def Basic(trainSet,
testSet,
file,
fout,
name,
vecin,
clfName,
isCount=False):
auc = 0
l = GLOB(clfName).getClassifier()
l.buildClassifier(trainSet)
vec = l.evaluateModel(testSet)
actual = testSet[:, -1]
if isCount:
vals = DPLIB.getMeasuresCount(actual, vec)
print(name + ":" + file + ": " + str(vals))
fout.write("\n" + name + ":" + file + ": " + "Vals=" + str(vals))
else:
tvals = DPLIB.getConfMatrix(actual, vec)
vals = DPLIB.getMeasures(tvals)
auc = DPLIB.getAUC(actual, vec)
print(name + ":" + file + ": " + str(vals) + " AUC = " + str(auc))
fout.write("\n" + name + ":" + file + ": " + " AUC = " + str(auc) +
";" + "Vals=" + str(vals))
def NNFilterMulti(trainSeti, testSet, file, fout, name, vecin, count,
clfName, tunelrn, vSets):
startTime = Common.getCurrentTimeMil()
trainSet = DPLIB.NNFilterMulti(trainSeti, testSet, count)
l = GLOB(clfName, tunelrn).getClassifier()
if (tunelrn):
l = l.getTunedCLF(trainSet, vSets, fout, name, file)
print("#TUNE-LRN-PARAMS-" + name + ":" + file + ": " +
str(l.selectedParams))
fout.write("#TUNE-LRN-PARAMS-" + name + ":" + file + ": ")
fout.write(str(l.selectedParams))
fout.write("\n")
sCheck = l.getCLFOptions()
print("#SETSET-LRN-PARAMS-" + name + ":" + file + ": " +
str(sCheck))
fout.write("#SETSET-LRN-PARAMS-" + name + ":" + file + ": ")
fout.write(str(sCheck))
fout.write("\n")
l.buildClassifier(trainSet)
vec = l.evaluateModel(testSet)
vecin = vec
tvals = DPLIB.getConfMatrix(testSet[:, -1], vecin)
print("#CONF-TEST-" + name + ":" + file + ": " + str(tvals))
fout.write("#CONF-TEST-" + name + ":" + file + ": ")
fout.write(str(tvals))
fout.write("\n")
auc = DPLIB.getAUC(testSet[:, -1], vec)
vals = DPLIB.getMeasures(tvals)
print(name + ":" + file + ": " + str(vals) + " AUC = " + str(auc))
fout.write(name + ":" + file + ": ")
fout.write(str(vals))
fout.write(" AUC = ")
fout.write(str(auc))
fout.write("\n")
time = Common.getCurrentTimeMil() - startTime
print("#TIME-FOR:" + name + ":" + file + ": " + str(time))
fout.write("#TIME-FOR:" + name + ":" + file + ": " + str(time) + "\n")
return vecin
def fit(self, trainSet, testSet, vSets, vSetType, clfName):
if self.isCount:
self.mad = GA.getBugSTDForMutation(trainSet)
if len(set(list(trainSet[:, -1]))) < 2:
self.prnt('Error: Number of classes can not be less than two.')
print('Error: Number of classes can not be less than two.')
return
trainSet, testSet = np.copy(trainSet), np.copy(testSet)
tstSize = len(testSet)
partSize = int(tstSize / self.numParts)
isOK = True
np.random.shuffle(testSet)
self.FinalLearner = None
self.FinalDataset = None
diffs = []
vSets = ValidationSetManager.getValidationSets(vSets, vSetType,
trainSet, testPart)
pop = GA.createInitialPopulation(trainSet, self.popSize,
fixedTrainSize, self.chrmSize)
pop = GA.assignFitness(pop,
GLOB(clfName).getClassifier(), vSets,
self.isCount)
pop = DPLIB.SortPopulation(pop)
for g in range(self.numGens):
self.prnt(str(g) + " ")
newPop = GA.generateNewPopulation(pop,
self.sizeTopP,
selectionType='TORNAMENT',
isCount=self.isCount,
mad=mad)
newPop = GA.assignFitness(newPop,
GLOB(clfName).getClassifier(), vSets,
self.isCount)
newPop = DPLIB.SortPopulation(newPop)
newPop, rdel = DPLIB.CombinePops(pop, newPop)
rdel = None
diff, exit = GA.checkExit(pop, newPop, self.countComp)
diffs.append(diff)
pop.clear()
pop = newPop
if (pop[0].getFitness() > 0.0) and (exit):
break
self.FinalDataset = pop[0].ds
def getKeySetKeys(self):
if self.isCount:
self.keySet = list(
DPLIB.getMeasuresCount([0, 1, 2, 3], [0, 1, 2, 3]).keys())
else:
self.keySet = list(DPLIB.MEASURES_BIN.keys())
return self.keySet
def WMulti(files,
file,
testSet,
fout,
features,
name,
clfName,
dp,
convertToBinary=True):
train = []
for file2 in files:
if (file2[0:3] == file[0:3] and file2 < file < 0):
train.append(file2)
if (len(train)):
trainSet = DPLIB.LoadCSV(train, dp, features, convertToBinary)
if (name.lower().find("infogain") >= 0):
#int indi[] = DPLIB.fSelectInfoGain(trainSet);
#if (DPLIB.useIterativeInfoGainSubsetting)
#{
# indi = DPLIB.iterativeInfoGainSubsetting(trainSet, indi,clfName);
#}
#else
# indi = DPLIB.getTopX(indi);
#trainSet = DPLIB.fSelectSet(trainSet, indi);
#testSet = DPLIB.fSelectSet(testSet, indi);
pass
l = GLOB(clfName).getClassifier()
l.buildClassifier(trainSet)
vec = l.evaluateModel(testSet)
tvals = DPLIB.getConfMatrix(testSet[:, -1], vec)
auc = DPLIB.getAUC(testSet[:, -1], vec)
vals = DPLIB.getMeasures(tvals)
print(name + ":" + file + ": " + str(vals) + " AUC = " + str(auc))
fout.write("\n" + name + ":" + file + ": " + " AUC = " + str(auc) +
";" + "Vals=" + str(vals))
else:
print(name + ":" + file + ": " + "!!!" + " AUC = !!!")
