def __init__(self, pre_splitted_path):
test_percentage = 0.2
validation_percentage = 0.2
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print(
"Dataset_MovielensHetrec2011: Attempting to load pre-splitted data"
)
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print(
"Dataset_MovielensHetrec2011: Pre-splitted data not found, building new one"
)
data_reader = MovielensHetrec2011Reader_DataManager()
loaded_dataset = data_reader.load_data()
URM_all = loaded_dataset.get_URM_all()
# keep only ratings 5
URM_all.data = URM_all.data == 5
URM_all.eliminate_zeros()
# create train - test - validation
URM_train_original, URM_test = split_train_validation_percentage_user_wise(
URM_all, train_percentage=1 - test_percentage, verbose=False)
URM_train, URM_validation = split_train_validation_percentage_user_wise(
URM_train_original,
train_percentage=1 - validation_percentage,
verbose=False)
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("Dataset_MovielensHetrec2011: Dataset loaded")
ut.print_stat_datareader(self)
def __init__(self, pre_splitted_path):
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print("Dataset_FilmTrust: Attempting to load pre-splitted data")
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print(
"Dataset_FilmTrust: Pre-splitted data not found, building new one"
)
data_reader = FilmTrustReader_DataManager()
loaded_dataset = data_reader.load_data()
URM_all = loaded_dataset.get_URM_all()
URM_all.eliminate_zeros()
URM_all.data = np.ones_like(URM_all.data)
URM_train, URM_test = split_train_validation_percentage_random_holdout(
URM_all, train_percentage=0.8)
URM_train, URM_validation = split_train_validation_percentage_random_holdout(
URM_train, train_percentage=0.9)
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("FilmTrust: Dataset loaded")
ut.print_stat_datareader(self)
def __init__(self):
test_percentage = 0.2
validation_percentage = 0.2
pre_splitted_path = "Data_manager_split_datasets/AmazonInstantVideo/RecSys/SpectralCF_our_interface/"
pre_splitted_filename = "splitted_data"
ratings_file_name = "ratings_Amazon_Instant_Video.csv"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print(
"Dataset_AmazonInstantVideo: Attempting to load pre-splitted data"
)
for attrib_name, attrib_object in load_data_dict(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print(
"Dataset_AmazonInstantVideo: Pre-splitted data not found, building new one"
)
folder_path = self.DATASET_SPLIT_ROOT_FOLDER + self.DATASET_SUBFOLDER
downloadFromURL(self.DATASET_URL, folder_path, ratings_file_name)
# read Amazon Instant Video
df = pd.read_csv(folder_path + ratings_file_name,
sep=',',
header=None,
names=['user', 'item', 'rating',
'timestamp'])[['user', 'item', 'rating']]
# keep only ratings = 5
URM_train_builder = IncrementalSparseMatrix(
auto_create_col_mapper=True, auto_create_row_mapper=True)
URM_train_builder.add_data_lists(df['user'].values,
df['item'].values,
df['rating'].values)
URM_all = URM_train_builder.get_SparseMatrix()
URM_all.data = URM_all.data == 5
URM_all.eliminate_zeros()
# keep only users with at least 5 ratings
URM_all = ut.filter_urm(URM_all,
user_min_number_ratings=5,
item_min_number_ratings=1)
# create train - test - validation
URM_train_original, self.URM_test = split_train_validation_percentage_user_wise(
URM_all, train_percentage=1 - test_percentage, verbose=False)
self.URM_train, self.URM_validation = split_train_validation_percentage_user_wise(
URM_train_original,
train_percentage=1 - validation_percentage,
verbose=False)
data_dict = {
"URM_train": self.URM_train,
"URM_test": self.URM_test,
"URM_validation": self.URM_validation,
}
save_data_dict(data_dict, pre_splitted_path, pre_splitted_filename)
print("Dataset_AmazonInstantVideo: Dataset loaded")
ut.print_stat_datareader(self)
def __init__(self, pre_splitted_path, original=True):
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print("Dataset_{}: Attempting to load pre-splitted data".format(
self.DATASET_NAME))
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print("Dataset_{}: Pre-splitted data not found, building new one".
