def test01():
print("Simulation: ML TheMostPopular")
rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescTheMostPopular()
pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomMLDefinition.THE_MOST_POPULAR.title(),
InputRecomMLDefinition.THE_MOST_POPULAR, rDescr)
batchID:str = "ml1mDiv90Ulinear0109R1"
dataset:DatasetML = DatasetML.readDatasets()
behaviourFile:str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
# remove old results
#path:str = ".." + os.sep + "results" + os.sep + batchID
#try:
# os.remove(path + os.sep + "computation-theMostPopular.txt")
# os.remove(path + os.sep + "historyOfRecommendation-theMostPopular.txt")
# os.remove(path + os.sep + "portfModelTimeEvolution-theMostPopular.txt")
#except:
# print("An exception occurred")
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationML, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def run(self, batchID: str, jobID: str):
divisionDatasetPercentualSize: int
uBehaviour: str
repetition: int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition(
).getBatchParameters(self.datasetID)[batchID]
eTool: AEvalTool = EToolDoNothing({})
rIDs, rDescs = InputRecomRRDefinition.exportPairOfRecomIdsAndRecomDescrs(
)
aDescWeightedFAI: AggregationDescription = InputAggrDefinition.exportADescFAI(
)
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"FAI" + jobID, rIDs, rDescs, aDescWeightedFAI)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
simulator: Simulator = InputSimulatorDefinition(
).exportSimulatorRetailRocket(batchID, divisionDatasetPercentualSize,
uBehaviour, repetition)
simulator.simulate([pDescr], [model], [eTool],
[HistoryHierDF(pDescr.getPortfolioID())])
def run(self, batchID: str, jobID: str):
divisionDatasetPercentualSize: int
uBehaviour: str
repetition: int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition(
).getBatchParameters(self.datasetID)[batchID]
eTool: AEvalTool = EToolDoNothing({})
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs(
)
mainMethodID: str = "RecomW2Vtalli100000Ws1Vs32Upsmaxups1" # the best method for ST
aDescRandomKfromN: AggregationDescription = InputAggrDefinition.exportADescRandomKfromN(
mainMethodID)
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
self.getBatchName() + jobID, rIDs, rDescs, aDescRandomKfromN)
model: DataFrame = DataFrame()
simulator: Simulator = InputSimulatorDefinition(
).exportSimulatorSlantour(batchID, divisionDatasetPercentualSize,
uBehaviour, repetition)
simulator.simulate([pDescr], [model], [eTool],
[HistoryHierDF(pDescr.getPortfolioID())])
def test02():
print("Test 02")
rDescr: RecommenderDescription = InputRecomRRDefinition.exportRDescTheMostPopular(
)
recommenderID: str = InputRecomRRDefinition.THE_MOST_POPULAR
rDescr: RecommenderDescription = InputRecomRRDefinition.exportRDescKNN()
recommenderID: str = InputRecomRRDefinition.KNN
rDescr: RecommenderDescription = InputRecomRRDefinition.exportRDescBPRMFIMPL(
)
recommenderID: str = InputRecomRRDefinition.BPRMFIMPL
rDescr: RecommenderDescription = InputRecomRRDefinition.exportRDescVMContextKNN(
)
recommenderID: str = InputRecomRRDefinition.VMC_KNN
rDescr: RecommenderDescription = InputRecomRRDefinition.exportRDescCosineCB(
)
recommenderID: str = InputRecomRRDefinition.COSINECB
rDescr: RecommenderDescription = InputRecomRRDefinition.exportRDescW2V()
recommenderID: str = InputRecomRRDefinition.W2V
pDescr: Portfolio1MethDescription = Portfolio1MethDescription(
recommenderID.title(), recommenderID, rDescr)
dataset: ADataset = DatasetRetailRocket.readDatasetsWithFilter(
minEventCount=50)
behavioursDF: DataFrame = BehavioursRR.readFromFileRR(
BehavioursRR.getFile("static08"))
history: AHistory = HistoryDF("test")
p: APortfolio = pDescr.exportPortfolio("jobID", history)
p.train(history, dataset)
argsSimulationDict: Dict[str, str] = {
SimulationRR.ARG_WINDOW_SIZE: 50,
SimulationRR.ARG_RECOM_REPETITION_COUNT: 1,
SimulationRR.ARG_NUMBER_OF_RECOMM_ITEMS: 100,
SimulationRR.ARG_NUMBER_OF_AGGR_ITEMS:
InputSimulatorDefinition.numberOfAggrItems,
SimulationRR.ARG_DIV_DATASET_PERC_SIZE: 90,
SimulationRR.ARG_HISTORY_LENGTH: 10
}
# simulation of portfolio
simulator: Simulator = Simulator("test", SimulationRR, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})],
[HistoryHierDF("a")])
def run(self, batchID:str, jobID:str):
divisionDatasetPercentualSize:int
uBehaviour:str
repetition:int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition().getBatchParameters(self.datasetID)[batchID]
rDescr:RecommenderDescription = self.getParameters()[jobID]
recommenderID:str = "W2V" + jobID
