def exConMat(dbname, r, cate, iterflag, modeflag):
fn4 = dbname + '_results_r' + str(
r) + '_' + iterflag + '_' + modeflag + '.npy'
fn5 = dbname + '_results_r' + str(
r) + '_' + iterflag + '_' + modeflag + '.cpkl'
path4 = util.getPath2(fn4)
path5 = util.getPath2(fn5)
cres = numpy.load(path4)
objs = dataLoader3.cpklload(path5)
anaT, concT = summarize(cres, cate)
cml = []
for i in xrange(numpy.shape(concT)[0]):
x1 = concT[i, 2]
x2 = concT[i, 1]
s, t = numpy.shape(cres)
for m in xrange(s):
y1 = cres[m, 2]
y2 = cres[m, 5]
if cres[m, 2] == concT[i, 2] and cres[m, 5] == concT[i, 1]:
cml.append([
concT[i, 2], concT[i, 1], objs[m][0], objs[m][1],
objs[m][2], objs[m][3]
])
fn6 = dbname + '_result_r' + str(
r) + '_' + iterflag + '_ex' + modeflag + '.cpkl'
path6 = util.getPath2(fn6)
dataLoader3.cpklsave(cml, path6)
def seqLearnCM(cate,
ratio,
r,
numCenterList,
alphaList,
QList,
KList,
lenPara,
dbname,
iter='ZZZ',
mode='ZZZ'):
# setting and starting ppservers ...
ppservers = ()
ncpus = 2
job_server = pp.Server(ncpus, ppservers=ppservers)
print str(datetime.datetime.now()
)[:19] + " Starting python parallel with", job_server.get_ncpus(
), "workers. "
paraPerm = list(itertools.product(numCenterList, alphaList, QList, KList))
path4 = util.getPath2(dbname + "_ycobjs_r" + str(r) + ".cpkl")
if os.path.exists(path4):
fnResults = util.getPath2(dbname + "_results_r" + str(r) + "_" + iter +
"_" + mode + ".npy")
fnRBFobjs = util.getPath2(dbname + "_results_r" + str(r) + "_" + iter +
"_" + mode + ".cpkl")
if not os.path.exists(fnResults):
ctrainM, ctestM, ytrainM, ytestM = dataLoader3.cpklload(path4)
# ctrainM, ctestM = numpy.mat(ctrain).T, numpy.mat(ctest).T
results = numpy.mat(numpy.zeros((0, lenPara)))
objsRBF = []
jobs = [
job_server.submit(
classifyCM,
(ratio, r, para[0], para[1], para[2], para[3], lenPara,
ytrainM, ytestM, ctrainM, ctestM, dbname), (),
("numpy", "dataProcess", "RBFNetwork", "dataLoader3",
"datetime", "util")) for para in paraPerm
]
for job in jobs:
cnm = job()
result, objs = cnm[0], cnm[1]
results = numpy.concatenate((results, result), axis=0)
objsRBF = objsRBF + objs
print "\n"
if not (numpy.shape(results)[0] == 0 or len(objsRBF) == 0):
dataLoader3.saveMatrix([results], [fnResults])
dataLoader3.saveObjects([objsRBF], [fnRBFobjs])
else:
util.infoErr([fnResults, fnRBFobjs])
else:
util.exPath([fnResults, fnRBFobjs])
else:
util.noPath([path4])
def anaCMat(dbname, r, iterflag, cate):
fn4 = dbname + '_results_r' + str(r) + '_' + iterflag + '_CM.npy'
fn5 = dbname + '_results_r' + str(r) + '_' + iterflag + '_exCM.cpkl'
path4 = util.getPath2(fn4)
path5 = util.getPath2(fn5)
cres = numpy.load(path4)
ana3, conc3 = summarize(cres, cate)
cmat = dataLoader3.cpklload(path5)
icc = []
for cm in cmat:
icc.append(cm[5])
return ana3, conc3, cres, icc
def seqLearnTest(cate,
ratio,
r,
numCenterList,
alphaList,
QList,
KList,
lenPara,
dbname,
