def __init__(self, path): ''' Constructor ''' trainMatrix = self.load_rating_file_as_matrix(path + ".train.rating") testRatings = self.load_rating_file_as_matrix(path + ".test.rating") testNegatives = self.load_negative_file(path + ".test.negative") assert len(testRatings) == len(testNegatives) self.num_users, self.num_items = trainMatrix.shape from Base.Recommender_utils import reshapeSparse self.URM_train = trainMatrix.tocsr() self.URM_test = testRatings.tocsr() shape = (max(self.URM_train.shape[0], self.URM_test.shape[0]), max(self.URM_train.shape[1], self.URM_test.shape[1])) self.URM_train = reshapeSparse(self.URM_train, shape) self.URM_test = reshapeSparse(self.URM_test, shape) URM_test_negatives_builder = IncrementalSparseMatrix(n_rows=shape[0], n_cols=shape[1]) for user_index in range(len(testNegatives)): user_test_items = testNegatives[user_index] URM_test_negatives_builder.add_single_row(user_index, user_test_items, data=1.0) self.URM_test_negative = URM_test_negatives_builder.get_SparseMatrix()
def _load_data_file(self, filePath, separator=" "): URM_builder = IncrementalSparseMatrix(auto_create_row_mapper=False, auto_create_col_mapper=False) fileHandle = open(filePath, "r") user_index = 0 for line in fileHandle: if (user_index % 1000000 == 0): print("Processed {} cells".format(user_index)) if (len(line)) > 1: line = line.replace("\n", "") line = line.split(separator) if len(line) > 0: if line[0] != "0": line = [int(line[i]) for i in range(len(line))] URM_builder.add_single_row(user_index, line[1:], data=1.0) user_index += 1 fileHandle.close() return URM_builder
def test_IncrementalSparseMatrix_add_rows(self): import numpy as np n_rows = 100 n_cols = 200 randomMatrix = sps.random(n_rows, n_cols, density=0.01, format="csr") incrementalMatrix = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) for row in range(n_rows): row_data = randomMatrix.indices[randomMatrix. indptr[row]:randomMatrix.indptr[row + 1]] incrementalMatrix.add_single_row(row, row_data, 5.0) randomMatrix.data = np.ones_like(randomMatrix.data) * 5.0 randomMatrix_incremental = incrementalMatrix.get_SparseMatrix() assert sparse_are_equals(randomMatrix, randomMatrix_incremental)
def split_train_validation_test_negative_leave_one_out_user_wise(URM_all, negative_items_per_positive=50, verbose=True, at_least_n_train_items_test=0, at_least_n_train_items_validation=0): """ This function creates a Train, Test, Validation split with negative items sampled The split is perfomed user-wise, hold 1 out for validation and test :param URM_all: :param negative_items_per_positive: :return: """ URM_all = sps.csr_matrix(URM_all) n_rows, n_cols = URM_all.shape print('Creation test...') URM_train_all, URM_test = split_train_validation_leave_one_out_user_wise(URM_all, at_least_n_train_items=at_least_n_train_items_test, verbose=verbose) print('Creation validation...') URM_train, URM_validation = split_train_validation_leave_one_out_user_wise(URM_train_all, at_least_n_train_items=at_least_n_train_items_validation, verbose=verbose) URM_negative_builder = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) all_items = np.arange(0, n_cols, dtype=np.int) for user_index in range(URM_train_all.shape[0]): if user_index % 10000 == 0: print("split_data_train_validation_test_negative: user {} of {}".format(user_index, URM_all.shape[0])) start_pos = URM_all.indptr[user_index] end_pos = URM_all.indptr[user_index + 1] user_profile = URM_all.indices[start_pos:end_pos] unobserved_index = np.in1d(all_items, user_profile, assume_unique=True, invert=True) unobserved_items = all_items[unobserved_index] np.random.shuffle(unobserved_items) n_test_items = URM_test.indptr[user_index + 1] - URM_test.indptr[user_index] num_negative_items = n_test_items * negative_items_per_positive if num_negative_items > len(unobserved_items): print( "split_data_train_validation_test_negative: WARNING number of negative to sample for user {} is greater than available negative items {}".format( num_negative_items, len(unobserved_items))) num_negative_items = min(num_negative_items, len(unobserved_items)) URM_negative_builder.add_single_row(user_index, unobserved_items[:num_negative_items], 1.0) URM_negative = URM_negative_builder.get_SparseMatrix() return URM_train, URM_validation, URM_test, URM_negative