pDescr:APortfolioDescription = Portfolio1MethDescription(recommenderID.title(), recommenderID, rDescr)
simulator:Simulator = InputSimulatorDefinition().exportSimulatorRetailRocket(
batchID, divisionDatasetPercentualSize, uBehaviour, repetition)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test26():
print("Simulation: ST VMCMF")
rDescr:RecommenderDescription = InputRecomSTDefinition.exportRDescVMContextKNN()
pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomSTDefinition.VMC_KNN.title(),
InputRecomSTDefinition.VMC_KNN, rDescr)
batchID:str = "slantourDiv90Ulinear0109R1"
dataset:DatasetST = DatasetST.readDatasets()
behaviourFile:str = BehavioursST.getFile(BehavioursST.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursST.readFromFileST(behaviourFile)
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationST, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test24():
print("Simulation: ST CB")
rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescCosineCBcbdOHEupsweightedMeanups3()
pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomMLDefinition.COS_CB_MEAN.title(),
InputRecomMLDefinition.COS_CB_MEAN, rDescr)
batchID:str = "slantourDiv90Ulinear0109R1"
dataset:DatasetST = DatasetST.readDatasets()
behaviourFile:str = BehavioursST.getFile(BehavioursST.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursST.readFromFileST(behaviourFile)
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationST, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test11():
print("Simulation: RR TheMostPopular")
rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescTheMostPopular()
pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomMLDefinition.THE_MOST_POPULAR.title(),
InputRecomMLDefinition.THE_MOST_POPULAR, rDescr)
batchID:str = "retailrocketDiv90Ulinear0109R1"
dataset:DatasetRetailRocket = DatasetRetailRocket.readDatasets()
behaviourFile:str = BehavioursRR.getFile(BehavioursRR.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursRR.readFromFileRR(behaviourFile)
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationRR, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test03():
print("Simulation: ML KNN")
rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescKNN()
pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomMLDefinition.KNN.title(),
InputRecomMLDefinition.KNN, rDescr)
batchID:str = "ml1mDiv90Ulinear0109R1"
dataset:DatasetML = DatasetML.readDatasets()
behaviourFile:str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationML, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test02():
print("Simulation: ML W2V")
rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescW2Vtpositivei50000ws1vs32upsweightedMeanups3()
pDescr:APortfolioDescription = Portfolio1MethDescription("W2vPositiveMax",
"w2vPositiveMax", rDescr)
batchID:str = "ml1mDiv90Ulinear0109R1"
dataset:DatasetML = DatasetML.readDatasets()
behaviourFile:str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationML, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def getW2Vtalli100000ws1vs32upsmaxups1():
taskID:str = "Web" + "W2Vtalli100000ws1vs32upsmaxups1"
rDescr:RecommenderDescription = InputRecomSTDefinition.exportRDescW2Vtalli100000ws1vs32upsmaxups1()
recommenderID:str = "W2V"
pDescr:Portfolio1MethDescription = Portfolio1MethDescription(recommenderID.title(), recommenderID, rDescr)
dataset:ADataset = DatasetST.readDatasets()
history:AHistory = HistoryHierDF(taskID)
port:APortfolio = pDescr.exportPortfolio(taskID, history)
port.train(history, dataset)
model:DataFrame = DataFrame()
evalTool:AEvalTool = EToolDoNothing({})
return (taskID, port, model, evalTool, history)
def run(self, batchID:str, jobID:str):
divisionDatasetPercentualSize:int
uBehaviour:str
repetition:int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition().getBatchParameters(self.datasetID)[batchID]
kI:str = self.getParameters()[jobID]
recommenderID:str = "RecommendervmContextKNN" + "K" + str(kI)
rVMCtKNN:RecommenderDescription = RecommenderDescription(RecommenderVMContextKNN, {
RecommenderVMContextKNN.ARG_K: kI})
pDescr:APortfolioDescription = Portfolio1MethDescription(recommenderID.title(), recommenderID, rVMCtKNN)
simulator:Simulator = InputSimulatorDefinition().exportSimulatorSlantour(
batchID, divisionDatasetPercentualSize, uBehaviour, repetition)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def run(self, batchID:str, jobID:str):
divisionDatasetPercentualSize:int
uBehaviour:str
repetition:int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition().getBatchParameters(self.datasetID)[batchID]
