def test02():
print("Test 02")
eventsDF: DataFrame = Events.readFromFile()
ratings4DF: DataFrame = eventsDF[[
Events.COL_VISITOR_ID, Events.COL_ITEM_ID, Events.COL_EVENT
]]
ratings4DF = ratings4DF.drop_duplicates()
ratings4DF.loc[ratings4DF[Events.COL_EVENT] == "view", "rating"] = 1
ratings4DF.loc[ratings4DF[Events.COL_EVENT] == "addtocart", "rating"] = 2
ratings4DF.loc[ratings4DF[Events.COL_EVENT] == "transaction", "rating"] = 3
ratingsDF: DataFrame = ratings4DF[[
Events.COL_VISITOR_ID, Events.COL_ITEM_ID, "rating"
]]
ratingsDF = ratingsDF.groupby([Events.COL_VISITOR_ID, Events.COL_ITEM_ID],
as_index=False)["rating"].max()
print(ratingsDF.head(40))
print(len(eventsDF))
print(len(ratingsDF))
def generateFileRR(numberOfItems: int, countOfRepetitions: int,
behaviourID: str, uBehavDesc: UserBehaviourDescription):
np.random.seed(42)
random.seed(42)
print("Generate Behaviour RR " + behaviourID)
behaviourFile: str = BehavioursRR.getFile(behaviourID)
eventsDF: DataFrame = Events.readFromFile()
eventsCopyDF: DataFrame = eventsDF[[
Events.COL_VISITOR_ID, Events.COL_ITEM_ID
]].copy()
eventsCopyDF[BehavioursRR.COL_REPETITION] = [
range(countOfRepetitions)
] * len(eventsCopyDF)
behavioursDF: DataFrame = eventsCopyDF.explode(
BehavioursRR.COL_REPETITION)
behavioursDF[BehavioursRR.COL_BEHAVIOUR] = [None] * len(behavioursDF)
behavioursDF.reset_index(inplace=True)
#print("General")
BehavioursRR.__generateGeneralBehaviourrRR(behavioursDF, numberOfItems,
countOfRepetitions,
uBehavDesc)
#print(behavioursDF.head(10))
del behavioursDF['index']
#print(behavioursDF.head(10))
behavioursDF.to_csv(behaviourFile, sep='\t', index=False)
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 readDatasetsWithFilter(minEventCount:int):
eventsDF:DataFrame = Events.readFromFileWithFilter(minEventCount=minEventCount)
categoryTreeDF:DataFrame = CategoryTree.readFromFile()
itemPropertiesDF:DataFrame = ItemProperties.readFromFile()
return DatasetRetailRocket("rrDivAll", eventsDF, categoryTreeDF, itemPropertiesDF)
def readDatasets():
eventsDF:DataFrame = Events.readFromFile()
categoryTreeDF:DataFrame = CategoryTree.readFromFile()
itemPropertiesDF:DataFrame = ItemProperties.readFromFile()
return DatasetRetailRocket("rrDivAll", eventsDF, categoryTreeDF, itemPropertiesDF)
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 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 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)
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")
def test01():
print("Test 01")
userID: int = 565892
currentItemID: int = 168952
repetition: int = 0
# 5919585 b11111100011100000000
# 5947295 b11010110001101000010
# 5980935 b11111000000010101000
userID: int = 1043630
currentItemID: int = 349104
repetition: int = 0
#5952135 b10111101000000000000
#5962570 b11111100000100100000
#5980920 b11111011101100101000
#5980945 b11011100100110101100
#5995975 b11111011000010001010
eventsDF: DataFrame = Events.readFromFile()
#evensDF = evensDF.loc[evens[Events.COL_EVENT] == "transaction"]
eventsDF: DataFrame = eventsDF.sort_values(by=Events.COL_TIME_STAMP)