format(self.DATASET_NAME))
compressed_file_folder = "Conferences/IJCAI/ConvNCF_github/Data/"
decompressed_file_folder = "Data_manager_split_datasets/Yelp/"
# compressed_file = tarfile.open(compressed_file_folder + "yelp.test.negative.gz", "r:gz")
# compressed_file.extract("yelp.test.negative", path=decompressed_file_folder + "decompressed/")
# compressed_file.close()
#
# compressed_file = tarfile.open(compressed_file_folder + "yelp.test.rating.gz", "r:gz")
# compressed_file.extract("yelp.test.rating", path=decompressed_file_folder + "decompressed/")
# compressed_file.close()
#
# compressed_file = tarfile.open(compressed_file_folder + "yelp.train.rating.gz", "r:gz")
# compressed_file.extract("yelp.train.rating", path=decompressed_file_folder + "decompressed/")
# compressed_file.close()
# if original:
Dataset_github.load_rating_file_as_list = Dataset_github.load_training_file_as_matrix
try:
dataset = Dataset_github(compressed_file_folder + "yelp")
except FileNotFoundError as exc:
print(
"Dataset_{}: Uncompressed files not found, please manually decompress the *.gz files in this folder: '{}'"
.format(self.DATASET_NAME, compressed_file_folder))
raise exc
URM_train_original, URM_test = dataset.trainMatrix, dataset.testRatings
n_users = max(URM_train_original.shape[0], URM_test.shape[0])
n_items = max(URM_train_original.shape[1], URM_test.shape[1])
URM_train_original = sps.csr_matrix(URM_train_original,
shape=(n_users, n_items))
URM_test = sps.csr_matrix(URM_test, shape=(n_users, n_items))
URM_train_original.data = np.ones_like(URM_train_original.data)
URM_test.data = np.ones_like(URM_test.data)
URM_test_negatives_builder = IncrementalSparseMatrix(
n_rows=n_users, n_cols=n_items)
n_negative_samples = 999
for user_index in range(len(dataset.testNegatives)):
user_test_items = dataset.testNegatives[user_index]
if len(user_test_items) != n_negative_samples:
print(
"user id: {} has {} negative items instead {}".format(
user_index, len(user_test_items),
n_negative_samples))
URM_test_negatives_builder.add_single_row(user_index,
user_test_items,
data=1.0)
URM_test_negative = URM_test_negatives_builder.get_SparseMatrix()
URM_test_negative.data = np.ones_like(URM_test_negative.data)
URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(
URM_train_original.copy(), verbose=False)
#
# else:
# data_reader = YelpReader_DataManager()
# loaded_dataset = data_reader.load_data()
#
# URM_all = loaded_dataset.get_URM_all()
#
# URM_timestamp = URM_all.copy()
#
# URM_all.data = np.ones_like(URM_all.data)
#
# URM_train, URM_validation, URM_test, URM_negative = split_data_on_timestamp(URM_all, URM_timestamp, negative_items_per_positive=999)
# URM_train = URM_train + URM_validation
# URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(URM_train, verbose=False)
shutil.rmtree(decompressed_file_folder + "decompressed/",
ignore_errors=True)
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
"URM_test_negative": URM_test_negative,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("{}: Dataset loaded".format(self.DATASET_NAME))
ut.print_stat_datareader(self)
def __init__(self,
pre_splitted_path,
type="original",
cold_start=False,
cold_items=None):
assert type in ["original", "ours"]
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# their mode in cold start
mode = 1
# path for pre existed movielens1M split
movielens_splitted_path = "Conferences/RecSys/SpectralCF_github/data/ml-1m/"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print("Dataset_Movielens1M: Attempting to load pre-splitted data")
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print(
"Dataset_Movielens1M: Pre-splitted data not found, building new one"
)
if type == "original":
assert (cold_start is False)
# use the SpectralCF class to read data
data_generator = Data(
train_file=movielens_splitted_path + 'train_users.dat',
test_file=movielens_splitted_path + 'test_users.dat',
batch_size=BATCH_SIZE)
# convert train into csr
full_train_matrix = sps.csr_matrix(data_generator.R)
URM_train_original = full_train_matrix
# convert test into csr
test_set = data_generator.test_set
uids, items = [], []
for uid in test_set.keys():
uids += np.full(len(test_set[uid]), uid).tolist()
items += test_set[uid]
test_matrix = sps.csr_matrix(
(np.ones(len(items)), (uids, items)),
shape=(full_train_matrix.shape))
if not cold_start:
URM_test = test_matrix
# create validation
URM_train, URM_validation = split_train_validation_percentage_user_wise(
URM_train_original,
train_percentage=0.9,
verbose=False)
else:
print('nothing')
elif type == "ours":
data_reader = Movielens1MReader_DataManager()
loaded_dataset = data_reader.load_data()
URM_all = loaded_dataset.get_URM_all()
URM_all.data = URM_all.data == 5
URM_all.eliminate_zeros()
if not cold_start:
URM_train, URM_test = split_train_validation_percentage_user_wise(
URM_all, train_percentage=0.8, verbose=False)
URM_train, URM_validation = split_train_validation_percentage_user_wise(
URM_train, train_percentage=0.9, verbose=False)
else:
if mode == 1: # their mode, cold start for full dataset
URM_train, URM_test = split_train_validation_cold_start_user_wise(
URM_all,
full_train_percentage=0.0,
cold_items=cold_items,
verbose=False)
URM_test, URM_validation = split_train_validation_percentage_user_wise(
URM_test, train_percentage=0.9, verbose=False)
if mode == 2: # cold start only for some users
URM_train, URM_test = split_train_validation_cold_start_user_wise(
URM_all,
full_train_percentage=0.8,
cold_items=cold_items,
verbose=False)
URM_train, URM_validation = split_train_validation_cold_start_user_wise(
URM_train,
full_train_percentage=0.9,
cold_items=cold_items,
verbose=False)
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("Dataset_Movielens1M: Dataset loaded")
ut.print_stat_datareader(self)
def __init__(self, pre_splitted_path, type='original'):
assert type in ["original", "ours"]
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print("Dataset_{}: Attempting to load pre-splitted data".format(
self.DATASET_NAME))
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print("Dataset_{}: Pre-splitted data not found, building new one".