fout.write("\n" + name + ":" + file + ": !!!")
def score(self, predictions, testLabels):
if self.isCount:
pass
else:
if testLabels != None:
confs, measures = DPLIB.getConfAndExtMeasures(testLabels, predictions)
return confs, measures
return None
def toDict(lds):
measures = None
expNames = ('GIS','LSH','FIXED','VAR','VR','FX',)
out = {}
for line in DPLIB.doReplaces('\n'.join(['\n'.join(l) for l in lds])).split('\n'):
line = line.strip()
if line.startswith(expNames):
parts = line.replace("': ","'=>").split(':')
perf = parts[2].replace('{','').replace('}','').strip()
method = parts[0]
ds = parts[1]
learner = method.split('-')[-1]
apprName = method[:method.rfind('-')]
featureSpace = apprName.split('-')[-1]
vals = []
measures = []
for p in perf.split(','):
p = p.strip().split('=>')
p[0] = p[0].strip().replace("'","")
p[1] = p[1].strip()
if p[0] not in measures:
measures.append(p[0])
vals.append(float(p[1]))
if method not in out.keys():
out[method] = {}
if ds not in out[method].keys():
out[method][ds] = {}
out[method][ds]['measures'] = {}
out[method][ds]['confs'] = []
for mindex, m in enumerate(measures):
if m not in out[method][ds]['measures'].keys():
out[method][ds]['measures'][m] = []
out[method][ds]['measures'][m].append(vals[mindex])
elif line.startswith("#CONF-TEST:"):
parts = line.replace("': ","'=>").split(':')[1:]
perf = parts[2].replace('{','').replace('}','').strip()
method = parts[0]
ds = parts[1]
learner = method.split('-')[-1]
apprName = method[:method.rfind('-')]
featureSpace = apprName.split('-')[-1]
if method not in out.keys():
out[method] = {}
if ds not in out[method].keys():
out[method][ds] = {}
out[method][ds]['measures'] = {}
out[method][ds]['confs'] = []
out[method][ds]['confs'].append(perf)
return out
def createInitialPopulation(pool, popSize, fixedTrainSize,
maxChromosomeSize):
pop = []
for i in range(popSize):
uinds = set()
size = GA.getChromosomeSize(fixedTrainSize, maxChromosomeSize)
while True:
#Select a subset that has noth classes
trSet = DPLIB.getRandomSubSet(size, pool)
if len(set(list(trSet[:, -1]))) >= 2:
break
pop.append(trSet)
return pop
def LOC50(testSeti, file, fout, name, locIndex):
startTime = Common.getCurrentTimeMil()
spentISTime = 0
tempTime = 0
spentISTime = Common.getCurrentTimeMil()
allloc = testSeti[:, locIndex]
med = np.median(allloc)
predicted = [1 if t >= med else 0 for t in allloc]
actual = testSeti[:, -1]
tvals = DPLIB.getConfMatrix(actual, predicted)
print("#CONF-TEST-" + name + ":" + file + ": " + str(tvals))
fout.write("#CONF-TEST-" + name + ":" + file + ": ")
fout.write(str(tvals))
fout.write("\n")
vals = DPLIB.getMeasures(tvals)
auc = DPLIB.getAUC(actual, predicted)
print(name + ":" + file + ": " + str(vals) + " AUC = " + str(auc))
fout.write(name + ":" + file + ": ")
fout.write(str(vals))
fout.write(" AUC = ")
fout.write(str(auc))
fout.write("\n")
time = Common.getCurrentTimeMil() - startTime
print("#TIME-FOR:" + name + ":" + file + ": " + str(time))
fout.write("#TIME-FOR:" + name + ":" + file + ": " + str(time) + "\n")
print("#TIME-FOR-IS:" + name + ":" + file + ": " + str(time))
fout.write("#TIME-FOR-IS:" + name + ":" + file + ": " + str(time) +
"\n")
def assignFitness(pop, clf, vSets, isCount):
for i in range(len(pop)):
clf.buildClassifier(pop[i])
all_confs_measures = []
all_predictions = clf.evaluateMultiModel(vSets)
if isCount:
pass
else:
for index, predictions in enumerate(all_predictions):
confs_measures = DPLIB.getConfMatrixAndExtMeasures(
vSets[index][:, -1], predictions)
all_confs_measures.append(confs_measures)
h = CHRM_GIS(pop[i], all_measures, all_confs_measures)
pop[i] = h
return pop
def Mutate(ds, mProb=0.1, mCount=1, isCount=False, mad=0.0):
"""
Performs mutation with specified parameters.
Please note that the mutation should consider the fact that datasets might contain
repeated instances of the same data row, and the operation should consider consistency.
After performing mutation, all instances with exact same data should have a consistent label.
"""
r2 = np.random.rand()
if (r2 <= mProb):
rands = set()
i = 0
while (i < mCount):
r1 = np.random.randint(0, len(ds))
if len(rands) == len(ds):
return ds
if (r1 in rands):
continue
instLabel = ds[r1, -1]
#Mutation for non binary class values. Shift Using normal distribution random value
if isCount:
shift = int(np.random.randn() * mad)
classVal = instLabel + shift
if (classVal < 0):
classVal = 0
else:
classVal = (1 - instLabel)
st = DPLIB.FindAllSimilarInstancesIndexes(r1, ds)
for r1 in st:
rands.add(r1)
ds[r1, -1] = classVal
i += 1
return ds
def crossOver(ds1, ds2, fixedSize, isCount=False):
"""
Cross over operator. It supports both one point and two point cross over methods.
