def test_CreateDefaultClassifierUsingPreTrainedRegressionClassifiers(self):
""" Test the creation of default Consensus Classifier using pre-trained classification classifiers. """
# Arrange
learners = [
AZorngCvSVM.CvSVMLearner(),
AZorngCvANN.CvANNLearner(),
AZorngRF.RFLearner()
]
classifiers = [l(self.getRegressionTrainingData()) for l in learners]
# Act
classifier = AZorngConsensus.ConsensusClassifier(
classifiers=classifiers)
# Assert
self.assertNotEqual(classifier, None)
self.assertEqual(len(classifier.classifiers), len(learners))
self.assertNotEqual(classifier.basicStat, None)
self.assertNotEqual(classifier.classVar, None)
self.assertNotEqual(classifier.domain, None)
self.assertEqual(classifier.expression, None)
self.assertNotEqual(classifier.imputeData, None)
#self.assertEqual(classifier.NTrainEx, len(trainingData))
self.assertEqual(classifier.name, "Consensus classifier")
self.assertNotEqual(classifier.varNames, None)
self.assertEqual(classifier.verbose, 0)
self.assertEqual(classifier.weights, None)
def test_CreateDefaultClassifierUsingPreTrainedRegressionClassifiers(self):
""" Test the creation of custom Consensus Classifier using pre-trained regression classifiers. """
# Arrange
learners = {
'a': AZorngCvSVM.CvSVMLearner(),
'b': AZorngCvANN.CvANNLearner(),
'c': AZorngRF.RFLearner()
}
classifiers = {}
for k, v in learners.items():
classifiers[k] = v(self.getRegressionTrainingData())
expression = "a + b + c"
# Act
classifier = AZorngConsensus.ConsensusClassifier(
classifiers=classifiers, expression=expression)
# Assert
self.assertNotEqual(classifier, None)
self.assertEqual(len(classifier.classifiers), len(learners))
self.assertNotEqual(classifier.basicStat, None)
self.assertNotEqual(classifier.classVar, None)
self.assertNotEqual(classifier.domain, None)
self.assertEqual(classifier.expression, expression)
self.assertNotEqual(classifier.imputeData, None)
#self.assertEqual(classifier.NTrainEx, len(trainingData))
self.assertEqual(classifier.name, "Consensus classifier")
self.assertNotEqual(classifier.varNames, None)
self.assertEqual(classifier.verbose, 0)
self.assertEqual(classifier.weights, None)
def getAcc(self, callBack=None, callBackWithFoldModel=None):
""" For regression problems, it returns the RMSE and the Q2
For Classification problems, it returns CA and the ConfMat
The return is made in a Dict: {"RMSE":0.2,"Q2":0.1,"CA":0.98,"CM":[[TP, FP],[FN,TN]]}
For the EvalResults not supported for a specific learner/datase, the respective result will be None
if the learner is a dict {"LearnerName":learner, ...} the results will be a dict with results for all Learners and for a consensus
made out of those that were stable
It some error occurred, the respective values in the Dict will be None
"""
self.__log("Starting Calculating MLStatistics")
statistics = {}
if not self.__areInputsOK():
return None
# Set the response type
self.responseType = self.data.domain.classVar.varType == orange.VarTypes.Discrete and "Classification" or "Regression"
self.__log(" " + str(self.responseType))
#Create the Train and test sets
if self.usePreDefFolds:
DataIdxs = self.preDefIndices
else:
DataIdxs = self.sampler(self.data, self.nExtFolds)
foldsN = [f for f in dict.fromkeys(DataIdxs) if f != 0
] #Folds used only from 1 on ... 0 are for fixed train Bias
nFolds = len(foldsN)
#Fix the Indexes based on DataIdxs
# (0s) represents the train set ( >= 1s) represents the test set folds
if self.useVarCtrlCV:
nShifted = [0] * nFolds
for idx, isTest in enumerate(
self.preDefIndices
): # self.preDefIndices == 0 are to be used in TrainBias
if not isTest:
if DataIdxs[idx]:
nShifted[DataIdxs[idx]] += 1
DataIdxs[idx] = 0
for idx, shift in enumerate(nShifted):
self.__log("In fold " + str(idx) + ", " + str(shift) +
" examples were shifted to the train set.")