iter='ZZZ',
mode='ZZZ'):
paraPerm = list(itertools.product(numCenterList, alphaList, QList, KList))
path4 = util.getPath2(dbname + "_ycobjs_r" + str(r) + ".cpkl")
if os.path.exists(path4):
fnResults = util.getPath2(dbname + "_results_r" + str(r) + "_" + iter +
"_" + mode + ".npy")
# fnRBFobjs = util.getPath2(dbname + "_results_r" + str(r) + "_" + iter + ".cpkl")
if not os.path.exists(fnResults):
ctrainM, ctestM, ytrainM, ytestM = dataLoader3.cpklload(path4)
# ctrainM, ctestM = numpy.mat(ctrain).T, numpy.mat(ctest).T
results = numpy.mat(numpy.zeros((0, lenPara)))
objsRBF = []
for para in paraPerm:
result = classify(ratio, r, para[0], para[1], para[2], para[3],
lenPara, ytrainM, ytestM, ctrainM, ctestM,
dbname)
# cnm = job()
# result, obj = cnm[0], cnm[1]
results = numpy.concatenate((results, result), axis=0)
# objsRBF = objsRBF + obj
# results = numpy.concatenate((results, job()[0]), axis = 0)
# objsRBF = objsRBF + job()[1]
print "\n"
if not numpy.shape(results)[0] == 0:
dataLoader3.saveMatrix([results], [fnResults])
# dataLoader3.saveObjects([objsRBF], [fnRBFobjs])
else:
util.infoErr([fnResults])
else:
util.exPath([fnResults])
else:
util.noPath([path4])
def classifyCM(ratio, r, numCenter, alpha, Q, K, lenPara, trainY, testY,
countLineTrain, countLineTest, dbname):
results = numpy.mat(numpy.zeros((0, lenPara)))
objs = []
path5 = util.getPath2(dbname + "_bow" + "_r" + str(r) + "_k" + str(K) +
".cpkl")
# bowTrain, bowTest, centroids = dataLoader3.cpklload(path5)
if os.path.exists(path5):
print "\n" + str(datetime.datetime.now(
))[:19] + " Sequence learning for {r = " + str(
r) + ", numCenter = " + str(numCenter) + ", alpha = " + str(
alpha) + ", Q = " + str(Q) + ", K = " + str(K) + "} ... "
bowTrain, bowTest, centroids = dataLoader3.cpklload(path5)
# normalize dataset
trainX = dataProcess.autoNorm(bowTrain, countLineTrain)
testX = dataProcess.autoNorm(bowTest, countLineTest)
# define the architecture of Neural Network
indim = numpy.shape(trainX)[1]
outdim = numpy.shape(trainY)[1]
RBFClassifier = RBFNetwork.RBFNN(indim, numCenter, outdim, alpha, Q)
# classifier training and testing
RBFClassifier.train(trainX, trainY)
trainOut = RBFClassifier.test(trainX)
testOut = RBFClassifier.test(testX)
print str(
datetime.datetime.now()
)[:
19] + " The classifier testing is done! the shapes of {outputTrain, outputTest} are: " + str(
numpy.shape(trainOut)) + ", " + str(numpy.shape(testOut))
'''bug bug bug'''
results1, cmtrain, cmtest = RBFClassifier.evaluateAll(
trainX, trainY, trainOut, testX, testY, testOut)
results2 = [ratio, r, numCenter, alpha, Q, K]
results3 = numpy.mat(results2 + results1)
results = numpy.concatenate((results, results3), axis=0)
'''***************************************************'''
obj = [trainOut, testOut, cmtrain, cmtest]
objs.append(obj)
'''***************************************************'''
'''bug bug bug'''
