def createDHontModel(recommendersIDs: List[str]):
modelDHontData: List[List] = [[rIdI, 1] for rIdI in recommendersIDs]
modelDHontDF: DataFrame = pd.DataFrame(modelDHontData,
columns=["methodID", "votes"])
modelDHontDF.set_index("methodID", inplace=True)
EvalToolDHondt.linearNormalizingPortfolioModelDHont(modelDHontDF)
return modelDHontDF
def test01():
print("Test 01")
#print("Running Two paralel History Databases:")
# method results, items=[1,2,4,5,6,7,8,12,32,64,77]
methodsResultDict:dict = {
"metoda1": pd.Series([0.2, 0.1, 0.3, 0.3, 0.1], [32, 2, 8, 1, 4], name="rating"),
"metoda2": pd.Series([0.1, 0.1, 0.2, 0.3, 0.3], [1, 5, 32, 6, 7], name="rating"),
"metoda3": pd.Series([0.3, 0.1, 0.2, 0.3, 0.1], [7, 2, 77, 64, 12], name="rating")
}
rItemIDsWithResponsibility:List = [(7, {'metoda1': 0, 'metoda2': 24.0, 'metoda3': 18.0}), (1, {'metoda1': 30.0, 'metoda2': 8.0, 'metoda3': 0}), (32, {'metoda1': 20.0, 'metoda2': 16.0, 'metoda3': 0}), (8, {'metoda1': 30.0, 'metoda2': 0, 'metoda3': 0}), (6, {'metoda1': 0, 'metoda2': 24.0, 'metoda3': 0}), (64, {'metoda1': 0, 'metoda2': 0, 'metoda3': 18.0}), (2, {'metoda1': 10.0, 'metoda2': 0, 'metoda3': 6.0}), (77, {'metoda1': 0, 'metoda2': 0, 'metoda3': 12.0}), (4, {'metoda1': 10.0, 'metoda2': 0, 'metoda3': 0}), (5, {'metoda1': 0, 'metoda2': 8.0, 'metoda3': 0}), (12, {'metoda1': 0, 'metoda2': 0, 'metoda3': 6.0})]
# methods parametes
portfolioModelData:List[tuple] = [['metoda1',100], ['metoda2',80], ['metoda3',60]]
portfolioModelDF:DataFrame = pd.DataFrame(portfolioModelData, columns=["methodID","votes"])
portfolioModelDF.set_index("methodID", inplace=True)
print("Definition:")
print(portfolioModelDF)
print()
# linearly normalizing to unit sum of votes
#EvalToolDHont.linearNormalizingPortfolioModelDHont(portfolioModelDF)
print("Linearly normalizing:")
print(portfolioModelDF)
print()
evaluationDict:dict = {}
print("Clicked:")
EvalToolDHondt.click(rItemIDsWithResponsibility, 7, portfolioModelDF, evaluationDict)
EvalToolDHondt.click(rItemIDsWithResponsibility, 1, portfolioModelDF, evaluationDict)
EvalToolDHondt.click(rItemIDsWithResponsibility, 7, portfolioModelDF, evaluationDict)
print()
print("Displayed - start:")
for i in range(100):
rItemIDsWithResponsibility1:List = [(7, {'metoda1': 0, 'metoda2': 24.0, 'metoda3': 18.0})]
EvalToolDHondt.displayed(rItemIDsWithResponsibility1, portfolioModelDF, evaluationDict)
print(portfolioModelDF)
print("Displayed - end:")
print()
print("Clicked:")
EvalToolDHondt.click(rItemIDsWithResponsibility, 4, portfolioModelDF, evaluationDict)
print()
def getParameters(self):
selectorIDs: List[str] = BatchFuzzyDHondt().getSelectorParameters(
).keys()
negativeImplFeedback: List[
str] = self.getNegativeImplFeedbackParameters().keys()
#lrClicks:List[float] = [0.2, 0.1, 0.02, 0.005]
lrClicks: List[float] = [0.1]
#lrViewDivisors:List[float] = [200, 500, 1000]
lrViewDivisors: List[float] = [200]
aDict: dict = {}
for selectorIDH in selectorIDs:
for nImplFeedbackI in negativeImplFeedback:
for lrClickJ in lrClicks:
for lrViewDivisorK in lrViewDivisors:
keyIJ: str = str(selectorIDH) + "Clk" + str(
lrClickJ).replace(".", "") + "ViewDivisor" + str(
lrViewDivisorK).replace(".",
"") + nImplFeedbackI
lrViewIJK: float = lrClickJ / lrViewDivisorK
eTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClickJ,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrViewIJK
})
nImplFeedback: APenalization = self.getNegativeImplFeedbackParameters(
)[nImplFeedbackI]
selectorH: ADHondtSelector = BatchFuzzyDHondt(
).getSelectorParameters()[selectorIDH]
aDict[keyIJ] = (selectorH, nImplFeedback, eTool)
return aDict
def test02():
print("Test 02")
rIDs, rDescr = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs()
model: DataFrame = PModelDHondt(rIDs)
print(model)
userID: int = 1
rItemIDsWithResponsibility: List[(int, Dict)] = [(1, {
rIDs[0]: 0.05,
rIDs[1]: 0.05,
rIDs[2]: 0.05,
rIDs[3]: 0.05,
rIDs[4]: 0.05,
rIDs[5]: 0.05,
rIDs[6]: 0.05,
rIDs[7]: 0.65
})]
lrClick: float = 0.03
lrView: float = lrClick / 500
evalTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClick,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrView
})
evalTool.click(userID, rItemIDsWithResponsibility, 1, model, {})
for i in range(555):
evalTool.displayed(userID, rItemIDsWithResponsibility, model, {})
print(model)
def getParameters(self):
selectorIDs: List[str] = self.getSelectorParameters().keys()
lrClicks: List[float] = [0.2, 0.1, 0.02, 0.005]
#lrClicks:List[float] = [0.1]
lrViewDivisors: List[float] = [200, 500, 1000]
#lrViewDivisors:List[float] = [500]
aDict: dict = {}
for selectorIDI in selectorIDs:
for lrClickJ in lrClicks:
for lrViewDivisorK in lrViewDivisors:
keyIJ: str = selectorIDI + "Clk" + str(lrClickJ).replace(
".", "") + "ViewDivisor" + str(lrViewDivisorK).replace(
".", "")
lrViewIJK: float = lrClickJ / lrViewDivisorK
eToolIJK: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClickJ,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrViewIJK
})
selectorIJK: ADHondtSelector = self.getSelectorParameters(
)[selectorIDI]
aDict[keyIJ] = (selectorIJK, eToolIJK)
return aDict
def getFuzzyDHontINF():
#taskID:str = "Web" + "FuzzyDHondtINF" + "Roulette1"
taskID:str = "Web" + "FuzzyDHondt" + "Fixed"
dataset:ADataset = DatasetST.readDatasets()
#selector:ADHondtSelector = RouletteWheelSelector({RouletteWheelSelector.ARG_EXPONENT: 1})
selector:ADHondtSelector = TheMostVotedItemSelector({})
pToolOLin0802HLin1002:APenalization = PenalizationToolDefinition.exportPenaltyToolOLin0802HLin1002(
InputSimulatorDefinition.numberOfAggrItems)
aDescDHont:AggregationDescription = InputAggrDefinition.exportADescDHondtINF(selector, pToolOLin0802HLin1002)
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs()
pDescr:Portfolio1AggrDescription = Portfolio1AggrDescription(
taskID, rIDs, rDescs, aDescDHont)
history:AHistory = HistoryHierDF(taskID)
port:APortfolio = pDescr.exportPortfolio(taskID, history)
port.train(history, dataset)
model:DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
evalTool:AEvalTool = EvalToolDHondt({EvalToolDHondt.ARG_LEARNING_RATE_CLICKS: 0.03,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS: 0.03 / 500})
return (taskID, port, model, evalTool, history)
def getParameters(cls):
selectorIDs: List[str] = BatchDefMLFuzzyDHondt().getSelectorParameters(
).keys()
negativeImplFeedback: List[
str] = cls.getNegativeImplFeedbackParameters().keys()
aDict: Dict[str, object] = {}
for selectorIDH in selectorIDs:
for nImplFeedbackI in negativeImplFeedback:
for lrClickJ in cls.lrClicks:
for lrViewDivisorK in cls.lrViewDivisors:
keyIJ: str = str(selectorIDH) + "Clk" + str(
lrClickJ).replace(".", "") + "ViewDivisor" + str(
lrViewDivisorK).replace(".",
"") + nImplFeedbackI
lrViewIJK: float = lrClickJ / lrViewDivisorK
eTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClickJ,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrViewIJK
})
nImplFeedback: APenalization = cls.getNegativeImplFeedbackParameters(
)[nImplFeedbackI]
selectorH: ADHondtSelector = BatchDefMLFuzzyDHondt(
).getSelectorParameters()[selectorIDH]
aDict[keyIJ] = (selectorH, nImplFeedback, eTool)
return aDict
def test01():
print("Simulation: ML FuzzyDHondt")
jobID: str = "Roulette1"
selector = RouletteWheelSelector({RouletteWheelSelector.ARG_EXPONENT: 1})
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs()
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"FuzzyDHondt" + jobID, rIDs, rDescs,
InputAggrDefinition.exportADescDHondt(selector))
batchID: str = "ml1mDiv90Ulinear0109R1"
dataset: DatasetML = DatasetML.readDatasets()
behaviourFile: str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF: DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
lrClick: float = 0.03
lrView: float = lrClick / 500
eTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClick,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrView
})
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationML, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [model], [eTool],
[HistoryHierDF(pDescr.getPortfolioID())])
def __init__(self, argumentsDict: Dict[str, object]):
if type(argumentsDict) is not dict:
raise ValueError("Argument argumentsDict isn't type dict.")