#Var for saving each Fols result
optAcc = {}
results = {}
exp_pred = {}
nTrainEx = {}
nTestEx = {}
#Set a dict of learners
MLmethods = {}
if type(self.learner) == dict:
for ml in self.learner:
MLmethods[ml] = self.learner[ml]
else:
MLmethods[self.learner.name] = self.learner
models = {}
self.__log("Calculating Statistics for MLmethods:")
self.__log(" " + str([x for x in MLmethods]))
#Check data in advance so that, by chance, it will not faill at the last fold!
for foldN in foldsN:
trainData = self.data.select(DataIdxs, foldN, negate=1)
self.__checkTrainData(trainData)
#Optional!!
# Order Learners so that PLS is the first
sortedML = [ml for ml in MLmethods]
if "PLS" in sortedML:
sortedML.remove("PLS")
sortedML.insert(0, "PLS")
stepsDone = 0
nTotalSteps = len(sortedML) * self.nExtFolds
for ml in sortedML:
startTime = time.time()
self.__log(" > " + str(ml) + "...")
try:
#Var for saving each Fols result
results[ml] = []
exp_pred[ml] = []
models[ml] = []
nTrainEx[ml] = []
nTestEx[ml] = []
optAcc[ml] = []
logTxt = ""
for foldN in foldsN:
if type(self.learner) == dict:
self.paramList = None
trainData = self.data.select(DataIdxs, foldN, negate=1)
testData = self.data.select(DataIdxs, foldN)
smilesAttr = dataUtilities.getSMILESAttr(trainData)
if smilesAttr:
self.__log("Found SMILES attribute:" + smilesAttr)
if MLmethods[ml].specialType == 1:
trainData = dataUtilities.attributeSelectionData(
trainData,
[smilesAttr, trainData.domain.classVar.name])
testData = dataUtilities.attributeSelectionData(
testData,
[smilesAttr, testData.domain.classVar.name])
self.__log(
"Selected attrs: " +
str([attr.name for attr in trainData.domain]))
else:
trainData = dataUtilities.attributeDeselectionData(
trainData, [smilesAttr])
testData = dataUtilities.attributeDeselectionData(
testData, [smilesAttr])
self.__log("Selected attrs: " + str(
[attr.name for attr in trainData.domain[0:3]] +
["..."] + [
attr.name for attr in trainData.
domain[len(trainData.domain) - 3:]
]))
nTrainEx[ml].append(len(trainData))
nTestEx[ml].append(len(testData))
#Test if trainsets inside optimizer will respect dataSize criterias.
# if not, don't optimize, but still train the model
dontOptimize = False
if self.responseType != "Classification" and (
len(trainData) *
(1 - 1.0 / self.nInnerFolds) < 20):
dontOptimize = True
else:
tmpDataIdxs = self.sampler(trainData, self.nInnerFolds)
tmpTrainData = trainData.select(tmpDataIdxs,
1,
negate=1)
if not self.__checkTrainData(tmpTrainData, False):
dontOptimize = True
SpecialModel = None
if dontOptimize:
logTxt += " Fold " + str(
foldN
) + ": Too few compounds to optimize model hyper-parameters\n"
self.__log(logTxt)
if trainData.domain.classVar.varType == orange.VarTypes.Discrete:
res = evalUtilities.crossValidation(
[MLmethods[ml]],
trainData,
folds=5,
stratified=orange.MakeRandomIndices.
StratifiedIfPossible,
random_generator=random.randint(0, 100))
CA = evalUtilities.CA(res)[0]
optAcc[ml].append(CA)
else:
res = evalUtilities.crossValidation(
[MLmethods[ml]],
trainData,
folds=5,
stratified=orange.MakeRandomIndices.
StratifiedIfPossible,
random_generator=random.randint(0, 100))
R2 = evalUtilities.R2(res)[0]
optAcc[ml].append(R2)
else:
if MLmethods[ml].specialType == 1:
if trainData.domain.classVar.varType == orange.VarTypes.Discrete:
optInfo, SpecialModel = MLmethods[
ml].optimizePars(trainData, folds=5)
optAcc[ml].append(optInfo["Acc"])
else:
res = evalUtilities.crossValidation(
[MLmethods[ml]],
trainData,
folds=5,
stratified=orange.MakeRandomIndices.