Further, it can keep the datasets the same size, as well as change the data in a way to
generate varying size chromosomes.
Please note that the cross over should consider the fact that datasets might contain
repeated instances of the same data row, and the operation should consider consistency.
This is especially inportant since, data can come from multiple sources, as well as, the effect of
mutation on particular instances from previous generations.
After performing crossover, all instances with exact same data should have a consistent label.
This is done through majority voting rule in the cross over operations.
"""
ss = len(ds1)
point1 = 0
point2 = 0
if (fixedSize):
point1 = np.random.randint(ss)
point2 = point1
else:
point1 = np.random.randint(ss)
point2 = np.random.randint(len(ds2))
if (len(ds1) >= 4000):
point1 = int(len(ds1) / 2)
if (len(ds2) >= 4000):
point2 = int(len(ds2) / 2)
np.random.shuffle(ds1)
np.random.shuffle(ds2)
ds1c = np.copy(ds1[:point1, :])
ds2c = np.copy(ds2[:point2, :])
ds1c = np.append(ds1c, ds2[point2:, :], axis=0)
ds2c = np.append(ds2c, ds1[point1:, :], axis=0)
pSet = set()
for i in range(len(ds1c)):
if i in pSet:
continue
t = list(DPLIB.FindAllSimilarInstancesIndexes(i, ds1c))
lbl = 0
index = -1
for j in range(len(t)):
index = t[j]
lbl += ds1c[index, -1]
pSet.add(index)
lbl = lbl / (len(t))
if not isCount:
if (lbl >= 0.5):
lbl = 1
else:
lbl = 0
else:
if lbl < 0:
lbl = 0
for j in range(len(t)):
index = t[j]
#Process extra
#if ((int)ds1c.instance(index).classValue()!=(int)lbl)
# ds1c.instance(index).SetExtra(ds1c.instance(index).GetExtra() +"-C="+String.valueOf((int)(1-lbl))+">"+String.valueOf((int)lbl));
ds1c[index, -1] = lbl
pSet.clear()
for i in range(len(ds2c)):
if (i in pSet):
continue
t = list(DPLIB.FindAllSimilarInstancesIndexes(i, ds2c))
lbl = 0
index = -1
for j in range(len(t)):
index = t[j]
lbl += ds2c[index, -1]
pSet.add(index)
lbl = lbl / len(t)
if not isCount:
if (lbl >= 0.5):
lbl = 1
else:
lbl = 0
else:
if lbl < 0:
lbl = 0
for j in range(len(t)):
index = t[j]
#Process extra
#if ((int)ds2c.instance(index).classValue()!=(int)lbl)
# ds2c.instance(index).SetExtra(ds2c.instance(index).GetExtra() +"-C="+String.valueOf((int)(1-lbl))+">"+String.valueOf((int)lbl));
ds2c[index, -1] = lbl
return ds1c, ds2c
def CreateBuckets(self, trainSet, testSet, vSets, name, testCut, iternum,
save, superbit, stages, buckets, doprint, clfName,
tunelrn):
out = []
if self.isCount:
keySet = list(
DPLIB.getMeasuresCount([0, 1, 2, 3], [0, 1, 2, 3]).keys())
else:
keySet = list(
DPLIB.getExtMeasures({
"tp": 1,
"tn": 2,
"fp": 3,
"fn": 4
}).keys())
out.append("#STARTED FOR-" + name + ":" + self.file + ": ")
startTime = Common.getCurrentTimeMil()
spentIsTime = 0
tempTime = 0
out.append("#Using also Label For train in LSH")
if (vSets == None):
vSets = []
vSets.append(trainSet)
if (save):
DPLIB.SaveToCsv(
trainSet, "MAIN-TRAIN-FILE-" + "ITER=" + str(iternum) + "--" +
"METHOD=" + name + "--FILE=" + self.file + "--")
DPLIB.SaveToCsv(
testSet, "MAIN-TEST-FILE-" + "ITER=" + str(iternum) + "--" +
"METHOD=" + name + "--FILE=" + self.file + "--")
for i in range(len(vSets)):
DPLIB.SaveToCsv(
trainSet,
"VSET-FILE-" + "INDEX=" + str(i) + "ITER=" + str(iternum) +
"--" + "METHOD=" + name + "--FILE=" + self.file + "--")
np.random.shuffle(trainSet)
np.random.shuffle(testSet)
tempTime = Common.getCurrentTimeMil()
count = len(trainSet)
bins = {}
# R^n
n = trainSet.shape[1] - 1
binid = 0
#lshmin = LSHMinHash(stages, buckets, n);
try:
lshsuper = LSHSuperBit(stages=stages,
buckets=buckets,
dimensions=n)
except Exception as ex:
print('##SuperBit with specified parameters failed:' + str(ex))
return None
sp = 0.75
# Compute a SuperBit signature, and a LSH hash
for i in range(count):
vector = trainSet[i, 1:].tolist()
hash = None
if (superbit):
hash = lshsuper.hash(vector)
else:
##Minhash support
# #hash = lshmin.hash(vecBool);
pass
binid = hash[0]
if not binid in bins.keys():
bins[binid] = []
bins[binid].append(trainSet[i])
spentIsTime += Common.getCurrentTimeMil() - tempTime
numBins = len(bins.keys())
for binid in bins.keys():
bins[binid] = np.array(bins[binid])
out.append("#Number of BINS:" + name + ":" + self.file + ": " +
str(numBins))
pop = []
for i in bins.keys():
trSet = bins[i]
l = GLOB(clfName, tunelrn).getClassifier()
#if (tunelrn):
# l = l.getTunedCLF(trSet, vSets,fout,name, file);
l.buildClassifier(trSet)