users = eventsDF[Events.COL_VISITOR_ID].tolist()
items = eventsDF[Events.COL_ITEM_ID].tolist()
print(users[0])
eventsDF = eventsDF.loc[eventsDF[Events.COL_VISITOR_ID] == userID]
eventsDF = eventsDF.loc[eventsDF[Events.COL_ITEM_ID] == currentItemID]
# for userIDI in users:
# eventsDF = eventsDF.loc[eventsDF[Events.COL_VISITOR_ID] == userIDI]
# eventsDF = eventsDF.loc[eventsDF[Events.COL_ITEM_ID] == currentItemID]
# if len(eventsDF) > 0:
# print(len(eventsDF))
print(eventsDF.head(100))
def test01():
DEBUG:bool = False
# First get Dataset Data
eventsDF:DataFrame = Events.readFromFile()
eventsDF = eventsDF.sort_values(Events.COL_TIME_STAMP)
userIDs:List[int] = list(eventsDF[Events.COL_VISITOR_ID].unique())
#eventsIDs:List[int] = list(eventsDF[Events.COL_EVENT].unique())
print("Number of all events: " + str(len(eventsDF)))
print("Number of all usersIDs: " + str(len(userIDs)))
print("Number of all addtocart: " + str(len(eventsDF.loc[eventsDF[Events.COL_EVENT] == "addtocart"])))
print("Number of all transaction: " + str(len(eventsDF.loc[eventsDF[Events.COL_EVENT] == "transaction"])))
print("---------------------------------------------------------")
# kolik vsech uziatelu si vlozilo do kosiku item vice nez jednou
eventsACartDF:DataFrame = eventsDF.loc[eventsDF[Events.COL_EVENT] == "addtocart"]
eventsACart2DF = eventsACartDF.groupby(
[Events.COL_VISITOR_ID, Events.COL_ITEM_ID], as_index=False)[Events.COL_TIME_STAMP].count()
eventsACart2DF = eventsACart2DF.loc[eventsACart2DF[Events.COL_TIME_STAMP] > 1]
# kolik vsech uzivatelu si pridalo 1-N polozek
usersAndAddedItemsCountDF:DataFrame = eventsACartDF[[Events.COL_VISITOR_ID, Events.COL_ITEM_ID]].drop_duplicates().groupby(
[Events.COL_VISITOR_ID], as_index=False)[Events.COL_ITEM_ID].count()
plt.hist(list(usersAndAddedItemsCountDF[Events.COL_ITEM_ID]))
plt.yscale('log')
if DEBUG:
plt.show()
userIDs:List[int] = list(eventsDF[Events.COL_VISITOR_ID].unique())
print("Number of all users: " + str(len(userIDs)))
print("Number of all users 1< #itemI added: " + str(len(eventsACart2DF)))
print("---------------------------------------------------------")
# filtrace eventu - vymazeme uzivatele, kteri maji mene nez K zaznamu
userIdAndTimestampDF:DataFrame[int, int] = eventsDF.groupby(
[Events.COL_VISITOR_ID], as_index=False)[Events.COL_TIME_STAMP].count()
userIdAndTimestampSelDF:DataFrame[int, int] = userIdAndTimestampDF.loc[
userIdAndTimestampDF[Events.COL_TIME_STAMP] > 5]
#print(userIdAndTimestampSelDF)
userIDsSel:List[int] = list(userIdAndTimestampSelDF[Events.COL_VISITOR_ID].unique())
eventsSelDF:DataFrame = eventsDF.loc[eventsDF[Events.COL_VISITOR_ID].isin(userIDsSel)]
print("Number of selected events: " + str(len(eventsSelDF)))
print("Number of selected usersIDs: " + str(len(userIDsSel)))
print("Number of all addtocart: " + str(len(eventsSelDF.loc[eventsSelDF[Events.COL_EVENT] == "addtocart"])))
print("Number of selected transaction: " + str(len(eventsSelDF.loc[eventsSelDF[Events.COL_EVENT] == "transaction"])))
print("---------------------------------------------------------")
