class Hybrid3ScoreSubRecommender(BaseRecommender): """Hybrid3ScoreSubRecommender recommender""" RECOMMENDER_NAME = "Hybrid3ScoreRecommender" def __init__(self, data: DataObject): super(Hybrid3ScoreSubRecommender, self).__init__(data.urm_train) urm = sps.vstack([data.urm_train, data.icm_all_augmented.T]) urm = urm.tocsr() self.slim = SLIMElasticNetRecommender(urm) self.rp3 = RP3betaRecommender(self.URM_train) self.itemcf = ItemKNNCFRecommender(self.URM_train) self.random_seed = data.random_seed def fit(self, alpha_beta_ratio=1, alpha_gamma_ratio=1): try: self.slim.load_model('stored_recommenders/slim_elastic_net/', f'with_icm_{self.random_seed}_topK=100_l1_ratio=0.04705_alpha=0.00115_positive_only=True_max_iter=35') except: self.slim.fit(topK=100, l1_ratio=0.04705, alpha=0.00115, positive_only=True, max_iter=35) self.slim.save_model('stored_recommenders/slim_elastic_net/', f'with_icm_{self.random_seed}_topK=100_l1_ratio=0.04705_alpha=0.00115_positive_only=True_max_iter=35') self.rp3.fit(topK=20, alpha=0.16, beta=0.24) self.itemcf.fit(topK=22, shrink=850, similarity='jaccard', feature_weighting='BM25') self.alpha = 1 self.beta = alpha_beta_ratio self.gamma = alpha_gamma_ratio def _compute_item_score(self, user_id_array, items_to_compute = None): # ATTENTION! # THIS METHOD WORKS ONLY IF user_id_array IS A SCALAR AND NOT AN ARRAY # TODO scores_slim = self.slim._compute_item_score(user_id_array=user_id_array) scores_rp3 = self.rp3._compute_item_score(user_id_array=user_id_array) scores_itemcf = self.itemcf._compute_item_score(user_id_array=user_id_array) # normalization slim_max = scores_slim.max() rp3_max = scores_rp3.max() itemcf_max = scores_itemcf.max() if not slim_max == 0: scores_slim /= slim_max if not rp3_max == 0: scores_rp3 /= rp3_max if not itemcf_max == 0: scores_itemcf /= itemcf_max scores_total = self.alpha * scores_slim + self.beta * scores_rp3 + self.gamma * scores_itemcf return scores_total
class Hybrid3ScoreRecommender(BaseRecommender): """Hybrid3ScoreRecommender recommender""" RECOMMENDER_NAME = "Hybrid3ScoreRecommender" def __init__(self, data: DataObject, random_seed: int, alpha=1): super(Hybrid3ScoreRecommender, self).__init__(data.urm_train) self.random_seed = random_seed urm = sps.vstack([data.urm_train, data.icm_all_augmented.T]) urm = urm.tocsr() self.slim = SLIMElasticNetRecommender(urm) self.rp3 = RP3betaRecommender(urm) self.alpha = alpha def fit(self, alpha_beta_ratio=1, alpha_gamma_ratio=1): try: self.slim.load_model( 'stored_recommenders/slim_elastic_net/', f'with_icm_{self.random_seed}_topK=191_l1_ratio=0.0458089_alpha=0.000707_positive_only=True_max_iter=100' ) except: self.slim.fit(topK=191, l1_ratio=0.0458089, alpha=0.000707, positive_only=True, max_iter=100) self.slim.save_model( 'stored_recommenders/slim_elastic_net/', f'with_icm_{self.random_seed}_topK=191_l1_ratio=0.0458089_alpha=0.000707_positive_only=True_max_iter=100' ) try: self.rp3.load_model( 'stored_recommenders/rp3_beta/', f'with_icm_{self.random_seed}_topK=40_alpha=0.4_beta=0.2') except: self.rp3.fit(topK=40, alpha=0.4, beta=0.2) self.rp3.save_model( 'stored_recommenders/rp3_beta/', f'with_icm_{self.random_seed}_topK=40_alpha=0.4_beta=0.2') # self.alpha = 1 self.beta = self.alpha * alpha_beta_ratio self.gamma = self.alpha * alpha_gamma_ratio def _compute_item_score(self, user_id_array, items_to_compute=None): # ATTENTION! # THIS METHOD WORKS ONLY IF user_id_array IS A SCALAR AND NOT AN ARRAY # TODO scores_slim = self.slim._compute_item_score( user_id_array=user_id_array) scores_rp3 = self.rp3._compute_item_score(user_id_array=user_id_array) # normalization slim_max = scores_slim.max() rp3_max = scores_rp3.max() if not slim_max == 0: scores_slim /= slim_max if not rp3_max == 0: scores_rp3 /= rp3_max scores_total = self.alpha * scores_slim + self.beta * scores_rp3 return scores_total
