def test02():
print("Test 02")
print("Running of comparing Dataframe vs. Database based History:")
history1 = HistorySQLite("databse1")
history2 = HistoryDF("databse2")
start1 = time.time()
for i in range(100):
# userID, itemID, position, observation, clicked
history1.insertRecommendation(1, i, 1, 0.5, False)
isClicked: bool = history1.isObjectClicked(1, 1, 200)
print("isClicked: " + str(isClicked))
end1 = time.time()
start2 = time.time()
for i in range(100):
# userID, itemID, position, observation, clicked
history2.insertRecommendation(1, i, 1, 0.5, False)
end2 = time.time()
print()
print("Time HistorySQLite: " + format(end1 - start1, '.5f') + " s")
print("Time HistoryDF: " + format(end2 - start2, '.5f') + " s")
#print(history1.getPreviousRecomOfUser(1))
print(history1.getPreviousRecomOfUser(1)[0])
#print(history2.getPreviousRecomOfUser(1))
print(history2.getPreviousRecomOfUser(1)[0])
def test01():
print("Test 01")
# number of recommended items
N: int = 5
methodsResultDict: dict = {
"method1": pd.Series([0.9, 0.5, 0.4, 0.2], [1, 2, 3, 4],
name="rating"),
"method2": pd.Series([0.2, 0.9, 0.01], [3, 4, 5], name="rating"),
"method3": pd.Series([0.01, 0.9, 0.9], [5, 6, 7], name="rating")
}
# methods parametes
methodsParamsData: List[tuple] = [['method1', 5, 10, 1, 1],
['method2', 5, 12, 1, 1],
['method3', 6, 13, 1, 1]]
modelDF: DataFrame = pd.DataFrame(
methodsParamsData, columns=["methodID", "r", "n", "alpha0", "beta0"])
modelDF.set_index("methodID", inplace=True)
#modelDF:DataFrame = DataFrame({"votes": [0.5, 0.4, 0.1]}, index=["method1", "method2", "method3"])
#print(modelDF)
userID: int = 0
aggr: AggrDHondtDirectOptimizeThompsonSampling = AggrDHondtDirectOptimizeThompsonSampling(
HistoryDF(""), {
AggrDHondtDirectOptimizeThompsonSampling.ARG_SELECTOR:
TheMostVotedItemSelector({}),
AggrDHondtDirectOptimizeThompsonSampling.ARG_DISCOUNT_FACTOR:
"uniform"
})
itemIDs: List[tuple] = aggr.run(methodsResultDict, modelDF, userID, N)
print("itemIDs:" + str(itemIDs))
aggr: AggrDHondtDirectOptimizeThompsonSampling = AggrDHondtDirectOptimizeThompsonSampling(
HistoryDF(""), {
AggrDHondtDirectOptimizeThompsonSampling.ARG_SELECTOR:
TheMostVotedItemSelector({}),
AggrDHondtDirectOptimizeThompsonSampling.ARG_DISCOUNT_FACTOR:
"DCG"
})
itemIDs: List[tuple] = aggr.run(methodsResultDict, modelDF, userID, N)
print("itemIDs:" + str(itemIDs))
aggr: AggrDHondtDirectOptimizeThompsonSampling = AggrDHondtDirectOptimizeThompsonSampling(
HistoryDF(""), {
AggrDHondtDirectOptimizeThompsonSampling.ARG_SELECTOR:
TheMostVotedItemSelector({}),
AggrDHondtDirectOptimizeThompsonSampling.ARG_DISCOUNT_FACTOR:
"PowerLaw"
})
itemIDs: List[tuple] = aggr.run(methodsResultDict, modelDF, userID, N)
print("itemIDs:" + str(itemIDs))
def test03():
print("Test 03")
print("Running RecommenderCosineCB ST:")
dataset: DatasetST = DatasetST.readDatasets()
args: dict = {
RecommenderCosineCB.ARG_CB_DATA_PATH:
Configuration.cbSTDataFileWithPathTFIDF,
# RecommenderCosineCB.ARG_CB_DATA_PATH:Configuration.cbSTDataFileWithPathOHE,
RecommenderCosineCB.ARG_USER_PROFILE_SIZE:
5,
RecommenderCosineCB.ARG_USER_PROFILE_STRATEGY:
"max",
RecommenderCosineCB.ARG_USE_DIVERSITY:
False,
RecommenderCosineCB.ARG_ALLOWED_ITEMIDS:
list(range(0, 1000))
} #True
rec: ARecommender = RecommenderCosineCB("test", args)
rec.train(HistoryDF("test"), dataset)
#eventsDFDFUpdate:DataFrame = dataset.eventsDF.iloc[5003:5004]
#print(eventsDFDFUpdate)
#rec.update(eventsDFDFUpdate, args)
# user with very outdated profile - no recent objects
r: Series = rec.recommend(3500678, 10, args)
#print(type(r))
print(r)
args: dict = {
RecommenderCosineCB.ARG_CB_DATA_PATH:
Configuration.cbSTDataFileWithPathTFIDF,
# RecommenderCosineCB.ARG_CB_DATA_PATH:Configuration.cbSTDataFileWithPathOHE,
RecommenderCosineCB.ARG_USER_PROFILE_SIZE:
