def RunWithPars(pars, uid):
startTime = Common.getCurrentTimeMil()
reposFol = 'SavePath/Repos/'
if not os.path.exists(config.basedir + '/' + reposFol):
os.makedirs(config.basedir + '/' + reposFol)
fname = reposFol + Common.gen_rnd_filename()
os.makedirs(config.basedir + '/' + fname)
##ADD Field
e = Repo()
e.cloneFinishDate = "--RUNNING--"
e.cloneStartDate = str(startTime)
e.repoInfo = ''
e.isPrivate = int(pars['isPrivate'])
e.path = fname
e.repoName = pars['repoName']
e.url = pars['url']
e.userId = uid
db.session.add(e)
db.session.commit()
try:
porcelain.clone(pars['url'], config.basedir + '/' + fname)
endTime = Common.getCurrentTimeMil()
e.cloneFinishDate = str(endTime)
db.session.commit()
except Exception as ex:
print(ex)
e.delete()
db.session.commit()
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 RunWithPars(pars, uid):
"""
docstring here
:param pars:
:param uid:
"""
startTime = Common.getCurrentTimeMil()
modelsFol = 'SavePath/models/'
if not os.path.exists(config.basedir + '/' + modelsFol):
os.makedirs(config.basedir + '/' + modelsFol)
fname = modelsFol + Common.gen_rnd_filename() + '.pkl'
#ADD Field
pars['pid'] = os.getpid()
e = Experiment()
e.endDateTime = "--RUNNING--"
e.startDateTime = str(startTime)
e.pars = json.dumps(pars)
e.results = ""
e.type = pars['type']
e.expModelsFileName = ''
e.userId = uid
db.session.add(e)
db.session.commit()
ret, expModels = BCC.BCC.RunTests(uid, pars['type'], pars, config.basedir)
pickle.dump(expModels, open(config.basedir + '/' + fname, 'wb'))
if ret is None:
e.delete()
db.session.commit()
else:
endTime = Common.getCurrentTimeMil()
e.endDateTime = str(endTime)
e.startDateTime = str(startTime)
e.pars = json.dumps(pars)
e.expModelsFileName = fname
e.results = json.dumps(ret)
db.session.commit()
for method in ret.keys():
for ds in ret[method].keys():
perfs = ret[method][ds]
ep = ExperimentPrediction()
ep.data = None
ep.datasetName = ds
ep.predResult = json.dumps(perfs)
ep.expId = e.id
ep.predDateTime = e.endDateTime
ep.predType = 0 ###Test with known labels
db.session.add(ep)
db.session.commit()
def CreateBucketsTune(self, trainSet, testSet, vSets, name, testCut,
iternum, save, superbit, clfName, tunelrn):
startTime = Common.getCurrentTimeMil()
best = None
bestStages = 0
bestBuckets = 0
bestOut = None
spentTimeIS = 0
tempTime = 0
rand = random.Random(Common.getCurrentTimeMil())
for i in range(self.numOptions):
while True:
stages = rand.randint(0, self.maxStages - 1) + self.minStages
buckets = rand.randint(0,
self.maxBuckets - 1) + self.minBuckets
break
#if buckets>stages:
# break
chrm = None
while (True):
chrm, out = self.CreateBuckets(trainSet, testSet, vSets, name,
testCut, iternum, save,
superbit, stages, buckets,
False, clfName, tunelrn)
if chrm != None:
break
spentTimeIS += float(chrm.extra["SPENT-TIME-IS"])
if (best == None):
best = chrm
bestBuckets = buckets
bestStages = stages
bestOut = out
else:
if (chrm.getFitness() > best.getFitness()):
best = chrm
bestBuckets = buckets
bestStages = stages
bestOut = out
self.output += out
time = Common.getCurrentTimeMil() - startTime
self.prnt("#TIME-FOR:" + name + ":" + self.file + ": " + str(time) +
"\n")
self.prnt("#TIME-FOR-IS:" + name + ":" + self.file + ": " +
str(spentTimeIS) + "\n")
return best, out
def upload():
"""CKEditor file upload"""
error = ''
url = ''
#callback = request.args.get("CKEditorFuncNum")
if request.method == 'POST' and 'upload' in request.files:
fileobj = request.files['upload']
fname, fext = os.path.splitext(fileobj.filename)
if fext.lower() not in ['.jpg', '.png']:
return upload_fail('Only .jpg and .png extensions are allowed')
rnd_name = '%s%s' % (Common.gen_rnd_filename(), fext)
filepath = config.uploadsPath + '/' + rnd_name
dirname = config.uploadsPath
if not os.path.exists(dirname):
try:
os.makedirs(dirname)
except:
return upload_fail('ERROR_CREATE_DIR')
elif not os.access(dirname, os.W_OK):
return upload_fail('ERROR_DIR_NOT_WRITEABLE')
if not error:
#with open(filepath, 'w+') as destination:
# for chunk in fileobj.chunks():
# destination.write(chunk)
fileobj.save(filepath)
url = url_for('static', filename='upload/' + rnd_name)
return upload_success(url=url)
else:
return upload_fail(error)
else:
return upload_fail('post error')
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 submit_comment_reply():
message = None
if request.method == 'POST':
isAnonym = True
data = json.loads(request.data)
commentText = data['replyText']
inReplyTo = int(data['id'])
commentorId = 0
postId = int(data['postId'])
if Shared.isLoggedIn():
#return redirect(url_for('index'))
user = Shared.getLoggedInUser()
isAnonym = False
name = user.name
email = user.email
commentorId = user.id
else:
name = 'Anonym'
email = ''
commentorId = 0
pc = PostComment()
pc.commentorEmail = email
pc.commentorName = name
pc.commentText = commentText
pc.commentorId = commentorId
pc.inReplyTo = inReplyTo
pc.postId = postId
pc.commentDate = Common.getCurrentTimeMil()
db.session.add(pc)
db.session.commit()
resp = make_response(
render_template('blog/singleComment.html', comment=pc))
return json.dumps({
'html': resp.data.decode("utf-8"),
"id": str(inReplyTo)
})
#else:
# return render_template('blog/singleComment.html', comment = pc)
return ""
def create_post():
if not Shared.isLoggedIn():
return redirect(url_for('index'))
user = Shared.getLoggedInUser()
if user.utype != 1:
print('Not authorised to access')
return redirect(url_for('index'))
message = None
if request.method == 'POST':
title = request.form.get('title')
body = request.form.get('ckeditor')
bp = BlogPost()
bp.postBody = body
bp.postTitle = title
bp.postDate = Common.getCurrentTimeMil()
bp.postCreatorId = user.id
bp.postPerms = 0
bp.viewCount = 0
db.session.add(bp)
db.session.commit()
message = 'Post Saved Successfully'
return redirect(url_for('BPBlog.posts'))
return render_template('blog/create_post.html', message=message)
def viewpost(id):
if request.method == 'POST':
if 'formAddComment' in request.form:
name, email = None, None
commentorId = 0
if not Shared.isLoggedIn():
name = request.form['commentorName']
email = request.form['commentorEmail']
else:
user = Shared.getLoggedInUser()
name = user.name
email = user.email
commentorId = user.id
commentText = request.form['commentText']
pc = PostComment()
pc.commentorEmail = email
pc.commentorName = name
pc.commentText = commentText
pc.commentorId = commentorId
pc.inReplyTo = 0
pc.postId = id
pc.commentDate = Common.getCurrentTimeMil()
db.session.add(pc)
db.session.commit()
post = BlogPost.query.filter_by(id=id).first()
comments = PostComment.query.filter_by(postId=id)
#if comments.count()<=0:
# comments = None
commentsDict = None
commentReplies = None
if comments:
commentsDict = {comment.id: comment for comment in comments}
commentReplies = {}
#ht = ""
for comment in comments:
commentReplies[comment.id] = []
for comment in comments:
if comment.inReplyTo == 0:
continue
commentReplies[comment.inReplyTo].append(comment)
#if comment.inReplyTo == 0:
# parents.append(comment)
# p = 0
# ht+='<div class="row">'+ comment.commentText +'<a href="reply('+str(comment.id)+')" class="replyfont"> Reply </a>'+'</div>'
# ht = checkChilds(comment,ht,comments, p)
#else:
# depths[comment.id] = depths[comment.inReplyTo]+1
return render_template(
'blog/viewpost.html',
post=post,
comments=comments,
commentsDict=commentsDict,
commentReplies=commentReplies) # comments = comments, ht = ht)
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 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
def test001(self):
res = Common.execute_command("tns --version")
print res
assert 1 == 1
def tearDown(self):
print "End of test " + self._testMethodName
name = cwd + "\\" + self._testMethodName + ".png"
if sys.exc_info() == (None, None, None):
Common.capture_screen(name)
os.remove(name)
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 start_test(self):
#set up
TcStatus=0
msg='测试开始...'