cf = 0
j = 0
allvecs = []
confs = []
allcfs = []
allaucs = []
valsA = None
confsA = None
aucA = 0.0
for vSet in vSets:
vec = None
actuals = None
vec = l.evaluateModel(vSet)
actuals = vSet[:, -1]
vals = None
auc = 0
if self.isCount:
vals = DPLIB.getMeasuresCount(actuals, vec)
else:
auc = DPLIB.getAUC(actuals, vec)
aucA += auc
allaucs.append(auc)
if (testCut):
vCF = 0.1
bestCF = 0
bestCFVal = -1
bestVals = None
while True:
tvals = DPLIB.getConfMatrix(actuals, vec, vCF)
measures = DPLIB.getMeasures(tvals)
fit = measures["F"] * measures["GMean1"]
if (fit > bestCFVal or bestVals == None):
bestCFVal = fit
bestCF = vCF
bestVals = tvals
vCF += 0.1
if (vCF >= 1):
break
if (confsA == None):
confsA = {key: 0 for key in bestVals.keys()}
for j in confsA.keys():
confsA[j] += bestVals[j]
confs.append(bestVals)
vals = DPLIB.getMeasures(bestVals)
cf += bestCF
allcfs.append(bestCF)
else:
tvals = DPLIB.getConfMatrix(actuals, vec)
if (confsA == None):
confsA = {key: 0 for key in tvals.keys()}
for j in confsA.keys():
confsA[j] += tvals[j]
confs.append(tvals)
vals = DPLIB.getMeasures(tvals)
allcfs.append(DPLIB.DefaultCF)
allvecs.append(vals)
if (valsA == None):
valsA = {key: 0 for key in keySet}
for j in keySet:
valsA[j] += vals[j]
for j in keySet:
valsA[j] /= len(vSets)
h = None
if not self.isCount:
for j in confsA.keys():
confsA[j] /= len(vSets)
if (testCut):
cf /= len(vSets)
aucA /= len(vSets)
h = CHRM_GIS(trSet, valsA, aucA)
h.fitnesses = allvecs
h.aucs = allaucs
h.conf = confsA
h.confs = confs
h.allcfs = allcfs
if (testCut):
h.bestCF = cf
else:
h.bestCF = DPLIB.DefaultCF
else:
h = CHRM_GIS_Count(trSet, valsA)
h.fitnesses = allvecs
pop.append(h)
l = None
tempTime = Common.getCurrentTimeMil()
pop = DPLIB.MySort(pop)
spentIsTime += Common.getCurrentTimeMil() - tempTime
top = pop[0]
out.append("#Instances in Top:" + str(len(top.ds)))
out.append("#STAGES:" + name + ":" + self.file + ": " + str(stages))
out.append("#BUCKETS:" + name + ":" + self.file + ": " + str(buckets))
if not self.isCount:
out.append("#BEST-CF-VALUE:" + name + ":" + self.file + ": " +
str(top.bestCF))
l = GLOB(clfName, tunelrn).getClassifier()
if (tunelrn):
l = l.getTunedCLF(top.ds, vSets, fout, name, file)
out.append("#TUNE-LRN-PARAMS-" + name + ":" + self.file + ": " +
str(l.selectedParams))
sCheck = l.getCLFOptions()
out.append("#SETSET-LRN-PARAMS-" + name + ":" + self.file + ": " +
str(sCheck))
l.buildClassifier(top.ds)
vec = l.evaluateModel(testSet)
out.append("#LSH-FOR-TOP-ONLY")
if self.isCount:
vals = DPLIB.getMeasuresCount(testSet[:, -1], vec)
out.append(name + ":" + self.file + ": " + str(vals))
else:
tvals = DPLIB.getConfMatrix(testSet[:, -1], vec, top.bestCF)
out.append("#CONF-TEST-" + name + ":" + self.file + ": " +
str(tvals))
vals = DPLIB.getMeasures(tvals)
auc = DPLIB.getAUC(testSet[:, -1], vec)
vals['auc'] = auc
out.append(name + ":" + self.file + ": " + str(vals))
for i in range(len(pop)):
pop[i] = None
pop = None
for i in bins.keys():
bins[i] = None
bins = None
time = Common.getCurrentTimeMil() - startTime
if (name.find("LSHTune") < 0):
out.append("#TIME-FOR:" + name + ":" + self.file + ": " +
str(time))
out.append("#TIME-FOR-IS:" + name + ":" + self.file + ": " +
str(spentIsTime))
self.output = +out
top.addToExtra("SPENT-TIME-IS", float(spentIsTime))
return top, out
def run(self, trainSeti, testSeti, name, fout, vSets, vSetType,
fixedTrainSize, log, ignoreOK, threshold, thresholds, rejectedFits,
rejectedPerfs, rejectedTestPerfs, clfName):
mad = 0.0
if self.isCount:
keySet = list(
DPLIB.getMeasuresCount([0, 1, 2, 3], [0, 1, 2, 3]).keys())
mad = DPLIB.SetBugCountForMut(trainSeti)
else:
keySet = list(
DPLIB.getExtMeasures({
"tp": 1,
"tn": 2,
"fp": 3,
"fn": 4
}).keys())
startTime = Common.getCurrentTimeMil()
tempTime = 0
spentISTime = 0
#For Binary Prediction, isCount = False
auc = 0
preds = []
pop = []
trainSet = np.copy(trainSeti)
testSet = np.copy(testSeti)
pop.clear()
tstSize = len(testSet)
partSize = int(tstSize / self.numParts)
preds.clear()
diffs = []
auc = 0.0
#For isCount = True
actuals = []
prrs = []
if (log):
self.prnt("#GIS-OPTIONS;;For=" + name + "@" + ":iters=" +
str(self.iters) + "-POPSIZE=" + str(self.popSize) +
"-NumParts=" + str(self.numParts) + "-NumGens=" +
str(self.numGens) + "-sizeTop=" + str(self.sizeTopP) +
"-Learner=" + clfName + "\n")
isOK = True
np.random.shuffle(testSet)