5,
RecommenderCosineCB.ARG_USER_PROFILE_STRATEGY:
"max",
RecommenderCosineCB.ARG_USE_DIVERSITY:
True,
RecommenderCosineCB.ARG_MMR_LAMBDA:
0.5,
RecommenderCosineCB.ARG_ALLOWED_ITEMIDS:
list(range(0, 1000))
} #True
rec: ARecommender = RecommenderCosineCB("test", args)
rec.train(HistoryDF("test"), dataset)
r: Series = rec.recommend(3500678, 10, args)
print(r)
"""
def test01():
print("Test 01")
print("Running RecommenderTheMostPopular ML:")
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
ratingsDFTrain: DataFrame = ratingsDF.iloc[0:50000]
trainDataset: ADataset = DatasetML("test", ratingsDFTrain, pd.DataFrame(),
pd.DataFrame())
rec: ARecommender = RecommenderTheMostPopular("test", {})
rec.train(HistoryDF("test"), trainDataset)
ratingsDFUpdate: DataFrame = ratingsDF.iloc[50003:50004]
rec.update(ARecommender.UPDT_CLICK, ratingsDFUpdate)
r: Series = rec.recommend(331, 50, {})
print(type(r))
print(r)
# testing of a non-existent user
r: Series = rec.recommend(10000, 50, {})
print(type(r))
print(r)
def test01():
print("Test 01")
print("Running AggrRandomRecsSwitching:")
# number of recommended items
N = 3
# 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") ,
"metoda4": pd.Series([], [], name="rating")
}
# print(methodsResultDict)
aggr:AggrRandomRecsSwitching = AggrRandomRecsSwitching(HistoryDF(""), {AggrRandomRecsSwitching.ARG_MAIN_METHOD:"metoda1"})
userID:int = 101
itemIDs:List[tuple] = aggr.runWithResponsibility(methodsResultDict, {}, userID, N)
print(itemIDs)
itemIDs:List[tuple] = aggr.runWithResponsibility(methodsResultDict, {}, userID, N)
print(itemIDs)
userID:int = 102
itemIDs:List[tuple] = aggr.runWithResponsibility(methodsResultDict, {}, userID, N)
print(itemIDs)
def test01():
print("Test 01")
# result items=[21,3,4,5,6,7,8]
inputItemIDsDict: dict[str, pd.Series] = {
"input1":
pd.Series([1.0, 1.0, 1.0, 1.0, 1.0, 1.0], [21, 3, 4, 6, 7, 8],
name="rating"),
"input2":
pd.Series([1.0, 1.0, 1.0, 1.0, 1.0], [21, 2, 4, 5, 9], name="rating"),
"negative":
pd.Series([1.0, 1.0], [21, 2], name="rating")
}
#print(inputItemIDsDict)
modelDF: DataFrame = DataFrame()
history: AHistory = HistoryDF("test")
userID: int = 1
numberOfItems: int = 20
argumentsDict: Dict[str, object] = {
AggrD21.ARG_RATING_THRESHOLD_FOR_NEG: 1.0
}
aggrD21 = AggrD21(history, argumentsDict)
aggrD21.runWithResponsibility(inputItemIDsDict, modelDF, userID,
numberOfItems, argumentsDict)
def test02():
print("Test 02")
print("Running RecommenderW2V RR:")
dataset: DatasetRetailRocket = DatasetRetailRocket.readDatasetsWithFilter(
minEventCount=50)
trainDataset: DatasetRetailRocket = dataset
eventsDF: DataFrame = dataset.eventsDF
# train recommender
argsDict: Dict[str, str] = {
RecommenderW2V.ARG_ITERATIONS: 50000,
RecommenderW2V.ARG_TRAIN_VARIANT: 'posneg',
RecommenderW2V.ARG_USER_PROFILE_SIZE: -1,
RecommenderW2V.ARG_USER_PROFILE_STRATEGY: 'weightedMean',
RecommenderW2V.ARG_VECTOR_SIZE: 128,
RecommenderW2V.ARG_WINDOW_SIZE: 5
}
rec: ARecommender = RecommenderW2V("RecommenderW2V", argsDict)
rec.train(HistoryDF("test02"), trainDataset)
uDF: DataFrame = DataFrame([eventsDF.iloc[900]])
# print(str(eventsDF.tail(10)))
# print(str(type(uDF)))
rec.update(uDF, {})
r: Series = rec.recommend(1093035, 50, argsDict)
print("Recommendation:")
print(r)
def test03():
print("Test 03")
print("Running RecommenderW2V ST:")
dataset: DatasetST = DatasetST.readDatasets()
trainDataset: DatasetST = dataset
eventsDF: DataFrame = dataset.eventsDF
# train recommender
argsDict: Dict[str, str] = {
RecommenderW2V.ARG_ITERATIONS: 50000,
RecommenderW2V.ARG_TRAIN_VARIANT: 'all',
RecommenderW2V.ARG_USER_PROFILE_SIZE: 5,
RecommenderW2V.ARG_USER_PROFILE_STRATEGY: 'weightedMean',
RecommenderW2V.ARG_VECTOR_SIZE: 32,
