def exportPairOfRecomIdsAndRecomDescrsCluster(cls):
recom: str = "Recom" + "Cluster"
rIds: List[str] = []
rDescs: List[RecommenderDescription] = []
for gIdI in range(0, len(Items.getAllGenres())):
genreI: str = Items.getAllGenres()[gIdI]
rIds.append(recom + genreI)
rDescs.append(cls.exportRDescClusterBased(gIdI))
return (rIds, rDescs)
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]
itemsDF:DataFrame = Items.readFromFileMl1m()
usersDF:DataFrame = Users.readFromFileMl1m()
historyDF:AHistory = HistoryHierDF("test01")
eTool:AEvalTool = EvalToolContext({
EvalToolContext.ARG_USERS: usersDF,
EvalToolContext.ARG_ITEMS: itemsDF,
EvalToolContext.ARG_DATASET: "ml",
EvalToolContext.ARG_HISTORY: historyDF})
rIDs, rDescs = InputRecomMLDefinition.exportPairOfRecomIdsAndRecomDescrs()
aDescDHont:AggregationDescription = InputAggrDefinition.exportADescContextFuzzyDHondtDirectOptimize(selector, eTool)
pDescr:Portfolio1AggrDescription = Portfolio1AggrDescription(
self.getBatchName() + jobID, rIDs, rDescs, aDescDHont)
model:DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
simulator:Simulator = InputSimulatorDefinition().exportSimulatorML1M(
batchID, divisionDatasetPercentualSize, uBehaviour, repetition)
simulator.simulate([pDescr], [model], [eTool], [HistoryHierDF(pDescr.getPortfolioID())])
def exportSimulatorML1M(batchID: str, divisionDatasetPercentualSize: int,
uBehaviourID: str, repetition: int):
argsSimulationDict: dict = {
SimulationPortfolioToUser.ARG_WINDOW_SIZE:
5,
SimulationPortfolioToUser.ARG_REPETITION_OF_RECOMMENDATION:
repetition,
SimulationPortfolioToUser.ARG_NUMBER_OF_RECOMM_ITEMS:
100,
SimulationPortfolioToUser.ARG_NUMBER_OF_AGGR_ITEMS:
InputSimulatorDefinition.numberOfAggrItems,
SimulationPortfolioToUser.ARG_DIV_DATASET_PERC_SIZE:
divisionDatasetPercentualSize
}
# dataset reading
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
usersDF: DataFrame = Users.readFromFileMl1m()
itemsDF: DataFrame = Items.readFromFileMl1m()
behaviourFile: str = Behaviours.getFile(uBehaviourID)
behavioursDF: DataFrame = Behaviours.readFromFileMl1m(behaviourFile)
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationPortfolioToUser,
argsSimulationDict, ratingsDF,
usersDF, itemsDF, behavioursDF)
return simulator
def readDatasets():
# dataset reading
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
usersDF: DataFrame = Users.readFromFileMl1m()
itemsDF: DataFrame = Items.readFromFileMl1m()
return DatasetML("ml1mDivAll", ratingsDF, usersDF, itemsDF)
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 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 test01():
print("Simulation: ML ContextDHondtINF")
jobID: str = "Roulette1"
selector = RouletteWheelSelector({RouletteWheelSelector.ARG_EXPONENT: 1})
#pProbToolOLin0802HLin1002:APenalization = PenalizationToolDefinition.exportProbPenaltyToolOStat08HLin1002(
# InputSimulatorDefinition.numberOfAggrItems)
pToolOLin0802HLin1002: APenalization = PenalizationToolDefinition.exportPenaltyToolOLin0802HLin1002(
InputSimulatorDefinition.numberOfAggrItems)
itemsDF: DataFrame = Items.readFromFileMl1m()
usersDF: DataFrame = Users.readFromFileMl1m()
historyDF: AHistory = HistoryDF("test01")
eTool: AEvalTool = EvalToolContext({
EvalToolContext.ARG_USERS: usersDF,
EvalToolContext.ARG_ITEMS: itemsDF,
EvalToolContext.ARG_DATASET: "ml",
EvalToolContext.ARG_HISTORY: historyDF