format(self.DATASET_NAME))
from Conferences.IJCAI.CoupledCF_original import LoadMovieDataCnn as DatareaderOriginal
path = "Conferences/IJCAI/CoupledCF_original/ml-1m/"
n_users, gender, age, occupation = DatareaderOriginal.load_user_attributes(
path=path, split=True)
n_items, items_genres_mat = DatareaderOriginal.load_itemGenres_as_matrix(
path=path)
ratings = DatareaderOriginal.load_rating_train_as_matrix(path=path)
testRatings = DatareaderOriginal.load_rating_file_as_list(
path=path)
testNegatives = DatareaderOriginal.load_negative_file(path=path)
URM_all = ratings.tocsr()
UCM_gender = gender.tocsr()
UCM_age = age.tocsr()
UCM_occupation = occupation.tocsr()
UCM_all = sps.hstack((UCM_gender, UCM_age, UCM_occupation)).tocsr()
ICM_all = sps.csr_matrix(items_genres_mat)
testRatings = np.array(testRatings).T
URM_test_builder = IncrementalSparseMatrix(n_rows=n_users + 1,
n_cols=n_items + 1)
URM_test_builder.add_data_lists(testRatings[0], testRatings[1],
np.ones(len(testRatings[0])))
URM_test = URM_test_builder.get_SparseMatrix()
URM_test_negatives_builder = IncrementalSparseMatrix(
n_rows=n_users + 1, n_cols=n_items + 1)
# care here, the test negative start from index 0 but it refer to user index 1 (user index start from 1)
n_negative_samples = 99
for index in range(len(testNegatives)):
user_test_items = testNegatives[index]
if len(user_test_items) != n_negative_samples:
print(
"user id: {} has {} negative items instead {}".format(
index + 1, len(user_test_items),
n_negative_samples))
URM_test_negatives_builder.add_single_row(index + 1,
user_test_items,
data=1.0)
URM_test_negative = URM_test_negatives_builder.get_SparseMatrix()
URM_test_negative.data = np.ones_like(URM_test_negative.data)
if type == 'original':
URM_test = URM_test
URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(
URM_all.copy(), verbose=False)
else: # redo the split
URM_full = URM_all + URM_test
URM_temp, URM_test = split_train_validation_leave_one_out_user_wise(
URM_full.copy(), verbose=False)
URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(
URM_temp.copy(), verbose=False)
self.ICM_DICT = {
"UCM_gender": UCM_gender,
"UCM_occupation": UCM_occupation,
"UCM_age": UCM_age,
"UCM_all": UCM_all,
"ICM_all": ICM_all,
}
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
"URM_test_negative": URM_test_negative,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("{}: Dataset loaded".format(self.DATASET_NAME))
ut.print_stat_datareader(self)
def __init__(self, pre_splitted_path, type='original'):
assert type in ["original", "ours"]
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print("Dataset_{}: Attempting to load pre-splitted data".format(
self.DATASET_NAME))
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print("Dataset_{}: Pre-splitted data not found, building new one".