RecommenderW2V.ARG_WINDOW_SIZE: 1,
RecommenderW2V.ARG_ALLOWED_ITEMIDS: list(range(0, 1000))
}
rec: ARecommender = RecommenderW2V("RecommenderW2V", argsDict)
rec.train(HistoryDF("test03"), trainDataset)
uDF: DataFrame = DataFrame([eventsDF.iloc[9000]])
print(uDF)
rec.update(uDF, argsDict)
r: Series = rec.recommend(2760420, 50, argsDict)
print(r)
def test01():
print("Test 01")
print("Running RecommenderItemBasedKNN ML:")
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
filmsDF: DataFrame = Items.readFromFileMl1m()
# Take only first 50k
ratingsDFTrain: DataFrame = ratingsDF.iloc[0:50000]
trainDataset: ADataset = DatasetML("test", ratingsDFTrain, pd.DataFrame(),
filmsDF)
# train recommender
rec: ARecommender = RecommenderItemBasedKNN("test", {})
rec.train(HistoryDF("test01"), trainDataset)
# get one rating for update
ratingsDFUpdate: DataFrame = ratingsDF.iloc[50005:50006]
# get recommendations:
print("Recommendations before update")
r: Series = rec.recommend(ratingsDFUpdate['userId'].iloc[0], 50, {})
rec.update(ratingsDFUpdate, {})
print("Recommendations after update")
r: Series = rec.recommend(ratingsDFUpdate['userId'].iloc[0], 50, {})
print("Test for non-existent user:"******"================== END OF TEST 01 ======================\n\n\n\n\n")
def test01():
print("Test 01")
rDescr: RecommenderDescription = RecommenderDescription(
RecommenderTheMostPopular, {})
recommenderID: str = "TheMostPopular"
pDescr: Portfolio1MethDescription = Portfolio1MethDescription(
recommenderID.title(), recommenderID, rDescr)
dataset: ADataset = DatasetST.readDatasets()
history: AHistory = HistoryDF("test")
p: APortfolio = pDescr.exportPortfolio("jobID", history)
portFolioModel: DataFrame = DataFrame()
p.train(history, dataset)
df: DataFrame = DataFrame(
[[1, 555]], columns=[Events.COL_USER_ID, Events.COL_OBJECT_ID])
p.update(ARecommender.UPDT_CLICK, df)
userID: int = 1
r, rp = p.recommend(userID, portFolioModel,
{APortfolio.ARG_NUMBER_OF_AGGR_ITEMS: 20})
print(r)
def test03():
print("Test 03")
print("Running Recommender BPRMF on RR:")
dataset: DatasetRetailRocket = DatasetRetailRocket.readDatasetsWithFilter(
minEventCount=50)
trainDataset: DatasetRetailRocket = dataset
eventsDF: DataFrame = dataset.eventsDF
# train recommender
rec: ARecommender = RecommenderBPRMFImplicit(
"test", {
RecommenderBPRMFImplicit.ARG_FACTORS: 20,
RecommenderBPRMFImplicit.ARG_ITERATIONS: 50,
RecommenderBPRMFImplicit.ARG_LEARNINGRATE: 0.003,
RecommenderBPRMFImplicit.ARG_REGULARIZATION: 0.003
})
rec.train(HistoryDF("test03"), trainDataset)
uDF: DataFrame = DataFrame([eventsDF.iloc[9000]])
print(uDF)
rec.update(uDF, {})
r: Series = rec.recommend(1093035, 50, {})
print("Recommendation:")
print(r)
def test04():
print("Test 04")
print("Running RecommenderVSKNN RR:")
from datasets.retailrocket.events import Events # class
#eventsDF:DataFrame = Events.readFromFile()
eventsDF: DataFrame = Events.readFromFileWithFilter(minEventCount=50)
dataset: ADataset = DatasetRetailRocket("test", eventsDF, DataFrame(),
DataFrame())
rec: ARecommender = RecommenderVMContextKNN("test", {})
print("train")
rec.train(HistoryDF("test"), dataset)
uDF: DataFrame = DataFrame([eventsDF.iloc[9000]])
print(uDF)
rec.update(uDF, {})
recommendation = rec.recommend(1093035, 20, {})
print("Recommendation:")
print(recommendation)
print("================== END OF TEST 04 ======================\n\n\n\n\n")
def evaluate(self, rDscr: RecommenderDescription):
print("StaticEvaluation")
recom: ARecommender = rDscr.exportRecommender("test")
args: dict = rDscr.getArguments()
eventsDF: DataFrame = self.dataset.eventsDF
eventsTrainDF: DataFrame = eventsDF[0:int(len(eventsDF) / 2)]
eventsTestDF: DataFrame = eventsDF[int(len(eventsDF) / 2):]