})
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs()
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"ContextDHondtINF" + jobID, rIDs, rDescs,
InputAggrDefinition.exportADescDContextHondtINF(
selector, pToolOLin0802HLin1002, eTool))
batchID: str = "ml1mDiv90Ulinear0109R1"
dataset: DatasetML = DatasetML.readDatasets()
behaviourFile: str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF: DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationML, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [model], [eTool],
[HistoryHierDF(pDescr.getPortfolioID())])
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[0:800000]
trainDataset: ADataset = DatasetML("test", ratingsDFTrain, pd.DataFrame(),
filmsDF)
# train recommender
rec: ARecommender = RecommenderVMContextKNN("test", {})
start = time.time()
rec.train(HistoryDF("test01"), trainDataset)
end = time.time()
print("Time to train: " + str(end - start))
# get one rating for update
ratingsDFUpdate: DataFrame = ratingsDF.iloc[800006:800007]
# get recommendations:
print("Recommendations before update")
start = time.time()
r: Series = rec.recommend(ratingsDFUpdate['userId'].iloc[0], 50, {})
end = time.time()
print("Time to train: " + str(end - start))
rec.update(ARecommender.UPDT_CLICK, 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 train(self, history:AHistory, dataset: ADataset):
if not isinstance(history, AHistory):
raise ValueError("Argument history isn't type AHistory.")
if not isinstance(dataset, ADataset):
raise ValueError("Argument dataset isn't type ADataset.")
self.trainDataset = dataset
if type(dataset) is DatasetML:
from datasets.ml.items import Items #class
allGenres:List[str] = Items.getAllGenres()
self._sortedAscRatings4CountDF:DataFrame = dataset.getTheMostPopularOfGenre(
allGenres[self.recommenderNumericId])
elif type(dataset) is DatasetRetailRocket:
self._sortedAsceventsTransCountDF:DataFrame = dataset.getTheMostSold()
elif type(dataset) is DatasetST:
self._sortedTheMostCommon = dataset.getTheMostSold()
else:
raise ValueError("Argument dataset isn't of expected type.")
def test02():
print("Test 02")
print("Running RecommenderItemBasedKNN ML:")
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
filmsDF: DataFrame = Items.readFromFileMl1m()
ratingsDFTrain: DataFrame = ratingsDF.iloc[0:1000000]
trainDataset: ADataset = DatasetML("test", ratingsDFTrain, pd.DataFrame(),
filmsDF)
# train recommender
rec: ARecommender = RecommenderItemBasedKNN("test", {})
rec.train(HistoryDF("test02"), trainDataset)
r: Series = rec.recommend(1, 50, {})
print(r)
print("================== END OF TEST 02 ======================\n\n\n\n\n")
def test01():
print("Simulation: ML ContextFuzzyDHondtDirectOptimize")
jobID: str = "Roulette1"
selector: ADHondtSelector = RouletteWheelSelector(
{RouletteWheelSelector.ARG_EXPONENT: 1})
itemsDF: DataFrame = Items.readFromFileMl1m()
usersDF: DataFrame = Users.readFromFileMl1m()
historyDF: AHistory = HistoryHierDF("test01")
eTool: AEvalTool = EvalToolContext({
EvalToolContext.ARG_USERS: usersDF,
EvalToolContext.ARG_ITEMS: itemsDF,
EvalToolContext.ARG_DATASET: "ml",
EvalToolContext.ARG_HISTORY: historyDF
})
rIDs, rDescs = InputRecomSTDefinition.exportPairOfRecomIdsAndRecomDescrs()
pDescr: Portfolio1AggrDescription = Portfolio1AggrDescription(
"ContextFuzzyDHondtDirectOptimize" + jobID, rIDs, rDescs,
