP(dataArr, labelArr, 200, 0.0001, 10000, ('rbf', 0.10))
sm.drawDataMap(dataArr, labelArr, b, alphas)
sm.getTrainingDataResult(dataArr, labelArr, b, alphas, 0.10)
dataArr1, labelArr1 = sm.loadDataSet('test.txt')
#测试结果
sm.getTestDataResult(dataArr1, labelArr1, b, alphas, 0.10)
import svm
import numpy as np
dataArr, labelArr = svm.loadDataSet("testSet.txt")
print("dataArr.shape:", np.shape(dataArr), "labelArr.shape:",
np.shape(labelArr))
#b, alphas = svm.smoSimple(dataArr, labelArr, 0.6, 0.001, 40)
b, alphas = svm.smoP(dataArr, labelArr, 0.6, 0.001, 40)
print("b=", b)
# print("---")
print("alpha.shape:", alphas.shape)
print(alphas[alphas > 0])
# 支持向量
# for i in range(len(dataArr)):
# if alphas[i] > 0.0:
# print(dataArr[i], labelArr[i])
w = svm.calcWs(alphas, dataArr, labelArr)
#svm.plot_sv(dataArr, labelArr, w, b, alphas)
i = 5
y_ = svm.predict(dataArr[5], w, b)
print("y_:{}, y:{}".format(y_, labelArr[i]))
svm.eval(dataArr, labelArr, w, b)
def training(d, l, C = 0.6, tol = 0.01, max_iter = 20, p = True):
b, alphas = svm.smoP(d, l, C, tol, max_iter)
if p == True:
print calcrate(d, l, b, alphas)
return b, alphas
loadedlist = dir()
loaded = False
for name in loadedlist:
if not cmp(name.strip(), u'svm'):
loaded = True
print "svm.py loaded"
if (loaded):
reload(svm)
print "reload svm"
else:
import svm
print "import svm"
dataMat, labelMat = svm.loadDataSet('testSet.txt')
print "loadDataSet()"
#alphas,b = svm.smoSimple(dataMat,labelMat,0.6,0.001,40)
alphas, b = svm.smoP(dataMat, labelMat, 0.6, 0.001, 40)
print "calculate alphas ,bias"
print "plot linegrapha"
svm.plotBestFit(dataMat, labelMat, alphas, b)