# kolik vybranych uzivatelu si vlozilo do kosiku item aspon jednou
eventsSelACartDF:DataFrame = eventsSelDF.loc[eventsSelDF[Events.COL_EVENT] == "addtocart"]
userIDSelsACart:List[int] = list(eventsSelACartDF[Events.COL_VISITOR_ID].unique())
eventsSelACart1DF = eventsSelACartDF.groupby(
[Events.COL_VISITOR_ID, Events.COL_ITEM_ID], as_index=False)[Events.COL_TIME_STAMP].count()
eventsSelACart1DF = eventsSelACart1DF.loc[eventsSelACart1DF[Events.COL_TIME_STAMP] > 0]
print("Number of selected users: " + str(len(userIDsSel)))
print("Number of selected users who added something to cart: " + str(len(userIDSelsACart)))
print("---------------------------------------------------------")
# kolik vybranych uzivatelu koupilo vice jak dva ne nutne ruzne itemy
eventsSelACartDF:DataFrame = eventsSelDF.loc[eventsSelDF[Events.COL_EVENT] == "addtocart"]
eventsSelACartDF_ = eventsSelACartDF.groupby(
[Events.COL_VISITOR_ID], as_index=False)[Events.COL_TIME_STAMP].count()
eventsSelACart2DF = eventsSelACartDF_.loc[eventsSelACartDF_[Events.COL_TIME_STAMP] > 1]
userSelACart2IDs:List[int] = list(eventsSelACart2DF[Events.COL_VISITOR_ID])
print("Number of selected users 1< #addItem: " + str(len(userSelACart2IDs)))
eventsSelACart1DF = eventsSelACartDF_.loc[eventsSelACartDF_[Events.COL_TIME_STAMP] == 1]
userSelACart1IDs:List[int] = list(eventsSelACart1DF[Events.COL_VISITOR_ID])
print("Number of selected users 1= #addItem: " + str(len(userSelACart1IDs)))
# kolik vybranych uzivatelu si pridalo jednu jedinou polozku libovolnekrat
usersSelAndAddedItemsCountDF:DataFrame = eventsSelACartDF[[Events.COL_VISITOR_ID, Events.COL_ITEM_ID]].drop_duplicates().groupby(
[Events.COL_VISITOR_ID], as_index=False)[Events.COL_ITEM_ID].count()
plt.hist(list(usersSelAndAddedItemsCountDF[Events.COL_ITEM_ID]), bins=700)
if DEBUG:
plt.show()
a = len(usersSelAndAddedItemsCountDF.loc[usersSelAndAddedItemsCountDF[Events.COL_ITEM_ID] == 1])
print("Number of selected users who added only 1 unique itemI (possibly many times): " + str(a))
print("---------------------------------------------------------")
# kolik procent uzivatelu si koupilo jen jednu vec vicekrat
b = (a - len(userSelACart1IDs)) / len(userSelACart2IDs) * 100
print(str(b) + " %")
# zajimalo by me kolikrat si uzivatele kupovali stejnou vec
eventsTransDF:DataFrame = eventsDF.loc[eventsDF[Events.COL_EVENT] == "transaction"]
events2DF = eventsTransDF.groupby(
[Events.COL_VISITOR_ID, Events.COL_ITEM_ID], as_index=False)[Events.COL_TIME_STAMP].count()
events2DF = events2DF.loc[events2DF[Events.COL_TIME_STAMP] > 4]
#print(events2DF.head(10))
events152963DF:DataFrame = eventsDF.loc[eventsDF[Events.COL_VISITOR_ID] == 152963]
events152963DF = events152963DF.loc[events152963DF[Events.COL_ITEM_ID] == 119736]
#print(events152963DF.head(1000000).to_string())
events530559DF:DataFrame = eventsDF.loc[eventsDF[Events.COL_VISITOR_ID] == 530559]
events530559DF = events530559DF.loc[events530559DF[Events.COL_ITEM_ID] == 119736]
#print(events530559DF.head(1000000).to_string())
events76757DF:DataFrame = eventsDF.loc[eventsDF[Events.COL_VISITOR_ID] == 76757]
events76757DF:DataFrame = events76757DF.loc[events76757DF[Events.COL_EVENT] == "transaction"]