InputAggrDefinition.exportADescContextFuzzyDHondtDirectOptimize(
selector, eTool))
batchID: str = "ml1mDiv90Ulinear0109R1"
dataset: DatasetML = DatasetML.readDatasets()
behaviourFile: str = BehavioursML.getFile(BehavioursML.BHVR_LINEAR0109)
behavioursDF: DataFrame = BehavioursML.readFromFileMl1m(behaviourFile)
model: DataFrame = PModelDHondt(pDescr.getRecommendersIDs())
# simulation of portfolio
simulator: Simulator = Simulator(batchID, SimulationML, argsSimulationDict,
dataset, behavioursDF)
simulator.simulate([pDescr], [model], [eTool], [historyDF])
def test02(repetitions=1):
N = 100
# get dataset
itemsDF: DataFrame = Items.readFromFileMl1m()
usersDF: DataFrame = Users.readFromFileMl1m()
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
ratingsDFTrain = ratingsDF[:50000]
ratingsDFUpdate: DataFrame = ratingsDF.iloc[50001:50100]
trainDataset: ADataset = DatasetML("ml", ratingsDFTrain, usersDF, itemsDF)
historyDF: AHistory = HistoryDF("test01")
# train KNN
rec1: ARecommender = RecommenderItemBasedKNN("run", {})
rec1.train(HistoryDF("test01"), trainDataset)
# train Most Popular
rec2: ARecommender = RecommenderTheMostPopular("run", {})
rec2.train(historyDF, trainDataset)
# methods parametes
methodsParamsData: List[tuple] = [['ItembasedKNN', 0.4],
['MostPopular', 0.6]]
methodsParamsDF: DataFrame = pd.DataFrame(methodsParamsData,
columns=["methodID", "votes"])
methodsParamsDF.set_index("methodID", inplace=True)
userID = 352
ratingsDFuserID = ratingsDF[ratingsDF['userId'] == userID]
itemID = ratingsDFuserID.iloc[0]['movieId']
historyDF: AHistory = HistoryDF("test01")
historyDF.insertRecommendation(userID, itemID, 1, True, 10)
r1: Series = rec1.recommend(userID, N, {})
r2: Series = rec2.recommend(userID, N, {})
methodsResultDict: dict = {"ItembasedKNN": r1, "MostPopular": r2}
evaluationDict: dict = {
EvalToolContext.ARG_USER_ID: userID,
EvalToolContext.ARG_RELEVANCE: methodsResultDict
}
evalToolDHondt = EvalToolContext({
EvalToolContext.ARG_USERS: usersDF,
EvalToolContext.ARG_ITEMS: itemsDF,
EvalToolContext.ARG_DATASET: "ml",
EvalToolContext.ARG_HISTORY: historyDF
})
aggr: AggrContextFuzzyDHondt = AggrContextFuzzyDHondt(
historyDF, {
AggrContextFuzzyDHondt.ARG_EVAL_TOOL: evalToolDHondt,
AggrContextFuzzyDHondt.ARG_SELECTOR: TheMostVotedItemSelector({})
})
aggrInit: AggrFuzzyDHondt = AggrFuzzyDHondt(
historyDF,
{AggrFuzzyDHondt.ARG_SELECTOR: TheMostVotedItemSelector({})})
l1 = aggrInit.runWithResponsibility(methodsResultDict, methodsParamsDF,
userID, N)
import random
print("l1:" + str(l1))
evalToolDHondt.displayed(l1, methodsParamsDF, evaluationDict)
evalToolDHondt.click(l1,
random.choice(l1)[0], methodsParamsDF, evaluationDict)
timestamp = 10
counter = 0
r1c = 0
r2c = 0
for _ in range(repetitions):
for index, row in ratingsDFuserID.iterrows():
r1: Series = rec1.recommend(userID, N, {})
r2: Series = rec2.recommend(userID, N, {})
methodsResultDict: dict = {"ItembasedKNN": r1, "MostPopular": r2}
evalDict = {"a": 1}
historyDF.insertRecommendation(userID, row['movieId'], 1, True,
timestamp)
timestamp += 1
l1 = aggr.runWithResponsibility(methodsResultDict,
methodsParamsDF,
userID,
argumentsDict=evalDict,
numberOfItems=N)
import random
randomItem = random.choice(l1)[0]
if randomItem in r1.index:
r1c += 1
if randomItem in r2.index:
r2c += 1
evaluationDict: dict = {