self.FinalLearners = []
self.FinalDatasets = []
for p in range(self.numParts):
diffp = []
self.prnt("\n" + str(p) + ": ")
tempTime = Common.getCurrentTimeMil()
pop.clear()
start = p * partSize
end = (p + 1) * partSize
if (end > tstSize):
end = tstSize
if (p == self.numParts - 1):
end = tstSize
testPart = testSet[start:end, :]
spentISTime += Common.getCurrentTimeMil() - tempTime
uinds = set()
if (vSets == None or len(vSets) == 0):
if (vSets == None):
vSets = []
vSet = None
retVal = ""
if (vSetType == 'Train Set'):
vSet = trainSeti
if (log):
retVal = DPLIB.getStats(vSet, True, True, True)
self.prnt("#VSETINFO;;prt=" + str(p) + ";;For=" +
name + "@" + ":" + retVal + "\n")
retVal = None
elif (vSetType == 'NN-Filter'):
tempTime = Common.getCurrentTimeMil()
vSet = DPLIB.NNFilter(trainSet, testPart, 1)
spentISTime += Common.getCurrentTimeMil() - tempTime
if (log):
retVal = DPLIB.getStats(vSet, True, True, True)
self.prnt("#VSETINFO;;prt=" + str(p) + ";;For=" +
name + "@" + ":" + retVal + "\n")
retVal = None
#If random, but not fed into the func, generate one randomly, with size of testPart
elif (vSetType == 'Multiple Random'
or vSetType == 'Single Random'):
size = len(testPart)
vSet = []
j = 0
while (j < size):
index = np.random.randint(trainSet.numInstances())
if (not index in uinds):
uinds.add(index)
else:
continue
vSets.append(trainSet[index])
j += 1
if (log):
retVal = DPLIB.getStats(vSet, true, true, True)
self.prnt("#VSETINFO;;prt=" + str(p) + ";;For=" +
name + "@" + ":" + retVal + "\n")
retVal = None
vSet = np.array(vSet)
elif (vSetType == '!!TEST!!'):
#Upper Bound. Should not be used.
self.prnt("Should not be used.")
vSet = testSeti
if (log):
retVal = DPLIB.getStats(vSet, True, True, True)
self.prnt("#VSETINFO;;prt=" + str(p) + ";;For=" +
name + "@" + ":" + retVal + "\n")
retVal = None
elif vSetType == 'KS2':
vSet = None
vSets.append(vSet)
else:
retVal = ""
for vSet in vSets:
if (log):
retVal = DPLIB.getStats(vSet, True, True, True)
self.prnt("#VSETINFO;;prt=" + str(p) + ";;For=" +
name + "@" + ":" + retVal + "\n")
retVal = None
for i in range(self.popSize):
tempTime = Common.getCurrentTimeMil()
uinds.clear()
size = 0
if (fixedTrainSize):
size = self.chrmSize
else:
size = np.random.randint(self.chrmSize) + 10
while True:
trSet = []
j = 0
while (j < size):
index = np.random.randint(len(trainSet))
trSet.append(trainSet[index])
if (not index in uinds):
uinds.add(index)
j += 1
spentISTime += Common.getCurrentTimeMil() - tempTime
trSet = np.array(trSet)
if len(set(list(trSet[:, -1]))) >= 2:
break
tempTime = Common.getCurrentTimeMil()
pv, p_vals = DPLIB.checkSimilarity(trSet[:, :-1],
testPart[:, :-1])
if self.isCount:
h = CHRM_GIS_Count(trSet, None, extraAsFitness='p-val')
h.addToExtra('p-val', sum(p_vals))
pop.append(h)
else:
h = CHRM_GIS(trSet, None, None, extraAsFitness='p-val')
h.addToExtra('p-val', sum(p_vals))
pop.append(h)
spentISTime += Common.getCurrentTimeMil() - tempTime
tempTime = Common.getCurrentTimeMil()
pop = DPLIB.MySort(pop)
spentISTime += Common.getCurrentTimeMil() - tempTime
cnt = 0
g = 0
for g in range(self.numGens):
self.prnt(str(g) + " ")
if (log):
pass
#retVal = ""
#for i in range(len(pop)):
# chrm = pop[i]
# retVal = DPLIB.getStats(chrm.ds, False, False, False);
# self.prnt("#POPITNFO;;gn="+str(g)+";;prt="+str(p)+";;For="+name+"@"+":"+retVal+"\n");
# self.prnt("#POPITVALS;;gn="+str(g)+";;prt="+str(p)+";;For="+name+"@"+":"+"rpaf="+str(chrm.fitness).replace(", ", ",")
# +";;conf="+str(chrm.conf).replace(", ", ",")+";;fit="+str(chrm.getFitness())+";;TConf2="+str(chrm.testConf).replace(", ", ",")+";;TRpaf2="+str(chrm.testFitness).replace(", ", ",")+"\n");
# retVal = None;
tempTime = Common.getCurrentTimeMil()
newPop = []
for i in range(self.sizeTopP):
newPop.append(pop[i])
i = 0
for i in range(0, len(pop) - self.sizeTopP, 2):
idx1 = 0
idx2 = 0
while (idx1 == idx2):
if (cnt >= 3):
idx1 = np.random.randint(len(pop))
idx2 = np.random.randint(len(pop))
else:
idx1 = GA.tornament(pop)
idx2 = GA.tornament(pop)
cnt += 1
cnt = 0
ds1 = pop[idx1].ds
ds2 = pop[idx2].ds
while True:
ds1, ds2 = GA.crossOver(ds1,
ds2,
fixedTrainSize,
isCount=self.isCount)
if len(set(list(ds1[:, -1]))) >= 2 and len(
set(list(ds2[:, -1]))) >= 2:
break
self.prnt('repeat cross')
while True:
ds1 = GA.Mutate(ds1, isCount=self.isCount, mad=mad)
if len(set(list(ds1[:, -1]))) >= 2:
break