def split_data_train_validation_test_negative_user_wise(URM_all, negative_items_per_positive=50): """ This function creates a Train, Test, Validation split with negative items sampled The split is perfomed user-wise, 20% is test, 80% is train. Train is further divided in 90% final train and 10% validation :param URM_all: :param negative_items_per_positive: :return: """ URM_all = sps.csr_matrix(URM_all) n_rows, n_cols = URM_all.shape URM_train_all, URM_test = split_train_validation_percentage_user_wise(URM_all, train_percentage=0.8) URM_train, URM_validation = split_train_validation_percentage_user_wise(URM_train_all, train_percentage=0.9) URM_negative_builder = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) all_items = np.arange(0, n_cols, dtype=np.int) for user_index in range(URM_train_all.shape[0]): if user_index % 10000 == 0: print("split_data_train_validation_test_negative: user {} of {}".format(user_index, URM_all.shape[0])) start_pos = URM_all.indptr[user_index] end_pos = URM_all.indptr[user_index + 1] user_profile = URM_all.indices[start_pos:end_pos] unobserved_index = np.in1d(all_items, user_profile, assume_unique=True, invert=True) unobserved_items = all_items[unobserved_index] np.random.shuffle(unobserved_items) n_test_items = URM_test.indptr[user_index + 1] - URM_test.indptr[user_index] num_negative_items = n_test_items * negative_items_per_positive if num_negative_items > len(unobserved_items): print( "split_data_train_validation_test_negative: WARNING number of negative to sample for user {} is greater than available negative items {}".format( num_negative_items, len(unobserved_items))) num_negative_items = min(num_negative_items, len(unobserved_items)) URM_negative_builder.add_single_row(user_index, unobserved_items[:num_negative_items], 1.0) URM_negative = URM_negative_builder.get_SparseMatrix() return URM_train, URM_validation, URM_test, URM_negative
def __init__(self): super(Movielens100KReader, self).__init__() pre_splitted_path = "Data_manager_split_datasets/Movielens100K/KDD/MCRec_our_interface/" pre_splitted_filename = "splitted_data" original_data_path = "Conferences/KDD/MCRec_github/data/" # If directory does not exist, create if not os.path.exists(pre_splitted_path): os.makedirs(pre_splitted_path) try: print("Movielens100KReader: 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("Movielens100KReader: Pre-splitted data not found, building new one") print("Movielens100KReader: loading URM") from Conferences.KDD.MCRec_github.code.Dataset import Dataset dataset = 'ml-100k' dataset = Dataset(original_data_path + dataset) URM_train, testRatings, testNegatives = dataset.trainMatrix, dataset.testRatings, dataset.testNegatives # Dataset adds 1 to user and item id, removing it to restore 0 indexing URM_train = sps.coo_matrix(URM_train) URM_train.row -= 1 URM_train.col -= 1 self.URM_train = sps.csr_matrix((np.ones_like(URM_train.data), (URM_train.row, URM_train.col))) num_users, num_items = self.URM_train.shape # Build sparse matrices from lists URM_test_builder = IncrementalSparseMatrix(n_rows=num_users, n_cols=num_items) URM_test_negative_builder = IncrementalSparseMatrix(n_rows=num_users, n_cols=num_items) for user_index in range(len(testRatings)): user_id = testRatings[user_index][0] current_user_test_items = testRatings[user_index][1:] current_user_test_negative_items = testNegatives[user_index] current_user_test_items = np.array(current_user_test_items) -1 current_user_test_negative_items = np.array(current_user_test_negative_items) -1 URM_test_builder.add_single_row(user_id -1, current_user_test_items, 1.0) URM_test_negative_builder.add_single_row(user_id -1, current_user_test_negative_items, 1.0) # the test data has repeated data, apparently self.URM_test = URM_test_builder.get_SparseMatrix() self.URM_test_negative = URM_test_negative_builder.get_SparseMatrix() # Split validation from train as 10% from Data_manager.split_functions.split_train_validation import split_train_validation_percentage_user_wise self.URM_train, self.URM_validation = split_train_validation_percentage_user_wise(self.URM_train, train_percentage=0.9) # Load features data_reader = Movielens100KReader_DataManager() data_reader.load_data() zipFile_path = data_reader.DATASET_SPLIT_ROOT_FOLDER + data_reader.DATASET_SUBFOLDER dataFile = zipfile.ZipFile(zipFile_path + "ml-100k.zip") ICM_path = dataFile.extract("ml-100k/u.item", path=zipFile_path + "decompressed/") ICM_genre = self._loadICM(ICM_path) ICM_genre = ICM_genre.get_SparseMatrix() shutil.rmtree(zipFile_path + "decompressed", ignore_errors=True) self.ICM_dict = {"ICM_genre": ICM_genre} data_dict = { "URM_train": self.URM_train, "URM_test": self.URM_test, "URM_validation": self.URM_validation, "URM_test_negative": self.URM_test_negative, "ICM_dict": self.ICM_dict, } save_data_dict(data_dict, pre_splitted_path, pre_splitted_filename) print("Movielens100KReader: loading complete")
def __init__(self, pre_splitted_path): super(Movielens1MReader, self).__init__() 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_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" ) # Ensure file is loaded as matrix Dataset_github.load_rating_file_as_list = Dataset_github.load_rating_file_as_matrix dataset = Dataset_github("Conferences/WWW/NeuMF_github/Data/ml-1m") URM_train_original, URM_test = dataset.trainMatrix, dataset.testRatings URM_train_original = URM_train_original.tocsr() URM_test = URM_test.tocsr() from Base.Recommender_utils import reshapeSparse shape = (max(URM_train_original.shape[0], URM_test.shape[0]), max(URM_train_original.shape[1], URM_test.shape[1])) URM_train_original = reshapeSparse(URM_train_original, shape) URM_test = reshapeSparse(URM_test, shape) URM_test_negatives_builder = IncrementalSparseMatrix( n_rows=shape[0], n_cols=shape[1]) for user_index in range(len(dataset.testNegatives)): user_test_items = dataset.testNegatives[user_index] 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_train, URM_validation = split_train_validation_leave_one_out_user_wise( URM_train_original.copy()) self.URM_DICT = { "URM_train_original": URM_train_original, "URM_train": URM_train, "URM_test": URM_test, "URM_test_negative": URM_test_negative, "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")
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'): 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 split_data_on_timestamp(URM_all, URM_timestamp, negative_items_per_positive=100): URM_all = sps.csr_matrix(URM_all) URM_timestamp = sps.csr_matrix(URM_timestamp) n_rows, n_cols = URM_all.shape URM_train_builder = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) URM_test_builder = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) URM_validation_builder = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) URM_negative_builder = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols) all_items = np.arange(0, n_cols, dtype=np.int) for user_index in range(URM_all.shape[0]): if user_index % 10000 == 0: print("split_data_on_sequence: user {} of {}".format(user_index, URM_all.shape[0])) start_pos = URM_all.indptr[user_index] end_pos = URM_all.indptr[user_index+1] user_profile = URM_all.indices[start_pos:end_pos] user_data = URM_all.data[start_pos:end_pos] user_sequence = URM_timestamp.data[start_pos:end_pos] unobserved_index = np.in1d(all_items, user_profile, assume_unique=True, invert=True) unobserved_items = all_items[unobserved_index] np.random.shuffle(unobserved_items) URM_negative_builder.add_single_row(user_index, unobserved_items[:negative_items_per_positive], 1.0) if len(user_profile) >= 3: # Test contain the first one, validation the second min_pos = np.argmax(user_sequence) venue_index = user_profile[min_pos] venue_data = user_data[min_pos] URM_test_builder.add_data_lists([user_index], [venue_index], [venue_data]) user_profile = np.delete(user_profile, min_pos) user_data = np.delete(user_data, min_pos) user_sequence = np.delete(user_sequence, min_pos) min_pos = np.argmax(user_sequence) venue_index = user_profile[min_pos] venue_data = user_data[min_pos] URM_validation_builder.add_data_lists([user_index], [venue_index], [venue_data]) user_profile = np.delete(user_profile, min_pos) user_data = np.delete(user_data, min_pos) #user_sequence = np.delete(user_sequence, min_pos) URM_train_builder.add_data_lists([user_index]*len(user_profile), user_profile, user_data) URM_train = URM_train_builder.get_SparseMatrix() URM_validation = URM_validation_builder.get_SparseMatrix() URM_test = URM_test_builder.get_SparseMatrix() URM_negative = URM_negative_builder.get_SparseMatrix() return URM_train, URM_validation, URM_test, URM_negative