self.et: AEvalTool = EvalToolDHondt(argumentsDict)
self.normalizationOfResponsibility: bool = argumentsDict.get(
self.ARG_NORMALIZATION_OF_RESPONSIBILITY, False)
def getParameters(self):
aDict:Dict[str,object] = {}
for lrClickI in self.lrClicks:
for lrViewDivisorJ in self.lrViewDivisors:
keyIJ:str = "Clk" + str(lrClickI).replace(".", "") + "ViewDivisor" + str(lrViewDivisorJ).replace(".", "")
lrViewIJ:float = lrClickI / lrViewDivisorJ
eToolIJ:AEvalTool = EvalToolDHondt({EvalToolDHondt.ARG_LEARNING_RATE_CLICKS: lrClickI,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS: lrViewIJ})
aDict[keyIJ] = eToolIJ
return aDict
def getParameters(self):
aDict:Dict[str,object] = {}
for selectorIDI in self.selectorIDs:
for lrClickJ in self.lrClicks:
for normOfResponsK in self.normOfRespons:
for lrViewDivisorK in self.lrViewDivisors:
keyIJ:str = selectorIDI + "Clk" + str(lrClickJ).replace(".", "") + "ViewDivisor" + str(lrViewDivisorK).replace(".", "") + "NR" + str(normOfResponsK)
lrViewIJK:float = lrClickJ / lrViewDivisorK
eToolIJK:AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS: lrClickJ,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS: lrViewIJK,
EvalToolDHondt.ARG_NORMALIZATION_OF_RESPONSIBILITY: normOfResponsK})
selectorIJK:ADHondtSelector = self.getSelectorParameters()[selectorIDI]
aDict[keyIJ] = (selectorIJK, eToolIJK)
return aDict
def getParameters(self):
aDict: Dict[str, object] = {}
for selectorIDI in self.selectorIDs:
for gLrClickJ in self.mGlobalLrClicks:
for gLrViewDivisorK in self.mGlobalLrViewDivisors:
for gNormOfResponsL in self.mGlobalNormOfRespons:
for pLrClickM in self.mPersonLrClicks:
for pLrViewDivisorN in self.mPersonLrViewDivisors:
for pLrViewDivisorO in self.mPersonNormOfRespons:
gjk: str = "Clk" + str(gLrClickJ).replace(
".", "") + "ViewDivisor" + str(
gLrViewDivisorK).replace(
".", "") + "NR" + str(
gNormOfResponsL)
pjk: str = "Clk" + str(pLrClickM).replace(
".", "") + "ViewDivisor" + str(
pLrViewDivisorN).replace(
".", "") + "NR" + str(
pLrViewDivisorO)
keyIJ: str = selectorIDI + gjk + pjk
lrViewJK: float = gLrClickJ / gLrViewDivisorK
lrViewLM: float = pLrClickM / pLrViewDivisorN
evalToolMGlobal: EvalToolDHondt = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
gLrClickJ,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrViewJK,
EvalToolDHondt.ARG_NORMALIZATION_OF_RESPONSIBILITY:
gNormOfResponsL
})
evalToolMPerson: EvalToolDHondt = EvalToolDHondtPersonal({
EvalToolDHondtPersonal.ARG_LEARNING_RATE_CLICKS:
pLrClickM,
EvalToolDHondtPersonal.ARG_LEARNING_RATE_VIEWS:
lrViewLM,
EvalToolDHondtPersonal.ARG_NORMALIZATION_OF_RESPONSIBILITY:
pLrViewDivisorO
})
eToolIJK: AEvalTool = EToolHybrid(
evalToolMGlobal, evalToolMPerson, {})
selectorIJK: ADHondtSelector = BatchDefMLFuzzyDHondt(
).getSelectorParameters()[selectorIDI]
aDict[keyIJ] = (selectorIJK, eToolIJK)
return aDict
def test21():
print("Simulation: ST FuzzyDHondtINF")
jobID: str = "Roulette1"
selector = RouletteWheelSelector({RouletteWheelSelector.ARG_EXPONENT: 1})
#pProbToolOLin0802HLin1002:APenalization = PenalizationToolDefinition.exportProbPenaltyToolOStat08HLin1002(
# InputSimulatorDefinition.numberOfAggrItems)
pToolOLin0802HLin1002: APenalization = PenalizationToolDefinition.exportPenaltyToolOLin0802HLin1002(
InputSimulatorDefinition.numberOfAggrItems)
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs()
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"FuzzyDHondtINF" + jobID, rIDs, rDescs,
InputAggrDefinition.exportADescDHondtINF(selector,
pToolOLin0802HLin1002))
batchID: str = "stDiv90Ulinear0109R1"
dataset: DatasetST = DatasetST.readDatasets()
behaviourFile: str = BehavioursST.getFile(BehavioursST.BHVR_LINEAR0109)
behavioursDF: DataFrame = BehavioursST.readFromFileST(behaviourFile)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