s_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
log.WritetoLog(self.logfile,msg)
#test
try:
#set up
self.driver = webdriver.Remote('http://localhost:4723/wd/hub', self.desired_caps)
time.sleep(8)
#test
#registry
'''
registry_result = account.create_user(self.sn)
self.username = registry_result[0]
self.password = registry_result[1]
'''
self.username = '******'
self.password = '******'
#Login
self.login_result = al.login_to_page(self.driver,self.username,self.password,self.sn)
log.WritetoLog(self.logfile,'Login_result:'+str(self.login_result))
assert self.login_result == 1
time.sleep(5)
#Get gateway version
version_content = al.get_version(self.driver)
log.WritetoLog(self.logfile,'Get_version_result:'+str(version_content))
if self.gateway_version == version_content:
self.version_check_result = 1
assert self.version_check_result == 1
#add area and devices
area = 'Test'
device_list = [[self.shuangkai_mac,'1','2'],[self.sankai_mac,'2','1']]
add_device_result = al.add_area_devices(self.driver,area,device_list)
assert add_device_result == 1
'''
#wait for device
msg = 'Please wait 2 minutes'
log.WritetoLog(self.logfile,msg)
al.wait_for_access(self.driver)
#time.sleep(120)
'''
'''
#status check
light_control_result = al.get_all_opendevice_in_light(self.driver)
if len(light_control_result) == 1 and light_control_result[0] == self.light_result:
self.status_check_result = 1
else:
self.status_check_result = 0
log.WritetoLog(self.logfile,'status_check_result:'+str(self.status_check_result))
assert self.status_check_result == 1
#control test
control_test_result = al.control_device_in_device(self.driver)
log.WritetoLog(self.logfile,'Control_test_result:'+str(control_test_result))
self.control_test_result = control_test_result
assert self.control_test_result == 1
'''
TcStatus=1
except Exception as e:
msg= 'Error occurred:'+str(e)
log.WritetoLog(self.logfile,msg)
self.driver.quit()
self.driver = webdriver.Remote('http://localhost:4723/wd/hub', self.desired_caps)
time.sleep(5)
self.login_result = al.login_to_page(self.driver,self.username,self.password,self.sn)
finally:
#teardown
try:
clear_env_result = al.clear_env(self.driver)
log.WritetoLog(self.logfile,'环境恢复成功！')
except Exception as e:
print e
log.WritetoLog(self.logfile,'环境恢复失败！')
finally:
self.driver.quit()
msg='测试结果:'+str(TcStatus) #Set Result
log.WritetoLog(self.logfile,msg)
msg='测试结束...'
log.WritetoLog(self.logfile,msg)
e_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
#generate report
Common.generate_report(self.report,self.sn,self.login_result,self.version_check_result,self.status_check_result,self.control_test_result,self.env_clear_result,TcStatus,s_time,e_time)
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