datasetTrain = DatasetRetailRocket("rrTrain", eventsTrainDF,
DataFrame(), DataFrame())
userIDs: List[int] = list(eventsDF[Events.COL_VISITOR_ID].unique())
recom.train(HistoryDF("test"), datasetTrain)
counter: int = 0
for userIdI in userIDs:
#print("userId: " + str(userIdI))
itemIDs: List[int] = list(
eventsTestDF.loc[eventsTestDF[Events.COL_VISITOR_ID] ==
userIdI][Events.COL_ITEM_ID].unique())
recommendationI: List[int] = recom.recommend(userIdI, 20,
args).keys()
intersectionI: List[int] = [
value for value in itemIDs if value in recommendationI
]
#print(" " + str(len(intersectionI)))
counter += len(intersectionI)
print(" counter: " + str(counter))
def test02():
print("Test 02")
print("Running Recommender BPRMF on ML:")
dataset: DatasetML = DatasetML.readDatasets()
# Take only first 500k
trainDataset: DatasetML = DatasetML("test",
dataset.ratingsDF.iloc[0:800000],
dataset.usersDF, dataset.itemsDF)
print(dataset.ratingsDF.iloc[655924:655926])
# train recommender
rec: ARecommender = RecommenderBPRMFImplicit(
"test", {
RecommenderBPRMFImplicit.ARG_FACTORS: 20,
RecommenderBPRMFImplicit.ARG_ITERATIONS: 50,
RecommenderBPRMFImplicit.ARG_LEARNINGRATE: 0.003,
RecommenderBPRMFImplicit.ARG_REGULARIZATION: 0.003
})
rec.train(HistoryDF("test02"), trainDataset)
# get recommendations:
print("Recommendations before update")
r: Series = rec.recommend(23, 50, {})
print(r)
print("================== END OF TEST 02 ======================\n\n\n\n\n")
def test02():
print("Test 02")
print("Running RecommenderCosineCB RR:")
dataset: DatasetST = DatasetRetailRocket.readDatasets()
args: dict = {
RecommenderCosineCB.ARG_CB_DATA_PATH:
Configuration.cbRRDataFileWithPathOHE,
RecommenderCosineCB.ARG_USER_PROFILE_SIZE: 5,
RecommenderCosineCB.ARG_USER_PROFILE_STRATEGY: "max",
RecommenderCosineCB.ARG_USE_DIVERSITY: False,
} #True
rec: ARecommender = RecommenderCosineCB("test", args)
rec.train(HistoryDF("test"), dataset)
eventsDFDFUpdate: DataFrame = dataset.eventsDF.iloc[5003:5004]
print(eventsDFDFUpdate)
rec.update(eventsDFDFUpdate, args)
# user with very outdated profile - no recent objects
r: Series = rec.recommend(863743, 20, args)
print(type(r))
print(r)
# testing of a non-existent user
r: Series = rec.recommend(10000, 50, args)
print(type(r))
print(r)
def test01():
print("Test 01")
print("Running AggrBanditTSRun:")
# number of recommended items
N = 120
# 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")
}
# print(methodsResultDict)
# methods parametes
methodsParamsData:List[tuple] = [['metoda1', 5, 10, 1, 1], ['metoda2', 5, 12, 1, 1], ['metoda3', 6, 13, 1, 1]]
methodsParamsDF:DataFrame = pd.DataFrame(methodsParamsData, columns=["methodID", "r", "n", "alpha0", "beta0"])
methodsParamsDF.set_index("methodID", inplace=True)
# print(methodsParamsDF)
aggr:AggrBanditTS = AggrBanditTS(HistoryDF(""), {AggrBanditTS.ARG_SELECTOR:RouletteWheelSelector({RouletteWheelSelector.ARG_EXPONENT:1})})
itemIDs:List[tuple] = aggr.runWithResponsibility(methodsResultDict, methodsParamsDF, N)
#itemIDs:List[tuple] = aggr.run(methodsResultDict, methodsParamsDF, N)
print(itemIDs)
def test01():
print("Test 01")
# number of recommended items
N = 120
#a = observationalLinearProbabilityFnc(0.1, 0.9, 5)
#print(a)
uBehaviourDesc: UserBehaviourDescription = UserBehaviourDescription(
observationalLinearProbabilityFnc, [0.1, 0.9])
# method results, items=[1,2,4,5,6,7,8,12,32,64,77]
methodsResultDict: dict[str, pd.Series] = {
"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")
}
#print(methodsResultDict)
# methods parametes
methodsParamsData: List[tuple] = [['metoda1', 100], ['metoda2', 80],
['metoda3', 60]]
methodsParamsDF: DataFrame = pd.DataFrame(methodsParamsData,
columns=["methodID", "votes"])
methodsParamsDF.set_index("methodID", inplace=True)