StratifiedIfPossible,
random_generator=random.randint(0, 100))
R2 = evalUtilities.R2(res)[0]
optAcc[ml].append(R2)
else:
runPath = miscUtilities.createScratchDir(
baseDir=AZOC.NFS_SCRATCHDIR,
desc="AccWOptParam",
seed=id(trainData))
trainData.save(
os.path.join(runPath, "trainData.tab"))
tunedPars = paramOptUtilities.getOptParam(
learner=MLmethods[ml],
trainDataFile=os.path.join(
runPath, "trainData.tab"),
paramList=self.paramList,
useGrid=False,
verbose=self.verbose,
queueType=self.queueType,
runPath=runPath,
nExtFolds=None,
nFolds=self.nInnerFolds,
logFile=self.logFile,
getTunedPars=True,
fixedParams=self.fixedParams)
if not MLmethods[ml] or not MLmethods[ml].optimized:
self.__log(
" WARNING: GETACCWOPTPARAM: The learner "
+ str(ml) + " was not optimized.")
self.__log(
" It will be ignored")
#self.__log(" It will be set to default parameters")
self.__log(
" DEBUG can be done in: "
+ runPath)
#Set learner back to default
#MLmethods[ml] = MLmethods[ml].__class__()
raise Exception("The learner " + str(ml) +
" was not optimized.")
else:
if trainData.domain.classVar.varType == orange.VarTypes.Discrete:
optAcc[ml].append(tunedPars[0])
else:
res = evalUtilities.crossValidation(
[MLmethods[ml]],
trainData,
folds=5,
stratified=orange.MakeRandomIndices.
StratifiedIfPossible,
random_generator=random.randint(
0, 100))
R2 = evalUtilities.R2(res)[0]
optAcc[ml].append(R2)
miscUtilities.removeDir(runPath)
#Train the model
if SpecialModel is not None:
model = SpecialModel
else:
model = MLmethods[ml](trainData)
models[ml].append(model)
#Test the model
if self.responseType == "Classification":
results[ml].append(
(evalUtilities.getClassificationAccuracy(
testData, model),
evalUtilities.getConfMat(testData, model)))
else:
local_exp_pred = []
# Predict using bulk-predict
predictions = model(testData)
# Gather predictions
for n, ex in enumerate(testData):
local_exp_pred.append(
(ex.getclass().value, predictions[n].value))
results[ml].append(
(evalUtilities.calcRMSE(local_exp_pred),
evalUtilities.calcRsqrt(local_exp_pred)))
#Save the experimental value and correspondent predicted value
exp_pred[ml] += local_exp_pred
if callBack:
stepsDone += 1
if not callBack((100 * stepsDone) / nTotalSteps):
return None
if callBackWithFoldModel:
callBackWithFoldModel(model)
res = self.createStatObj(
results[ml],
exp_pred[ml],
nTrainEx[ml],
nTestEx[ml],
self.responseType,
self.nExtFolds,
logTxt,
labels=hasattr(self.data.domain.classVar, "values")
and list(self.data.domain.classVar.values) or None)
if self.verbose > 0:
print "UnbiasedAccuracyGetter!Results " + ml + ":\n"
pprint(res)
if not res:
raise Exception("No results available!")
res["runningTime"] = time.time() - startTime
statistics[ml] = copy.deepcopy(res)
self.__writeResults(statistics)
self.__log(" OK")
except:
self.__log(" Learner " + str(ml) +
" failed to create/optimize the model!")
error = str(sys.exc_info()[0]) +" "+\
str(sys.exc_info()[1]) +" "+\
str(traceback.extract_tb(sys.exc_info()[2]))
self.__log(error)
res = self.createStatObj()
statistics[ml] = copy.deepcopy(res)
self.__writeResults(statistics)
if not statistics or len(statistics) < 1:
self.__log("ERROR: No statistics to return!")
return None
elif len(statistics) > 1:
#We still need to build a consensus model out of the stable models
# ONLY if there are more that one model stable!
# When only one or no stable models, build a consensus based on all models
# ALWAYS exclude specialType models (MLmethods[ml].specialType > 0)
consensusMLs = {}
for modelName in statistics:
StabilityValue = statistics[modelName]["StabilityValue"]
if StabilityValue is not None and statistics[modelName][
"stable"]:
consensusMLs[modelName] = copy.deepcopy(
statistics[modelName])
self.__log("Found " + str(len(consensusMLs)) +
" stable MLmethods out of " + str(len(statistics)) +
" MLmethods.")
if len(consensusMLs
) <= 1: # we need more models to build a consensus!