self.prnt(
'repeat mut ds1, because all elements are of type one class'
)
while True:
ds2 = GA.Mutate(ds2, isCount=self.isCount, mad=mad)
if len(set(list(ds2[:, -1]))) >= 2:
break
self.prnt(
'repeat mut ds1, because all elements are of type one class'
)
if self.isCount:
newPop.append(
CHRM_GIS_Count(ds1, None, extraAsFitness='p-val'))
newPop.append(
CHRM_GIS_Count(ds2, None, extraAsFitness='p-val'))
else:
newPop.append(
CHRM_GIS(ds1, None, extraAsFitness='p-val'))
newPop.append(
CHRM_GIS(ds2, None, extraAsFitness='p-val'))
spentISTime += Common.getCurrentTimeMil() - tempTime
for i in range(len(newPop)):
tempTime = Common.getCurrentTimeMil()
pv, p_vals = DPLIB.checkSimilarity(newPop[i].ds[:, :-1],
testPart[:, :-1])
newPop[i].addToExtra('p-val', sum(p_vals))
spentISTime += Common.getCurrentTimeMil() - tempTime
tempTime = Common.getCurrentTimeMil()
newPop = DPLIB.MySort(newPop)
exit = False
countComp = 0
newPop, rdel = DPLIB.CombinePops(pop, newPop)
if (log):
pass
#retVal = ""
#for i in range(len(rdel)):
# chrm = rdel[i];
# retVal = DPLIB.getStats(chrm.ds, False, False, False);
# self.prnt("#POPDELITNFO;;gn="+str(g)+";;prt="+str(p)+";;For="+name+"@"+":"+retVal+";;rpaf="+str(chrm.fitness).replace(", ", ",")
# +";;conf="+str(chrm.conf).replace(", ", ",")+";;fit="+str(chrm.getFitness())+";;TConf2="+str(chrm.testConf).replace(", ", ",")+";;TRpaf2="+str(chrm.testFitness).replace(", ", ",")
# +"\n");
# retVal = None;
rdel = None
diff = abs(
GA.GetMeanFittness(pop, countComp) -
GA.GetMeanFittness(newPop, countComp))
if (diff < 0.000001):
exit = True
diffp.append(diff)
pop = newPop
if (pop[0].getFitness() > 0.0) and (exit):
break
exit = False
spentISTime += Common.getCurrentTimeMil() - tempTime
w = []
if (self.count == 0):
self.count = len(pop)
for i in range(self.count):
l = GLOB(clfName).getClassifier()
tds = pop[i].ds
self.FinalLearners.append(l)
self.FinalDatasets.append(tds)
testPartI = testPart
l.buildClassifier(tds)
if self.isCount:
actual = DPLIB.getActuals(testPartI)
prr = l.evaluateModel(testPartI)
#vals = DPLIB.getMeasuresCount(actual,prr)
actall = None
predall = None
if (len(actuals) == self.count):
actuals[i] = actuals[i] + actual
prrs[i] = prrs[i] + prr
else:
actuals.append(actual)
prrs.append(prr)
else:
vec = l.evaluateModel(testPartI)
if (len(preds) == self.count):
preds[i] += list(vec)
else:
preds.append(list(vec))
if (log):
pass
#retVal = DPLIB.getStats(tds, True, True, True);
#self.prnt("#TRPRTNFO;;prt="+str(p)+";;For="+name+"@"+":"+retVal+"\n");
#retVal = DPLIB.getStats(testPart,true,true, True);
#self.prnt("#TSTPRTNFO;;prt="+str(p)+";;For="+name+"@"+":"+retVal+"\n");
#vals = DPLIB.getConfMatrix(testPart[:,-1],vec)
#self.prnt("#TSTPRTVALS;;prt="+str(p)+";;For="+name+"@"+":"+
# "rpaf="+str(DPLIB.getMeasures(vals)).replace(", ", ",")
# +";;conf="+str(vals).replace(", ", ",")+"\n");
#retVal = None;
w.append(pop[i].getFitness())
isOK = True
if not isOK:
pass
else:
thresholds.append(pop[0].getFitness())
self.prnt()
self.prnt("Best Top Fitness:" + str(pop[0].fitness))
self.prnt("Best Fitness (mean):", pop[0].getMeanFitness())
if self.isCount:
vals = DPLIB.getMeasuresCountSet(actuals, prrs)
else:
vals1 = DPLIB.getConfMatrixSet(testSet[:, -1], preds)
vals = DPLIB.getMeasures(vals1)
if (isOK):
if not self.isCount:
if (len(preds) == 1):
auc = DPLIB.getAUC(testSet[:, -1], preds[0])
else:
auc = DPLIB.getAUCSet(testSet[:, -1], preds)
vals['auc'] = auc
self.prnt()
self.prnt("#CONF-TEST:" + name + ":" + self.file + ": " +
str(vals1))
self.prnt()
self.prnt(name + ":" + self.file + ": " + str(vals))
self.prnt()
else:
self.prnt()
self.prnt(name + ":" + self.file + ": " + str(vals))
self.prnt()
else:
bestI = pop[0]
rejectedFits.append(bestI.getFitness())
rejVals = copy.deepcopy(bestI.fitness)
rejectedPerfs.append(rejVals)
testRejVals = copy.deepcopy(vals)
rejectedTestPerfs.eppend(testRejVals)
self.prnt("#NOTOKPREDS----" + name + ":" + self.file + ": " +
str(vals))
if not self.isCount:
self.prnt()
self.prnt("#NOTOKPREDS----" + "#CONF-TEST:" + name + ":" +
self.file + ": " + str(vals1))
time = Common.getCurrentTimeMil() - startTime
self.prnt("#TIME-FOR:" + name + ":" + self.file + ": " + str(time))
self.prnt("#TIME-FOR-IS:" + name + ":" + self.file + ": " +
str(spentISTime))
return isOK
def run(self):
lrnrnames = self.lrnrs
try:
rnd = random.Random(Common.getCurrentTimeMil())