datasetID:str = "ml1m" + "Div" + str(divisionDatasetPercentualSize)
recommenderID:str
nImplFeedback:APenalization
recommenderID, nImplFeedback = self.getParameters()[jobID]
rDescr:RecommenderDescription = InputRecomMLDefinition.exportInputRecomDefinition(recommenderID)
pDescr:APortfolioDescription = PortfolioNeg1MethDescription(jobID.title(), recommenderID, rDescr, nImplFeedback)
simulator:Simulator = InputSimulatorDefinition().exportSimulatorML1M(
batchID, divisionDatasetPercentualSize, uBehaviour, repetition)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test04():
print("Simulation: ML CB")
#rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescCBmean()
rDescr:RecommenderDescription = InputRecomMLDefinition.exportRDescCosineCBcbdOHEupsmaxups1()
#pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomMLDefinition.COS_CB_MEAN.title(),
# InputRecomMLDefinition.COS_CB_MEAN, rDescr)
pDescr:APortfolioDescription = Portfolio1MethDescription(InputRecomMLDefinition.COS_CB_WINDOW3.title(),
InputRecomMLDefinition.COS_CB_WINDOW3, rDescr)
batchID:str = "ml1mDiv90Ulinear0109R1"
dataset:DatasetML = DatasetML.readDatasets()
behaviourFile:str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF:DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
# simulation of portfolio
simulator:Simulator = Simulator(batchID, SimulationML, argsSimulationDict, dataset, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})], [HistoryHierDF(pDescr.getPortfolioID())])
def test01():
print("Test 01")
rDescr: RecommenderDescription = RecommenderDescription(
RecommenderTheMostPopular, {})
recommenderID: str = "TheMostPopular"
pDescr: Portfolio1MethDescription = Portfolio1MethDescription(
recommenderID.title(), recommenderID, rDescr)
dataset: ADataset = DatasetML.readDatasets()
history: AHistory = HistoryDF("test")
p: APortfolio = pDescr.exportPortfolio("jobID", history)
p.train(history, dataset)
# r, rwr = p.recommend(1, DataFrame(), {APortfolio.ARG_NUMBER_OF_AGGR_ITEMS:20})
# rItemID1 = r[0]
# rItemID2 = r[1]
# rItemID3 = r[2]
#
# print(r)
# print("rItemID1: " + str(rItemID1))
# print("rItemID2: " + str(rItemID2))
# print("rItemID3: " + str(rItemID3))
testRatingsDF: DataFrame = DataFrame(columns=[
Ratings.COL_USERID, Ratings.COL_MOVIEID, Ratings.COL_RATING,
Ratings.COL_TIMESTAMP
])
timeStampI: int = 1000
userID1: int = 1
userID2: int = 2
userID3: int = 3
rItemID1: int = 9001
rItemID2: int = 9002
rItemID3: int = 9003
# training part of dataset
for i in [i + 0 for i in range(5 * 8)]:
timeStampI = timeStampI + 1
testRatingsDF.loc[i] = [userID1] + list([9000, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID2] + list(
[rItemID1, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID2] + list(
[rItemID2, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID3] + list(
[rItemID3, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID2] + list(
[rItemID2, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID2] + list(
[rItemID2, 5, timeStampI])
# testing part of dataset
userID11: int = 11
userID12: int = 12
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID11] + list(
[rItemID1, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID11] + list(
[rItemID2, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID11] + list(
[rItemID3, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID12] + list(
[rItemID2, 5, timeStampI])
timeStampI = timeStampI + 1
testRatingsDF.loc[len(testRatingsDF)] = [userID11] + list(
[rItemID2, 5, timeStampI])
print("len(testRatingsDF): " + str(len(testRatingsDF)))
print(testRatingsDF.head(20))
print(testRatingsDF.tail(20))
datasetMy: ADataset = DatasetML("", testRatingsDF, dataset.usersDF,
dataset.itemsDF)
behavioursDF: DataFrame = DataFrame(
columns=[BehavioursML.COL_REPETITION, BehavioursML.COL_BEHAVIOUR])
for ratingIndexI in range(len(testRatingsDF)):
for repetitionI in range(5):
behavioursDF.loc[ratingIndexI * 5 + repetitionI] = list(
[repetitionI, [True] * 20])
print(behavioursDF.head(20))
argsSimulationDict: Dict[str, str] = {
SimulationML.ARG_WINDOW_SIZE: 5,
SimulationML.ARG_RECOM_REPETITION_COUNT: 1,
SimulationML.ARG_NUMBER_OF_RECOMM_ITEMS: 100,
SimulationML.ARG_NUMBER_OF_AGGR_ITEMS:
InputSimulatorDefinition.numberOfAggrItems,
SimulationML.ARG_DIV_DATASET_PERC_SIZE: 90,
SimulationML.ARG_HISTORY_LENGTH: 10
}
# simulation of portfolio
simulator: Simulator = Simulator("test", SimulationML, argsSimulationDict,
datasetMy, behavioursDF)
simulator.simulate([pDescr], [DataFrame()], [EToolDoNothing({})],
HistoryHierDF)