consensusMLs = {}
for modelName in statistics:
consensusMLs[modelName] = copy.deepcopy(
statistics[modelName])
# Exclude specialType models
excludeThis = []
for learnerName in consensusMLs:
if models[learnerName][0].specialType > 0:
excludeThis.append(learnerName)
for learnerName in excludeThis:
consensusMLs.pop(learnerName)
self.__log(" > Excluded special model " + learnerName)
self.__log(" > Stable modules: " + str(consensusMLs.keys()))
if len(consensusMLs) >= 2:
#Var for saving each Fols result
startTime = time.time()
Cresults = []
Cexp_pred = []
CnTrainEx = []
CnTestEx = []
self.__log(
"Calculating the statistics for a Consensus model based on "
+ str([ml for ml in consensusMLs]))
for foldN in range(self.nExtFolds):
if self.responseType == "Classification":
CLASS0 = str(self.data.domain.classVar.values[0])
CLASS1 = str(self.data.domain.classVar.values[1])
# exprTest0
exprTest0 = "(0"
for ml in consensusMLs:
exprTest0 += "+( " + ml + " == " + CLASS0 + " )*" + str(
optAcc[ml][foldN]) + " "
exprTest0 += ")/IF0(sum([False"
for ml in consensusMLs:
exprTest0 += ", " + ml + " == " + CLASS0 + " "
exprTest0 += "]),1)"
# exprTest1
exprTest1 = "(0"
for ml in consensusMLs:
exprTest1 += "+( " + ml + " == " + CLASS1 + " )*" + str(
optAcc[ml][foldN]) + " "
exprTest1 += ")/IF0(sum([False"
for ml in consensusMLs:
exprTest1 += ", " + ml + " == " + CLASS1 + " "
exprTest1 += "]),1)"
# Expression
expression = [
exprTest0 + " >= " + exprTest1 + " -> " + CLASS0,
" -> " + CLASS1
]
else:
Q2sum = sum([optAcc[ml][foldN] for ml in consensusMLs])
expression = "(1 / " + str(Q2sum) + ") * (0"
for ml in consensusMLs:
expression += " + " + str(
optAcc[ml][foldN]) + " * " + ml + " "
expression += ")"
testData = self.data.select(
DataIdxs, foldN + 1) # fold 0 if for the train Bias!!
smilesAttr = dataUtilities.getSMILESAttr(testData)
if smilesAttr:
self.__log("Found SMILES attribute:" + smilesAttr)
testData = dataUtilities.attributeDeselectionData(
testData, [smilesAttr])
self.__log("Selected attrs: " + str(
[attr.name
for attr in trainData.domain[0:3]] + ["..."] + [
attr.name for attr in
trainData.domain[len(trainData.domain) - 3:]
]))
CnTestEx.append(len(testData))
consensusClassifiers = {}
for learnerName in consensusMLs:
consensusClassifiers[learnerName] = models[
learnerName][foldN]
model = AZorngConsensus.ConsensusClassifier(
classifiers=consensusClassifiers,
expression=expression)
CnTrainEx.append(model.NTrainEx)
#Test the model
if self.responseType == "Classification":
Cresults.append(
(evalUtilities.getClassificationAccuracy(
testData, model),
evalUtilities.getConfMat(testData, model)))
else:
local_exp_pred = []
# Predict using bulk-predict
predictions = model(testData)
# Gather predictions
for n, ex in enumerate(testData):
local_exp_pred.append(
(ex.getclass().value, predictions[n].value))
Cresults.append(
(evalUtilities.calcRMSE(local_exp_pred),
evalUtilities.calcRsqrt(local_exp_pred)))
#Save the experimental value and correspondent predicted value
Cexp_pred += local_exp_pred
res = self.createStatObj(
Cresults,
Cexp_pred,
CnTrainEx,
CnTestEx,
self.responseType,
self.nExtFolds,
labels=hasattr(self.data.domain.classVar, "values")
and list(self.data.domain.classVar.values) or None)
res["runningTime"] = time.time() - startTime
statistics["Consensus"] = copy.deepcopy(res)
statistics["Consensus"][
"IndividualStatistics"] = copy.deepcopy(consensusMLs)
self.__writeResults(statistics)
self.__log("Returned multiple ML methods statistics.")
return statistics
#By default return the only existing statistics!
self.__writeResults(statistics)
self.__log("Returned only one ML method statistics.")
return statistics[statistics.keys()[0]]