if self.expType == 'GIS':
if self.isKS:
self.gis = GISKS2(self.pars,self.file)
else:
self.gis = GIS(self.pars)
elif self.expType == 'LSH':
lsh = CPDP_LSH_Binary(self.pars, self.file)
trainSetAll = DPLIB.LoadCSV(self.train, self.dp, self.features, convertToBinary = not self.isCount);
testSetAll = DPLIB.LoadCSV(self.test, self.dp, self.features, convertToBinary = not self.isCount);
ft = 'A'
indi = None
if not self.isCount:
if self.pars['features'] == 'Iterative InfoGain Subsetting':
ft = 'IG'
indi = DPLIB.fSelectInfoGain(trainSetAll);
if self.pars['features'] == 'All':
print ('All')
if self.pars['features'] == 'PCA':
ft = 'PCA'
print ('PCA')
trainSetAll, testSetAll = DPLIB.applyPCA(trainSetAll, testSetAll, 0.95)
for lk in range(len(lrnrnames)):
lrnr = "-" + lrnrnames[lk];
clfName = lrnrnames[lk];
vSets = None
if not self.isCount:
if self.pars['features'] == 'Iterative InfoGain Subsetting':
indis2 = DPLIB.iterativeInfoGainSubsetting(trainSetAll, indi, clfName);
trainSetAll = DPLIB.fSelectSet(trainSetAll, indis2);
testSetAll = DPLIB.fSelectSet(testSetAll, indis2);
if self.pars['vSetType'] in ['Single Random','Multiple Random']:
vSets = DatasetUtils.getRandomDatasets()
c = 0
while (c < self.iters):
print("Start:" + self.file + ": " + str(c));
print("====================================================");
#fout.write("#ITERINFO:For File=" +self.file + "-Iter:" + str(c) + "\n");
stages = None
buckets = None
sbtx = ""
if self.expType == 'GIS':
self.doGIS(trainSetAll, testSetAll, "FIXED-VMUL-GEN-"+ft, lrnr, fout, vSets, False, clfName, gis=gis);
gis.prnt('---------------------------------------\n')
elif self.expType == 'LSH':
lsh.CreateBucketsTune(trainSetAll, testSetAll, vSets, name= "LSHTune-ALL-TOP-SUPER" + sbtx + lrnr, testCut= self.pars['tunecut'], iternum=c, save=False, superbit=self.pars['lshType'] =='SuperBit', clfName=clfName,tunelrn = self.pars['tunelrnr']);
lsh.prnt('---------------------------------------\n')
c+=1
#fout.write("===================================================================\n");
#fout.close();
print("File Processing Ended:" +self.file);
except Exception as e:
try:
print (str(e))
print(traceback.format_exc())
except Exception as ex2:
print("X2", str(ex2));
print(traceback.format_exc())
if self.expType == 'GIS':
return gis
elif self.expType == 'LSH':
return lsh
def WCFolds(testSet, folds, file, fout, name, clfName):
auc = 0
preds = []
actuals = []
vals = None
tssCopy = testSet[:, :]
rnd = random.Random(Common.getCurrentTimeMil())
np.random.shuffle(tssCopy)
skf = StratifiedKFold(n_splits=folds)
X = tssCopy[:, :-1]
y = tssCopy[:, -1]
for train_index, test_index in skf.split(X, y):
cvtrain, cvtest = X[train_index], X[test_index]
cvtrainY, cvtestY = y[train_index], y[test_index]
cvtrain = np.append(cvtrain,
cvtrainY.reshape((len(cvtrainY), 1)),
axis=1)
cvtest = np.append(cvtest,
cvtestY.reshape((len(cvtestY), 1)),
axis=1)
if (name.lower().find("infogain") >= 0):
pass
#int indi[] = DPLIB.fSelectInfoGain(cvtrain);
#if (DPLIB.useIterativeInfoGainSubsetting)
#{
# indi = DPLIB.iterativeInfoGainSubsetting(cvtrain, indi, clfName);
#}
#else
# indi = DPLIB.getTopX(indi);
#cvtrain = DPLIB.fSelectSet(cvtrain, indi);
#cvtest = DPLIB.fSelectSet(cvtest, indi);
m = GLOB(clfName).getClassifier()
m.buildClassifier(cvtrain)
vec = m.evaluateModel(cvtest)
preds.append(vec)
actuals.append(cvtestY)
if vals == None:
vals = DPLIB.getConfMatrix(cvtestY, vec)
else:
v2 = DPLIB.getConfMatrix(cvtestY, vec)
for key in vals.keys():
vals[key] += v2[key]
auc = DPLIB.getAUCCV(actuals, preds)
vals1 = DPLIB.getMeasures(vals)
print(name + ":" + file + ": " + str(vals1) + " AUC = " + str(auc))
fout.write("\n" + name + ":" + file + ": " + " AUC = " + str(auc) +
";" + "Vals=" + str(vals1))
def NNFilter(trainSeti, testSet, file, fout, name, vecin, count, clfName,
tunelrn, vSets, testCut):
startTime = Common.getCurrentTimeMil()
spentISTime = 0
tempTime = 0
bestFit = 0.0
bestCount = 0
btrainSet = None
cfbf = DPLIB.DefaultCF
if (count == 0):
for i in range(1, 11):
tempTime = Common.getCurrentTimeMil()
trainSet = DPLIB.NNFilter(trainSeti, testSet, i)
spentISTime += Common.getCurrentTimeMil() - tempTime
l = GLOB(clfName, tunelrn).getClassifier()
if (tunelrn):
l = l.getTunedCLF(trainSet, vSets, fout, name, file)
l.buildClassifier(trainSet)
avgFit = 0.0
j = 0
for j in range(len(vSets)):
vec = l.evaluateModel(vSets[j])