# The epoch is done!
print str(datetime.datetime.now(
))[:19] + " Sequence learning for {r = " + str(
r) + ", numCenter = " + str(numCenter) + ", alpha = " + str(
alpha) + ", Q = " + str(Q) + ", K = " + str(K) + "} is done! "
else:
print str(datetime.datetime.now()
)[:19] + " Files: " + path5 + " do not exist! "
# print results, len(objs)
return (results, objs)
def mergeMatrix(dbname, r, iterflag, modelist):
fn1 = dbname + '_results_r' + str(r) + '_' + iterflag + '.npy'
path1 = util.getPath2(fn1)
result = numpy.load(path1)
checklist = []
for mode in modelist:
fn2 = dbname + '_results_r' + str(
r) + '_' + iterflag + '_' + mode + '.npy'
path2 = util.getPath2(fn2)
if os.path.exists(path2) and path2 not in checklist:
res = numpy.load(path2)
result = numpy.concatenate((result, res), axis=0)
checklist.append(path2)
else:
util.noPath(path2)
return result
import os
import util
KList = [k for k in xrange(128, 4096 + 1, 128)] + [200, 600, 1000, 4000]
for i in xrange(250):
if i not in KList:
filename = 'kth_bow_r0_k' + str(i) + '.cpkl'
path = util.getPath2(filename)
if(os.path.exists(path)):
os.remove(path)
print util.fetchTime() + ' ' + filename + 'is removed! '
else:
# print util.fetchTime() + ' ' + filename + ' error! '
pass
def evaluate(dbname, r, iterflag, modeflag):
fn6 = dbname + '_result_r' + str(
r) + '_' + iterflag + '_ex' + modeflag + '.cpkl'
fn4 = dbname + "_ycobjs_r" + str(r) + ".cpkl"
path4 = util.getPath2(fn4)
path6 = util.getPath2(fn6)
ycobj = dataLoader3.cpklload(path4)
outcm = dataLoader3.cpklload(path6)
ctrain, ctest, ytrain, ytest = ycobj[0], ycobj[1], ycobj[2], ycobj[3]
mtclistMlist = []
for oc in outcm:
m, k, outtrain, outtest, cmtrain, cmtest = oc[0], oc[1], oc[2], oc[
3], oc[4], oc[5]
# tartrainL = transLabelML(ytrain)
# outtrainL = transLabelML(outtrain)
outtestI = dataProcess.ftoi(outtest)
'''designed for kth'''
ytestM = numpy.mat(ytest)
tar = transLabelML(ytestM)
out = transLabelML(outtestI)
cm = ConMat(out, tar) # not (tar, out)
print cm
# iF1, iG, ipairs = AnaConMat(cm)
mtclist = []
for i in xrange(numpy.shape(cm)[1]):
t, it = multi2bin(tar, i)
o, io = multi2bin(out, i)
auc = AUC(t, o)
print auc
'''**************bugs***************'''
# assumption: TNR == iTPR and TPR == iTNR
# TPR, TNR = func(t, o)
# iTPR, iTNR = func(it, io)
print m, k, i
pre, rec, thre = PRC(t, o)
ipre, irec, ithre = PRC(it, io)
tnr, itnr = rec, irec
tpr, itpr = irec, rec
gmean = numpy.sqrt(tpr[-2] * tnr[-2])
print pre, rec, thre
print ipre, irec, ithre
print gmean
'''**************bugs***************'''
f1s = F1Score(t, o)
print f1s
mtc = [auc, pre[-2], rec[-2], tpr[-2], tnr[-2], gmean, f1s[-1]]
mtclist.append(mtc)
mtclistM = numpy.array(mtclist)
mtclistMlist.append(mtclistM)
return mtclistMlist
print gmean
'''**************bugs***************'''
f1s = F1Score(t, o)
print f1s
mtc = [auc, pre[-2], rec[-2], tpr[-2], tnr[-2], gmean, f1s[-1]]
mtclist.append(mtc)
mtclistM = numpy.array(mtclist)
mtclistMlist.append(mtclistM)
return mtclistMlist
if __name__ == '__main__':
path1 = util.getPath2('targetSetTrain.npy')
path2 = util.getPath2('targetSetTest.npy')
m = numpy.load(path1)
n = numpy.load(path2)
a = numpy.mat([[1, 0, 0, 0], [0, 0, 1, 0], [0, 1, 0, 0], [0, 0, 0, 1],
[1, 0, 0, 0], [0, 0, 1, 0]])
b = numpy.mat([[1, 0, 0, 0], [0, 1, 0, 0], [0, 0, 0, 1], [0, 0, 1, 0],
[1, 0, 0, 0], [0, 1, 0, 0]])
tar = transLabelML(m)
out = transLabelML(n)
cm = ConMat(out, tar) # not (tar, out)
print cm
iterflag = 'X'
modeflag = 'CM'
modelist = ['A1']
# func = 'conc'
func = 'exCM'
# mode = 'anCM'
mlower = 0
klower = 0
mupper = 200
kupper = 4096
KList = [4000, 4096, 200, 600, 1000]
'''*********************************************************'''
mtclistMlist = iMetrics.evaluate(dbname, r, iterflag, modeflag)
tmplist = [[0] * 7]
tmparry = numpy.array(tmplist)
summer = numpy.zeros((0, 7))
for mtc in mtclistMlist:
summer = numpy.concatenate((summer, mtc), axis=0)
summer = numpy.concatenate((summer, tmparry), axis=0)
fn8 = dbname + '_result_r' + str(
r) + '_' + iterflag + '_mtc' + modeflag + '.cpkl'
path8 = util.getPath2(fn8)
dataLoader3.cpklsave(mtclistMlist, path8)