def __init__(self, pre_splitted_path, type="original"): 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)) if type == "original": # Ensure file is loaded as matrix Dataset_github.load_rating_file_as_list = Dataset_github.load_rating_file_as_matrix dataset = Dataset_github( "Conferences/IJCAI/DELF_original/Data/ml-1m") URM_train, URM_validation, URM_test, testNegatives = dataset.trainMatrix, dataset.validRatings, \ dataset.testRatings, dataset.testNegatives URM_train = URM_train.tocsr() URM_validation = URM_validation.tocsr() URM_test = URM_test.tocsr() URM_timestamp = "no" from Base.Recommender_utils import reshapeSparse shape = (max(URM_train.shape[0], URM_validation.shape[0], URM_test.shape[0]), max(URM_train.shape[1], URM_validation.shape[1], URM_test.shape[1])) URM_train = reshapeSparse(URM_train, shape) URM_validation = reshapeSparse(URM_validation, shape) URM_test = reshapeSparse(URM_test, shape) URM_test_negatives_builder = IncrementalSparseMatrix( n_rows=shape[0], n_cols=shape[1]) for user_index in range(len(dataset.testNegatives)): user_test_items = dataset.testNegatives[user_index] URM_test_negatives_builder.add_single_row(user_index, user_test_items, data=1.0) URM_test_negative = URM_test_negatives_builder.get_SparseMatrix( ) elif type == "ours": # create from full dataset with leave out one time wise from ORIGINAL full dateset data_reader = Movielens1MReader_DataManager() loaded_dataset = data_reader.load_data() URM_all = loaded_dataset.get_URM_from_name("URM_all") URM_timestamp = loaded_dataset.get_URM_from_name( "URM_timestamp") # make rating implicit URM_all.data = np.ones_like(URM_all.data) URM_train, URM_validation, URM_test, URM_test_negative = split_data_on_timestamp( URM_all, URM_timestamp, negative_items_per_positive=99) else: assert False self.URM_DICT = { "URM_train": URM_train, "URM_test": URM_test, "URM_validation": URM_validation, "URM_test_negative": URM_test_negative, "URM_timestamp": URM_timestamp, } save_data_dict_zip(self.URM_DICT, self.ICM_DICT, pre_splitted_path, pre_splitted_filename) print("{}: Dataset loaded".format(self.DATASET_NAME)) 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): super(PinterestICCVReader, self).__init__() pre_splitted_path = "Data_manager_split_datasets/PinterestICCV/WWW/NeuMF_our_interface/" 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_Pinterest: 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_Pinterest: Pre-splitted data not found, building new one" ) # Ensure file is loaded as matrix Dataset_github.load_rating_file_as_list = Dataset_github.load_rating_file_as_matrix dataset = Dataset_github( "Conferences/WWW/NeuMF_github/Data/pinterest-20") self.URM_train_original, self.URM_test = dataset.trainMatrix, dataset.testRatings self.URM_train_original = self.URM_train_original.tocsr() self.URM_test = self.URM_test.tocsr() from Base.Recommender_utils import reshapeSparse shape = (max(self.URM_train_original.shape[0], self.URM_test.shape[0]), max(self.URM_train_original.shape[1], self.URM_test.shape[1])) self.URM_train_original = reshapeSparse(self.URM_train_original, shape) self.URM_test = reshapeSparse(self.URM_test, shape) URM_test_negatives_builder = IncrementalSparseMatrix( n_rows=shape[0], n_cols=shape[1]) for user_index in range(len(dataset.testNegatives)): user_test_items = dataset.testNegatives[user_index] URM_test_negatives_builder.add_single_row(user_index, user_test_items, data=1.0) self.URM_test_negative = URM_test_negatives_builder.get_SparseMatrix( ) self.URM_train, self.URM_validation = split_train_validation_leave_one_out_user_wise( self.URM_train_original.copy()) data_dict = { "URM_train_original": self.URM_train_original, "URM_train": self.URM_train, "URM_test": self.URM_test, "URM_test_negative": self.URM_test_negative, "URM_validation": self.URM_validation, } save_data_dict(data_dict, pre_splitted_path, pre_splitted_filename) print("Dataset_Pinterest: Dataset loaded") print("N_items {}, n_users {}".format(self.URM_train.shape[1], self.URM_train.shape[0]))
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)