#print(methodsParamsDF)
userID: int = 0
itemID: int = 7
historyDF: AHistory = HistoryDF("test01")
historyDF.insertRecommendation(userID, itemID, 1, 0.9, True)
historyDF.insertRecommendation(userID, itemID, 1, 0.9, True)
historyDF.insertRecommendation(userID, itemID, 1, 0.9, True)
historyDF.print()
ignoringValue: float = historyDF.getIgnoringValue(userID, itemID, limit=3)
print("IgnoringValue: " + str(ignoringValue))
aggr: AggrDHont = AggrDHontNegativeImplFeedback(
historyDF, {
AggrDHontNegativeImplFeedback.ARG_SELECTORFNC:
(AggrDHontNegativeImplFeedback.selectorOfTheMostVotedItem, []),
AggrDHontNegativeImplFeedback.AGR_LENGTH_OF_HISTORY:
10,
AggrDHontNegativeImplFeedback.AGR_BORDER_NEGATIVE_FEEDBACK:
1.0
})
itemIDs: List[tuple] = aggr.runWithResponsibility(methodsResultDict,
methodsParamsDF, userID,
N)
print(itemIDs)
def test04():
print("Test 04")
print("Running Recommender BPRMF on SL:")
from datasets.slantour.events import Events # class
dataset: DatasetST = DatasetST.readDatasets()
trainDataset: DatasetST = dataset
eventsDF: DataFrame = dataset.eventsDF
uIDMax: int = eventsDF[Events.COL_USER_ID].max()
print("uIDMax: " + str(uIDMax))
iIDMax: int = eventsDF[Events.COL_OBJECT_ID].max()
print("iIDMax: " + str(iIDMax))
# train recommender
rec: ARecommender = RecommenderBPRMFImplicit(
"test", {
RecommenderBPRMFImplicit.ARG_FACTORS: 20,
RecommenderBPRMFImplicit.ARG_ITERATIONS: 50,
RecommenderBPRMFImplicit.ARG_LEARNINGRATE: 0.003,
RecommenderBPRMFImplicit.ARG_REGULARIZATION: 0.003
})
rec.train(HistoryDF("test04"), trainDataset)
uDF1: DataFrame = DataFrame([eventsDF.iloc[9000]])
print(uDF1)
rec.update(uDF1, {})
userID1: int = uIDMax + 1
itemID1: int = iIDMax + 1
itemID2: int = iIDMax + 2
# update with unknown user and unknown item
uDF2: DataFrame = DataFrame(
columns=[Events.COL_USER_ID, Events.COL_OBJECT_ID])
uDF2.loc[0] = [userID1, itemID1]
print(uDF2)
rec.update(uDF2, {})
# update with unknown item
uDF3: DataFrame = DataFrame(
columns=[Events.COL_USER_ID, Events.COL_OBJECT_ID])
uDF3.loc[0] = [userID1, itemID2]
print(uDF3)
rec.update(uDF3, {})
r: Series = rec.recommend(23, 50, {})
print(r)
print()
# recommend for unknown user
r: Series = rec.recommend(userID1, 50, {})
print(r)
def test01():
print("Test 01")
# number of recommended items
N = 120
#a = observationalLinearProbabilityFnc(0.1, 0.9, 5)
#print(a)
uBehaviourDesc: UserBehaviourDescription = UserBehaviourDescription(
observationalLinearProbabilityFnc, [0.1, 0.9])
# method results, items=[1,2,4,5,6,7,8,12,32,64,77]
methodsResultDict: dict[str, pd.Series] = {
"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")
}
#print(methodsResultDict)
# methods parametes
methodsParamsData: List[tuple] = [['metoda1', 100], ['metoda2', 80],
['metoda3', 60]]
methodsParamsDF: DataFrame = pd.DataFrame(methodsParamsData,
columns=["methodID", "votes"])
methodsParamsDF.set_index("methodID", inplace=True)
#print(methodsParamsDF)
userID: int = 0
itemID: int = 7
historyDF: AHistory = HistoryDF("test01")
historyDF.insertRecommendation(userID, itemID, 1, True, None)
historyDF.insertRecommendation(userID, itemID, 1, True, None)
historyDF.insertRecommendation(userID, itemID, 1, True, None)
historyDF.print()
#ignoringValue:float = historyDF.getIgnoringValue(userID, itemID, limit=3)
#print("IgnoringValue: " + str(ignoringValue))
penalization: APenalization = PenalUsingReduceRelevance(
penaltyLinear, [0.8, 0.2, 3], penaltyLinear, [1.0, 0.2, 3], 3)
aggr: AggrFuzzyDHondt = AggrFuzzyDHondtINF(
historyDF, {
AggrFuzzyDHondtINF.ARG_SELECTOR: TheMostVotedItemSelector({}),
AggrFuzzyDHondtINF.ARG_PENALTY_TOOL: penalization
})
itemIDs: List[tuple] = aggr.runWithResponsibility(methodsResultDict,
methodsParamsDF, userID,
N)
print(itemIDs)
def test02():
