def divideDataset(dataset: ADataset, behaviourDF: DataFrame,
divisionDatasetPercentualSize: int,
testDatasetPercentualSize: int,
recomRepetitionCount: int):
eventsDF: DataFrame = dataset.eventsDF
serialsDF: DataFrame = dataset.serialsDF
# create train Dataset
eventsSortedDF: DataFrame = eventsDF #.sort_values(by=Events.COL_TIME_STAMP)
numberOfEvents: int = eventsSortedDF.shape[0]
trainSize: int = (int)(numberOfEvents * divisionDatasetPercentualSize /
100)
#print("trainSize: " + str(trainSize))
trainEventsDF: DataFrame = eventsSortedDF[0:trainSize]
datasetID: str = "st" + "Div" + str(divisionDatasetPercentualSize)
trainDataset: ADataset = DatasetST(datasetID, trainEventsDF, serialsDF)
# create test Event DataFrame
testSize: int = (int)(numberOfEvents * testDatasetPercentualSize / 100)
#print("testSize: " + str(testSize))
testEventsPartDF: DataFrame = eventsSortedDF[trainSize:(trainSize +
testSize)]
testEventsDF: DataFrame = testEventsPartDF.loc[
testEventsPartDF[Events.COL_OBJECT_ID] != 0]
# create test relevant Event DataFrame
testRelevantEventsDF: DataFrame = testEventsDF
# create behaviour dictionary of DataFrame indexed by recomRepetition
recomRepetitionCountInDataset: int = behaviourDF[
BehavioursST.COL_REPETITION].max() + 1
testRepeatedBehaviourDict: dict = {}
bIndexes: List[int] = list(
[recomRepetitionCountInDataset * i for i in testEventsDF.index])
for repetitionI in range(recomRepetitionCount):
# indexes of behaviour
indexes: List[int] = [vI + repetitionI for vI in bIndexes]
behaviourDFI: DataFrame = DataFrame(
behaviourDF.take(indexes).values.tolist(),
index=testEventsDF.index,
columns=behaviourDF.keys())
testRepeatedBehaviourDict[repetitionI] = behaviourDFI
return (trainDataset, testEventsDF, testRelevantEventsDF,
testRepeatedBehaviourDict)
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 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 test21():
print("Test 21")
print("Running RecommenderItemBasedKNN ST:")
from datasets.slantour.events import Events # class
eventsDF: DataFrame = Events.readFromFile()
dataset: ADataset = DatasetST("test", eventsDF, DataFrame())
rec: ARecommender = RecommenderItemBasedKNN("test", {})
rec.train(HistoryDF("test"), dataset)
uDF: DataFrame = DataFrame([eventsDF.iloc[9000]])
print(uDF)
rec.update(uDF, {})
r = rec.recommend(3325463, 20, {})
print(r)
print("================== END OF TEST 05 ======================\n\n\n\n\n")