EvalToolContext.ARG_USER_ID: userID,
EvalToolContext.ARG_RELEVANCE: methodsResultDict
}
print("votes Items: ", r1c)
print("votes mostPopular ", r2c)
evalToolDHondt.displayed(l1, methodsParamsDF, evaluationDict)
evalToolDHondt.click(l1, randomItem, methodsParamsDF,
evaluationDict)
rec1.update(ratingsDFuserID.loc[[index]], {})
# rec2.update(ratingsDFuserID.loc[index]) Not implemented
#print("Counter = ", counter, "; All = ", len(ratingsDFuserID.iloc[800:]), "; Index: ", index)
print(methodsParamsDF)
counter += 1
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 = [['metoda1', 100], ['metoda2', 80], ['metoda3', 60]]
portfolioModelDF: DataFrame = pd.DataFrame(portfolioModelData,
columns=["methodID", "votes"])
portfolioModelDF.set_index("methodID", inplace=True)
itemsDF: DataFrame = Items.readFromFileMl1m()
usersDF: DataFrame = Users.readFromFileMl1m()
print("Definition:")
print(portfolioModelDF)
print(sumMethods(portfolioModelDF))
print()
userID = 1
itemID = 2
historyDF: AHistory = HistoryDF("test01")
historyDF.insertRecommendation(userID, itemID, 1, True, 10)
historyDF.insertRecommendation(userID, itemID, 1, True, 20)
historyDF.insertRecommendation(userID, itemID, 1, True, 30)
historyDF.insertRecommendation(userID, itemID, 1, False, 40)
evaluationDict: dict = {
EvalToolContext.ARG_USER_ID: userID,
EvalToolContext.ARG_RELEVANCE: methodsResultDict
}
evalToolDHondt = EvalToolContext({
EvalToolContext.ARG_USERS: usersDF,
EvalToolContext.ARG_ITEMS: itemsDF,
EvalToolContext.ARG_DATASET: "ml",
EvalToolContext.ARG_HISTORY: historyDF
})
print("Clicked:")
#print("rItemIDsWithResponsibility: " + str(rItemIDsWithResponsibility))
evalToolDHondt.click(rItemIDsWithResponsibility, 7, portfolioModelDF,
evaluationDict)
evalToolDHondt.click(rItemIDsWithResponsibility, 1, portfolioModelDF,
evaluationDict)
evalToolDHondt.click(rItemIDsWithResponsibility, 7, portfolioModelDF,
evaluationDict)
print(portfolioModelDF)
print(sumMethods(portfolioModelDF))
print()
print("Displayed - start:")
for i in range(100):
print("rItemIDsWithResponsibility: " + str(rItemIDsWithResponsibility))
evalToolDHondt.displayed(rItemIDsWithResponsibility, portfolioModelDF,
evaluationDict)
print(portfolioModelDF)
print(sumMethods(portfolioModelDF))
print()
print(portfolioModelDF)
print(sumMethods(portfolioModelDF))
print("Displayed - end:")
print()
print("Clicked:")
evalToolDHondt.click(rItemIDsWithResponsibility, 4, portfolioModelDF,
evaluationDict)
print(portfolioModelDF)
print(sumMethods(portfolioModelDF))
print()
modelOfUserI: DataFrame = modelDF.getModel(float('nan'))
modelOfUserI: DataFrame = modelDF.getModel(userID)
print(modelOfUserI.head(25))
print(list(modelDF.index))
ratingsDF: DataFrame = Ratings.readFromFileMl1m()
#print(ratingsDF.head())
ratingsOfuser: DataFrame = ratingsDF[ratingsDF[Ratings.COL_USERID] ==
userID]
itemIds: List[int] = ratingsOfuser[Ratings.COL_MOVIEID].tolist()
#print(itemIds)
itemsDF: DataFrame = Items.readFromFileMl1m()
r = Items.countA(itemsDF, itemIds)
print(r)
#from matplotlib import pyplot as plt
#from matplotlib import font_manager as fm
# make a square figure and axes
#fig = plt.figure(1, figsize=(6, 6), dpi=50)
#ax = fig.add_axes([0.16, 0.16, 0.68, 0.68])
#plt.title("Scripting languages")
#ax.title.set_fontsize(30)
# vytvoření koláčového grafu
#ax.pie(r.values(), labels=r.keys(), autopct='%1.1f%%', shadow=True)