print("Test 02")
methodsResultDict: dict[str, pd.Series] = {
"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")
}
print(methodsResultDict)
print()
userID: int = 0
itemID: int = 1
historyDF: AHistory = HistoryDF("test01")
historyDF.insertRecommendation(userID, itemID, 0, 0.9, False)
historyDF.insertRecommendation(userID, itemID, 0, 0.9, False)
historyDF.insertRecommendation(userID, itemID, 0, 0.9, False)
#historyDF.print()
###################
maxPenaltyValue: float = 1.2
minPenaltyValue: float = 0.2
lengthOfHistory: int = 5
p = PenalizationOfResultsByNegImpFeedbackUsingReduceRelevance(
historyDF, maxPenaltyValue, minPenaltyValue, lengthOfHistory)
methodsResultDict: dict[str, pd.Series] = p.proportionalRelevanceReduction(
methodsResultDict, userID)
print("methodsResultDict")
print(methodsResultDict)
###################
i: int = 2
maxPenaltyValue: float = 1.2
minPenaltyValue: float = 0.2
lengthOfHistory: int = 5
value: float = PenalizationOfResultsByNegImpFeedbackUsingReduceRelevance.getPenaltyLinear2(
i, maxPenaltyValue, minPenaltyValue, lengthOfHistory)
print("value: " + str(value))
###################
minTimeDiff: float = 1.0
maxTimeDiff: float = 1.5
minPenalty: float = 0.0
maxPenalty: float = 1.0
timeDiff: float = minTimeDiff + 0.25
value: float = PenalizationOfResultsByNegImpFeedbackUsingReduceRelevance.getPenaltyLinear(
timeDiff, minTimeDiff, maxTimeDiff, minPenalty, maxPenalty)
print("value: " + str(value))
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 test21():
print("Simulation: ST ContextDHondtINF")
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()
dataset: ADataset = DatasetST.readDatasets()
events = dataset.eventsDF
serials = dataset.serialsDF
historyDF: AHistory = HistoryDF("test01")
# Init evalTool
evalTool: AEvalTool = EvalToolContext({
EvalToolContext.ARG_ITEMS:
serials, # ITEMS
EvalToolContext.ARG_EVENTS:
events, # EVENTS (FOR CALCULATING HISTORY OF USER)
EvalToolContext.ARG_DATASET:
"st", # WHAT DATASET ARE WE IN
EvalToolContext.ARG_HISTORY:
historyDF
}) # empty instance of AHistory is OK for ST dataset
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"ContextDHondtNIF" + jobID, rIDs, rDescs,
InputAggrDefinition.exportADescDContextHondtINF(
selector, pToolOLin0802HLin1002, evalTool))
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)
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationST, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [model], [evalTool],
[HistoryHierDF(pDescr.getPortfolioID())])
def test01():
print("Test 01")
print("Running RecommenderRepeatedPurchase RR:")
from datasets.retailrocket.events import Events # class
#eventsDF:DataFrame = Events.readFromFile()
eventsDF: DataFrame = Events.readFromFileWithFilter(minEventCount=50)
#print(eventsDF)
userID: int = 904351
trainSer = pd.Series(
[1433221523348, userID, Events.EVENT_ADDTOCART, 350688, "Nan"],
index=[
Events.COL_TIME_STAMP, Events.COL_VISITOR_ID, Events.COL_EVENT,
Events.COL_ITEM_ID, Events.EVENT_TRANSACTION
])
trainDF = pd.DataFrame([trainSer])
dataset: ADataset = DatasetRetailRocket("test", eventsDF, DataFrame(),
DataFrame())
rec: ARecommender = RecommenderRepeatedPurchase("rRepeatedPurchase", {})
rec.train(HistoryDF("test"), dataset)
# nejcasteji opakovane kupovane itemy: 119736, 119736, 119736, 213834, 119736, 227311, 382885, 119736, 213834, 119736, 432171, 183756, 119736, 305675, 320130
update1Ser = pd.Series(
[1433221523348, userID, Events.EVENT_ADDTOCART, 119736, "Nan"],
index=[
Events.COL_TIME_STAMP, Events.COL_VISITOR_ID, Events.COL_EVENT,
Events.COL_ITEM_ID, Events.EVENT_TRANSACTION
])
update1DF: DataFrame = pd.DataFrame([update1Ser])
update2Ser = pd.Series(
[1433221523348, userID, Events.EVENT_ADDTOCART, 213834, "Nan"],
index=[