format(self.DATASET_NAME))
from Conferences.IJCAI.CoupledCF_original import LoadTafengDataCnn as DatareaderOriginal
path = "Conferences/IJCAI/CoupledCF_original/tafeng/"
n_users, user_attributes_mat = DatareaderOriginal.load_user_attributes(
path=path)
n_items, items_genres_mat = DatareaderOriginal.load_itemGenres_as_matrix(
path=path)
ratings = DatareaderOriginal.load_rating_train_as_matrix(path=path)
testRatings = DatareaderOriginal.load_rating_file_as_list(
path=path)
testNegatives = DatareaderOriginal.load_negative_file(path=path)
URM_all = ratings.tocsr()
UCM_all = sps.csc_matrix(user_attributes_mat)
UCM_age = UCM_all[:, 0:11].tocsr()
UCM_region = UCM_all[:, 11:19].tocsr()
UCM_all = UCM_all.tocsr()
# col: 0->category, 2->asset(0-1), 1->price(0-1)
ICM_original = sps.csc_matrix(items_genres_mat)
# category could be used as matrix, not single row
ICM_sub_class = ICM_original[:, 0:1].tocsr()
max = ICM_sub_class.shape[0]
rows, cols, data = [], [], []
for idx in range(max):
# we have only index 0 as col
data_vect = ICM_sub_class.data[
ICM_sub_class.indptr[idx]:ICM_sub_class.indptr[idx + 1]]
if len(data_vect) == 0:
# handle category value 0 that in a csr matrix is not present
cols.append(int(0))
else:
cols.append(int(data_vect[0]))
rows.append(idx)
data.append(1.0)
ICM_sub_class = sps.csr_matrix((data, (rows, cols)))
ICM_asset = ICM_original[:, 1:2].tocsr()
ICM_price = ICM_original[:, 2:3].tocsr()
ICM_original = ICM_original.tocsc()
ICM_all = sps.hstack((ICM_sub_class, ICM_asset, ICM_price))
testRatings = np.array(testRatings).T
URM_test_builder = IncrementalSparseMatrix(n_rows=n_users + 1,
n_cols=n_items + 1)
URM_test_builder.add_data_lists(testRatings[0], testRatings[1],
np.ones(len(testRatings[0])))
URM_test = URM_test_builder.get_SparseMatrix()
URM_test_negatives_builder = IncrementalSparseMatrix(
n_rows=n_users + 1, n_cols=n_items + 1)
# care here, the test negative start from index 0 but it refer to user index 1 (user index start from 1)
n_negative_samples = 99
for index in range(len(testNegatives)):
user_test_items = testNegatives[index]
if len(user_test_items) != n_negative_samples:
print(
"user id: {} has {} negative items instead {}".format(
index + 1, len(user_test_items),
n_negative_samples))
URM_test_negatives_builder.add_single_row(index + 1,
user_test_items,
data=1.0)
URM_test_negative = URM_test_negatives_builder.get_SparseMatrix()
URM_test_negative.data = np.ones_like(URM_test_negative.data)
if type == 'original':
URM_test = URM_test
URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(
URM_all.copy(), verbose=False)
else: # redo the split
URM_full = URM_all + URM_test
URM_temp, URM_test = split_train_validation_leave_one_out_user_wise(
URM_full.copy(), verbose=False)
URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(
URM_temp.copy(), verbose=False)
self.ICM_DICT = {
"UCM_age": UCM_age,
"UCM_region": UCM_region,
"UCM_all": UCM_all,
"ICM_all": ICM_all,
"ICM_original": ICM_original,
"ICM_sub_class": ICM_sub_class,
"ICM_asset": ICM_asset,
"ICM_price": ICM_price,
}
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
"URM_test_negative": URM_test_negative,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("{}: Dataset loaded".format(self.DATASET_NAME))
ut.print_stat_datareader(self)
def __init__(self, pre_splitted_path):
pre_splitted_path += "data_split/"
pre_splitted_filename = "splitted_data_"
# If directory does not exist, create
if not os.path.exists(pre_splitted_path):
os.makedirs(pre_splitted_path)
try:
print("Dataset_{}: Attempting to load pre-splitted data".format(
self.DATASET_NAME))
for attrib_name, attrib_object in load_data_dict_zip(
pre_splitted_path, pre_splitted_filename).items():
self.__setattr__(attrib_name, attrib_object)
except FileNotFoundError:
print("Dataset_{}: Pre-splitted data not found, building new one".