print(model)
lrClick: float = 0.1
lrView: float = lrClick / 300
evalTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClick,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrView
})
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationST, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [model], [evalTool],
[HistoryHierDF(pDescr.getPortfolioID())])
def test31():
print("Simulation: RR FuzzyDHondt")
lrClick: float = 0.03
#lrView:float = lrClick / 300
lrViewDivisor: float = 250
jobID: str = "Fixed" + "Clk" + str(lrClick).replace(
".", "") + "ViewDivisor" + str(lrViewDivisor).replace(".", "")
selector: ADHondtSelector = TheMostVotedItemSelector({})
rIDs, rDescs = InputRecomRRDefinition.exportPairOfRecomIdsAndRecomDescrs()
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"FDHondt" + jobID, rIDs, rDescs,
InputAggrDefinition.exportADescDHondt(selector))
batchID: str = "rrDiv90Ulinear0109R1"
dataset: DatasetRetailRocket = DatasetRetailRocket.readDatasetsWithFilter(
minEventCount=50)
behaviourFile: str = BehavioursRR.getFile(BehavioursRR.BHVR_LINEAR0109)
behavioursDF: DataFrame = BehavioursRR.readFromFileRR(behaviourFile)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
print(model)
evalTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
lrClick,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
lrClick / lrViewDivisor
})
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationRR, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [model], [evalTool],
[HistoryHierDF(pDescr.getPortfolioID())])
def run(self, batchID:str, jobID:str):
divisionDatasetPercentualSize:int
uBehaviour:str
repetition:int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition().getBatchParameters(self.datasetID)[batchID]
selector, nImplFeedback = self.getParameters()[jobID]
eTool:AEvalTool = EvalToolDHondt({EvalToolDHondt.ARG_LEARNING_RATE_CLICKS: 0.02,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS: 1000})
rIDs, rDescs = InputRecomMLDefinition.exportPairOfRecomIdsAndRecomDescrs()
aDescFuzzyHontDirectOptimizeINF:AggregationDescription = InputAggrDefinition.exportADescDFuzzyHondtDirectOptimizeINF(selector, nImplFeedback)
pDescr:Portfolio1AggrDescription = Portfolio1AggrDescription(
self.getBatchName() + jobID, rIDs, rDescs, aDescFuzzyHontDirectOptimizeINF)
model:DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
simulator:Simulator = InputSimulatorDefinition().exportSimulatorML1M(
batchID, divisionDatasetPercentualSize, uBehaviour, repetition)
simulator.simulate([pDescr], [model], [eTool], [HistoryHierDF(pDescr.getPortfolioID())])
def run(self, batchID: str, jobID: str):
from execute.generateBatches import BatchParameters #class
divisionDatasetPercentualSize: int
uBehaviour: str
repetition: int
divisionDatasetPercentualSize, uBehaviour, repetition = BatchParameters.getBatchParameters(
)[batchID]
selector, nImplFeedback = self.getParameters()[jobID]
eTool: AEvalTool = EvalToolDHondt({
EvalToolDHondt.ARG_LEARNING_RATE_CLICKS:
0.02,
EvalToolDHondt.ARG_LEARNING_RATE_VIEWS:
1000
})
datasetID: str = "ml1m" + "Div" + str(divisionDatasetPercentualSize)
rIDs, rDescs = InputRecomDefinition.exportPairOfRecomIdsAndRecomDescrs(
datasetID)
aDescFuzzyHontDirectOptimizeINF: AggregationDescription = InputAggrDefinition.exportADescDFuzzyHontDirectOptimizeINF(
selector, nImplFeedback)
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"FuzzyDHondtDirectOptimizeINF" + jobID, rIDs, rDescs,
aDescFuzzyHontDirectOptimizeINF)
model: DataFrame = ModelDefinition.createDHontModel(
pDescr.getRecommendersIDs())
simulator: Simulator = InputSimulatorDefinition.exportSimulatorML1M(
batchID, divisionDatasetPercentualSize, uBehaviour, repetition)
simulator.simulate([pDescr], [model], [eTool], HistoryHierDF)