Events.COL_TIME_STAMP, Events.COL_VISITOR_ID, Events.COL_EVENT,
Events.COL_ITEM_ID, Events.EVENT_TRANSACTION
])
update2DF: DataFrame = pd.DataFrame([update2Ser])
rec.update(update1DF, {})
rec.update(update2DF, {})
recommendationSer: Series = rec.recommend(userID, 20, {})
print("Recommendation:")
print(recommendationSer)
def test01():
print("Test 01")
print("Running Recommender BPRMF on ML:")
dataset: DatasetML = DatasetML.readDatasets()
# Take only first 500k
trainDataset: DatasetML = DatasetML("test",
dataset.ratingsDF.iloc[0:499965],
dataset.usersDF, dataset.itemsDF)
# train recommender
rec: ARecommender = RecommenderBPRMFImplicit(
"test", {
RecommenderBPRMFImplicit.ARG_FACTORS: 20,
RecommenderBPRMFImplicit.ARG_ITERATIONS: 50,
RecommenderBPRMFImplicit.ARG_LEARNINGRATE: 0.003,
RecommenderBPRMFImplicit.ARG_REGULARIZATION: 0.003
})
rec.train(HistoryDF("test01"), trainDataset)
# get one rating for update
ratingsDFUpdate: DataFrame = dataset.ratingsDF.iloc[499965:503006]
# get recommendations:
print("Recommendations before update")
print(rec._movieFeaturesMatrixLIL[:, ratingsDFUpdate['userId'].iloc[0]].
getnnz())
r: Series = rec.recommend(ratingsDFUpdate['userId'].iloc[0], 50, {})
print(r)
for i in range(ratingsDFUpdate.shape[0]):
rUp = ratingsDFUpdate.iloc[i:i + 1, :]
rec.update(rUp, {})
print("Recommendations after update")
print(rec._movieFeaturesMatrixLIL[:, ratingsDFUpdate['userId'].iloc[0]].
getnnz())
r: Series = rec.recommend(ratingsDFUpdate['userId'].iloc[0], 50, {})
print(r)
print("Test for non-existent user:"******"================== END OF TEST 01 ======================\n\n\n\n\n")
def test03():
print("Test 03")
print("Running RecommenderVSKNN ST:")
dataset: DatasetST = DatasetST.readDatasets()
testD = dataset.eventsDF.iloc[4000:10000]
dataset.eventsDF = dataset.eventsDF.iloc[0:4000]
# train recommender
rec: ARecommender = RecommenderVMContextKNN("test", {})
start = time.time()
rec.train(HistoryDF("test03"), dataset)
end = time.time()
print("Time to train: " + str(end - start))
i = 0
"""
maxI = 5990
while i < maxI:
eventsDFDFUpdate:DataFrame = dataset.eventsDF.iloc[i:i+1]
rec.update(rec.UPDT_CLICK, eventsDFDFUpdate)
i = i+1
if i%100 == 0:
print(i)
"""
r: Series = rec.recommend(3342336, 20,
{rec.ARG_ALLOWED_ITEMIDS: list(range(0, 1000))})
print(type(r))
print(r)
r: Series = rec.recommend(2035310, 20,
{rec.ARG_ALLOWED_ITEMIDS: list(range(0, 1000))})
print(type(r))
print(r)
r: Series = rec.recommend(3342341, 20,
{rec.ARG_ALLOWED_ITEMIDS: list(range(0, 1000))})
print(type(r))
print(r)
# testing of a non-existent user
r: Series = rec.recommend(10000, 50,
{rec.ARG_ALLOWED_ITEMIDS: list(range(0, 1000))})
print(type(r))
print(r)
print("================== END OF TEST 03 ======================\n\n\n\n\n")
def test03():
print("Test 03")
# userID: 23
# currentItemID: 196
# repetition: 0
print("Running RecommenderItemBasedKNN ML:")
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
ratingsSortedDF: DataFrame = ratingsDF.sort_values(
by=Ratings.COL_TIMESTAMP)
filmsDF: DataFrame = Items.readFromFileMl1m()
print(len(ratingsSortedDF))
ratingsDFTrain: DataFrame = ratingsSortedDF[0:900000]
ratingsDFTrain: DataFrame = ratingsDFTrain[
ratingsDFTrain[Ratings.COL_USERID] != 23]
ratingsDFTrain: DataFrame = ratingsDFTrain[
ratingsDFTrain[Ratings.COL_MOVIEID] != 10]
print(ratingsDFTrain.head(25))
trainDataset: ADataset = DatasetML("test", ratingsDFTrain, pd.DataFrame(),
filmsDF)
# train recommender
rec: ARecommender = RecommenderItemBasedKNN("test1", {})
rec.train(HistoryDF("test03"), trainDataset)
uDdata = [[23, 10, 4, 10000]]
uDF: DataFrame = pd.DataFrame(uDdata,
columns=[
Ratings.COL_USERID, Ratings.COL_MOVIEID,
Ratings.COL_RATING, Ratings.COL_TIMESTAMP
])
rec.update(uDF, {})