tvals = DPLIB.getConfMatrix(vSets[j][:, -1], vec)
measures = DPLIB.getExtMeasures(tvals)
fit = measures["F"] * measures["GMean1"]
avgFit += fit
avgFit /= len(vSets)
if (avgFit > bestFit):
bestFit = avgFit
bestCount = i
btrainSet = trainSet[:, :]
if (testCut):
cf = 0
j = 0
trainSet = btrainSet
l = GLOB(clfName, tunelrn).getClassifier()
if (tunelrn):
l = l.getTunedCLF(trainSet, vSets, fout, name, file)
l.buildClassifier(trainSet)
avgFit = 0.0
for j in range(len(vSets)):
vec = l.evaluateModel(vSets[j])
vCF = 0.1
bestCF = 0
bestCFVal = -1
bestVals = None
while True:
tvals = DPLIB.getConfMatrix(vSets[j][:, -1], vec, vCF)
measures = DPLIB.getExtMeasures(tvals)
fit = measures["F"] * measures["GMean1"]
if (fit > bestCFVal or bestVals == None):
bestCFVal = fit
bestCF = vCF
bestVals = tvals
vCF += 0.1
if vCF >= 1:
break
cf += bestCF
cf /= vSets.size()
cfbf = cf
trainSet = None
if (count == 0):
trainSet = btrainSet
else:
tempTime = Common.getCurrentTimeMil()
trainSet = DPLIB.NNFilter(trainSeti, testSet, count)
spentISTime = Common.getCurrentTimeMil() - tempTime
bestCount = count
l = GLOB(clfName, tunelrn).getClassifier()
if (tunelrn):
l = l.getTunedCLF(trainSet, vSets, fout, name, file)
print("#TUNE-LRN-PARAMS-" + name + ":" + file + ": " +
str(l.selectedParams))
fout.write("#TUNE-LRN-PARAMS-" + name + ":" + file + ": ")
fout.write(str(l.selectedParams))
fout.write("\n")
sCheck = l.getCLFOptions()
print("#SETSET-LRN-PARAMS-" + name + ":" + file + ": " +
str(sCheck))
fout.write("#SETSET-LRN-PARAMS-" + name + ":" + file + ": ")
fout.write(str(sCheck))
fout.write("\n")
l.buildClassifier(trainSet)
vec = l.evaluateModel(testSet)
vecin = vec
tvals = DPLIB.getConfMatrix(testSet[:, -1], vecin, cfbf)
if (count == 0):
print("#BESTCOUNT-" + name + ":" + file + ": " + str(bestCount))
fout.write("#BESTCOUNT-" + name + ":" + file + ": ")
fout.write(str(bestCount))
fout.write("\n")
print("#BESTFIT-" + name + ":" + file + ": " + str(bestFit))
fout.write("#BESTFIT-" + name + ":" + file + ": ")
fout.write(str(bestFit))
fout.write("\n")
print("#CONF-TEST-" + name + ":" + file + ": " + str(tvals))
fout.write("#CONF-TEST-" + name + ":" + file + ": ")
fout.write(str(tvals))
fout.write("\n")
if (testCut):
print("#NN-BEST-CF-VALUE:" + name + ":" + file + ": " + str(cfbf))
fout.write("#NN-BEST-CF-VALUE:" + name + ":" + file + ": ")
fout.write(str(cfbf))
fout.write("\n")
vals = DPLIB.getMeasures(tvals)
auc = DPLIB.getAUC(testSet[:, -1], vecin)
print(name + ":" + file + ": " + str(vals) + " AUC = " + str(auc))
fout.write(name + ":" + file + ": ")
fout.write(str(vals))
fout.write(" AUC = ")
fout.write(str(auc))
fout.write("\n")
time = Common.getCurrentTimeMil() - startTime
print("#TIME-FOR:" + name + ":" + file + ": " + str(time))
fout.write("#TIME-FOR:" + name + ":" + file + ": " + str(time) + "\n")
print("#TIME-FOR-IS:" + name + ":" + file + ": " + str(spentISTime))
fout.write("#TIME-FOR-IS:" + name + ":" + file + ": " +
str(spentISTime) + "\n")
return vecin
for key in FutureBugs.keys():
bds = sorted([bugDates[b] for b in FutureBugs[key]])
if len(bds)>1:
timespans.append((datetime.datetime.fromtimestamp(bds[-1])-datetime.datetime.fromtimestamp(bds[0])).total_seconds()/86400)
timespansNoz.append(timespans[-1])
ids.append(key)
else:
timespans.append(0)
print ('2 Timespan of Bugs: Mean,STD,Median ',np.mean(timespans),np.std(timespans),np.median(timespans))
print ('2 Timespan of Bugs (for multibugs only): Mean,STD ,Median',np.mean(timespansNoz),np.std(timespansNoz),np.median(timespansNoz))
print ('2 Count Multi Bug:', len(timespansNoz))
print ('2 Count One or Multi Bug:', len(timespans))
mad = DPLIB.MAD(timespansNoz)
umad = mad+np.median(timespansNoz)
lmad = np.median(timespansNoz)-mad
if len(timespansNoz)>0:
print ('2 MAD, Median , UMAD , Percent>UMAD, Median Filtered:',
mad,np.median(timespansNoz),umad,'%.2f' %(100*len([t for t in timespansNoz if t>umad])/len(timespansNoz)), np.median([t for t in timespansNoz if t>umad]))
else:
print ('2 MAD, Median , UMAD , Percent>UMAD, Median Filtered:',
mad,np.median(timespansNoz),umad,'PERCENT UNDEF', np.median([t for t in timespansNoz if t>umad]))
#numfiles= [(key,len(logsd[int(key)][logcolnames.index('files')].split('---')[:-1])) for index,key in enumerate(ids) if timespansNoz[index]>umad]
#print (numfiles)
if len(timespansNoz)>0:
try:
pass
#plt.figure(figsize=(10,10))