format(self.DATASET_NAME))
compressed_file_folder = "Conferences/IJCAI/ConvNCF_github/Data/"
decompressed_file_folder = "Data_manager_split_datasets/Gowalla/"
# compressed_file = tarfile.open(compressed_file_folder + "gowalla.test.negative.gz", "r:gz")
# compressed_file.extract("yelp.test.negative", path=decompressed_file_folder + "decompressed/")
# compressed_file.close()
#
# compressed_file = tarfile.open(compressed_file_folder + "gowalla.test.rating.gz", "r:gz")
# compressed_file.extract("yelp.test.rating", path=decompressed_file_folder + "decompressed/")
# compressed_file.close()
#
# compressed_file = tarfile.open(compressed_file_folder + "gowalla.train.rating.gz", "r:gz")
# compressed_file.extract("yelp.train.rating", path=decompressed_file_folder + "decompressed/")
# compressed_file.close()
# if original:
Dataset_github.load_rating_file_as_list = Dataset_github.load_training_file_as_matrix
try:
dataset = Dataset_github(compressed_file_folder + "gowalla")
except FileNotFoundError as exc:
print(
"Dataset_{}: Gowalla files not found, please download them and put them in this folder '{}', url: {}"
.format(self.DATASET_NAME, compressed_file_folder,
self.DATASET_URL))
print(
"Dataset_{}: Uncompressed files not found, please manually decompress the *.gz files in this folder: '{}'"
.format(self.DATASET_NAME, compressed_file_folder))
raise exc
URM_train_original, URM_test = dataset.trainMatrix, dataset.testRatings
n_users = max(URM_train_original.shape[0], URM_test.shape[0])
n_items = max(URM_train_original.shape[1], URM_test.shape[1])
URM_train_original = sps.csr_matrix(URM_train_original,
shape=(n_users, n_items))
URM_test = sps.csr_matrix(URM_test, shape=(n_users, n_items))
URM_train_original.data = np.ones_like(URM_train_original.data)
URM_test.data = np.ones_like(URM_test.data)
URM_test_negatives_builder = IncrementalSparseMatrix(
n_rows=n_users, n_cols=n_items)
n_negative_samples = 999
for user_index in range(len(dataset.testNegatives)):
user_test_items = dataset.testNegatives[user_index]
if len(user_test_items) != n_negative_samples:
print(
"user id: {} has {} negative items instead {}".format(
user_index, len(user_test_items),
n_negative_samples))
URM_test_negatives_builder.add_single_row(user_index,
user_test_items,
data=1.0)
URM_test_negative = URM_test_negatives_builder.get_SparseMatrix(
).tocsr()
URM_test_negative.data = np.ones_like(URM_test_negative.data)
URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(
URM_train_original.copy(), verbose=False)
#
#
# # NOT USED
# # elif not time_split: #create from full dataset with random leave one out from LINKED dateset in the article since timestamp is not present.
# #
# # data_reader = GowallaGithubReader_DataManager()
# # loaded_dataset = data_reader.load_data()
# #
# # URM_all = loaded_dataset.get_URM_all()
# #
# # URM_all.eliminate_zeros()
# #
# # URM_all.data = np.ones_like(URM_all.data)
# #
# # #use this function 2 time because the order could change slightly the number of final interactions
# # #with this order we get the same number of interactions as in the paper
# # URM_all = filter_urm(URM_all, user_min_number_ratings=0, item_min_number_ratings=10)
# # URM_all = filter_urm(URM_all, user_min_number_ratings=2, item_min_number_ratings=0)
# #
# # URM_train, URM_validation, URM_test, URM_negative = split_train_validation_test_negative_leave_one_out_user_wise(URM_all, negative_items_per_positive=999,
# # at_least_n_train_items_test=0, at_least_n_train_items_validation=0,
# # verbose=True)
# # URM_timestamp = sps.csc_matrix(([],([],[])), shape=URM_train.shape)
#
# else: # create from full dataset with leave out one time wise from ORIGINAL full dateset
# data_reader = GowallaReader_DataManager()
# loaded_dataset = data_reader.load_data()
#
# URM_all = loaded_dataset.get_URM_all()
#
# # use this function 2 time because the order could change slightly the number of final interactions
# # with this order we get the same number of interactions as in the paper
# URM_all = filter_urm(URM_all, user_min_number_ratings=0, item_min_number_ratings=10)
# URM_all = filter_urm(URM_all, user_min_number_ratings=2, item_min_number_ratings=0)
#
# URM_timestamp = URM_all.copy()
# URM_all.data = np.ones_like(URM_all.data)
#
# URM_train, URM_validation, URM_test, URM_negative = split_data_on_timestamp(URM_all, URM_timestamp, negative_items_per_positive=999)
# URM_train = URM_train + URM_validation
# URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(URM_train, verbose=False)
self.URM_DICT = {
"URM_train": URM_train,
"URM_test": URM_test,
"URM_validation": URM_validation,
"URM_test_negative": URM_test_negative,
}
save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path,
pre_splitted_filename)
print("{}: Dataset loaded".format(self.DATASET_NAME))
ut.print_stat_datareader(self)