r: Series = rec.recommend(23, 10, {})
print(r)
print("\n")
r: Series = rec.recommend(23, 10, {})
print(r)
print("================== END OF TEST 03 ======================\n\n\n\n\n")
def test03():
print("Test 03")
print("Running RecommenderTheMostPopular ST:")
from datasets.slantour.events import Events # class
eventsDF: DataFrame = Events.readFromFile()
dataset: ADataset = DatasetST("test", eventsDF, DataFrame())
rec: ARecommender = RecommenderTheMostPopular("rTheMostPopular", {})
rec.train(HistoryDF("test"), dataset)
recommendation = rec.recommend(
1, 20, {rec.ARG_ALLOWED_ITEMIDS: list(range(0, 1000))})
print(recommendation)
def run(self, batchID: str, jobID: str):
divisionDatasetPercentualSize: int
uBehaviour: str
repetition: int
divisionDatasetPercentualSize, uBehaviour, repetition = InputABatchDefinition(
).getBatchParameters(self.datasetID)[batchID]
selector: ADHondtSelector = self.getParameters()[jobID]
portfolioID: str = self.getBatchName() + jobID
history: AHistory = HistoryHierDF(portfolioID)
dataset: ADataset = DatasetST.readDatasets()
events = dataset.eventsDF
serials = dataset.serialsDF
historyDF: AHistory = HistoryDF("test01")
# Init evalTool
evalTool: AEvalTool = EvalToolContext({
EvalToolContext.ARG_ITEMS:
serials, # ITEMS
EvalToolContext.ARG_EVENTS:
events, # EVENTS (FOR CALCULATING HISTORY OF USER)
EvalToolContext.ARG_DATASET:
"st", # WHAT DATASET ARE WE IN
EvalToolContext.ARG_HISTORY:
historyDF
}) # empty instance of AHistory is OK for ST dataset
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs(
)
aDescContextDHont: AggregationDescription = InputAggrDefinition.exportADescDContextHondt(
selector, evalTool)
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
portfolioID, rIDs, rDescs, aDescContextDHont)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
simulator: Simulator = InputSimulatorDefinition(
).exportSimulatorSlantour(batchID, divisionDatasetPercentualSize,
uBehaviour, repetition)
simulator.simulate([pDescr], [model], [evalTool], [history])
def test22():
print("Test 22")
print("Running RecommenderItemBasedKNN ST:")
from datasets.slantour.events import Events # class
userID1: int = 1
userID2: int = 2
userID3: int = 3
trainEventsDF: DataFrame = DataFrame(
columns=[Events.COL_USER_ID, Events.COL_OBJECT_ID])
trainEventsDF.loc[0] = [userID1, 101]
trainEventsDF.loc[1] = [userID1, 102]
trainEventsDF.loc[2] = [userID1, 103]
trainEventsDF.loc[3] = [userID1, 104]
trainEventsDF.loc[4] = [userID2, 101]
trainEventsDF.loc[5] = [userID2, 102]
print(trainEventsDF.head(10))
trainDataset: ADataset = DatasetST("test", trainEventsDF, DataFrame())
rec: ARecommender = RecommenderItemBasedKNN("test", {})
rec.train(HistoryDF("test"), trainDataset)
print("update 1:")
updateEvents1DF: DataFrame = DataFrame(columns=trainEventsDF.columns)
updateEvents1DF.loc[0] = [userID1, 105]
print(updateEvents1DF.head())
rec.update(updateEvents1DF, {})
print("update 2:")
updateEvents2DF: DataFrame = DataFrame(columns=trainEventsDF.columns)
updateEvents2DF.loc[0] = [userID3, 106]
print(updateEvents2DF.head())
rec.update(updateEvents2DF, {})
print("recommend:")
r = rec.recommend(userID2, 10, {})
print(r)
print("================== END OF TEST 06 ======================\n\n\n\n\n")
def test02():
print("Test 02")
print("Running RecommenderTheMostPopular RR:")
from datasets.retailrocket.events import Events # class
#eventsDF:DataFrame = Events.readFromFile()
eventsDF: DataFrame = Events.readFromFileWithFilter(minEventCount=50)
dataset: ADataset = DatasetRetailRocket("test", eventsDF, DataFrame(),
DataFrame())
rec: ARecommender = RecommenderTheMostPopular("rTheMostPopular", {})
rec.train(HistoryDF("test"), dataset)
recommendation = rec.recommend(1, 20, {})
print("Recommendation:")
print(recommendation)
