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 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 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 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 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