class LinearHybrid001(BaseItemSimilarityMatrixRecommender): RECOMMENDER_NAME = "LinearHybrid001" # set the seed equal to the one of the parameter search!!!! def __init__(self, URM_train, ICM_train, submission=False, verbose=True, seed=1205): super(LinearHybrid001, self).__init__(URM_train, verbose = verbose) self.URM_train = URM_train self.ICM_train = ICM_train self.__rec1 = SLIMElasticNetRecommender(URM_train, verbose=False) self.__rec1_params = {'topK': 120, 'l1_ratio': 1e-5, 'alpha': 0.066} # seed 1205: 'topK': 620, 'shrink': 121, 'similarity': 'asymmetric', 'normalize': True, 'asymmetric_alpha': 0.5526988987666924 self.__rec2 = ItemKNNCFRecommender(URM_train, verbose=False) self.__rec2_params = {'topK': 620, 'shrink': 121, 'similarity': 'asymmetric', 'normalize': True, 'asymmetric_alpha': 0.5526988987666924} # seed 1205: 'topK': 115, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True, 'feature_weighting': 'BM25' self.__rec3 = ItemKNNCBFRecommender(URM_train, ICM_train, verbose=False) self.__rec3_params = {'topK': 115, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True, 'feature_weighting': 'BM25'} self.__a = self.__b = self.__c = None self.seed=seed self.__submission=submission def fit(self, alpha=0.5, l1_ratio=0.5): self.__a = alpha * l1_ratio self.__b = alpha - self.__a self.__c = 1 - self.__a - self.__b if not self.__submission: try: self.__rec1.load_model('stored_recommenders/'+self.__rec1.RECOMMENDER_NAME+'/', f'seed_{str(self.seed)}_best_for_LinearHybrid001') print(f"{self.__rec1.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {self.__rec1.RECOMMENDER_NAME} ...") self.__rec1.fit(**self.__rec1_params) print(f"done.") self.__rec1.save_model('stored_recommenders/'+self.__rec1.RECOMMENDER_NAME+'/', f'seed_{str(self.seed)}_best_for_LinearHybrid001') try: self.__rec2.load_model('stored_recommenders/'+self.__rec2.RECOMMENDER_NAME+'/', f'seed_{str(self.seed)}_best_for_LinearHybrid001') print(f"{self.__rec2.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {self.__rec2.RECOMMENDER_NAME} ...") self.__rec2.fit(**self.__rec2_params) print(f"done.") self.__rec2.save_model('stored_recommenders/'+self.__rec2.RECOMMENDER_NAME+'/', f'seed_{str(self.seed)}_best_for_LinearHybrid001') try: self.__rec3.load_model('stored_recommenders/'+self.__rec3.RECOMMENDER_NAME+'/', f'seed_{str(self.seed)}_best_for_LinearHybrid001') print(f"{self.__rec3.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {self.__rec3.RECOMMENDER_NAME} ...") self.__rec3.fit(**self.__rec3_params) print(f"done.") self.__rec3.save_model('stored_recommenders/'+self.__rec3.RECOMMENDER_NAME+'/', f'seed_{str(self.seed)}_best_for_LinearHybrid001') else: self.__rec1.fit(**self.__rec1_params) self.__rec2.fit(**self.__rec2_params) self.__rec3.fit(**self.__rec3_params) def _compute_item_score(self, user_id_array, items_to_compute=None): item_weights_1 = self.__rec1._compute_item_score(user_id_array) item_weights_2 = self.__rec2._compute_item_score(user_id_array) item_weights_3 = self.__rec3._compute_item_score(user_id_array) item_weights = item_weights_1 * self.__a + item_weights_2 * self.__b + item_weights_3 * self.__c return item_weights def save_model(self, folder_path, file_name = None): if file_name is None: file_name = self.RECOMMENDER_NAME self._print("Saving model in file '{}'".format(folder_path + file_name)) dataIO = DataIO(folder_path=folder_path) dataIO.save_data(file_name=file_name, data_dict_to_save = {}) self._print("Saving complete")
def __init__(self, URM_train, ICM_train, submission=False, verbose=True, seed=1205): super(LinearOverMerged001, self).__init__(URM_train, verbose=verbose) self.URM_train = URM_train self.ICM_train = ICM_train self.__submission = submission self.__rec1 = UserKNNCFRecommender(URM_train, verbose=False) self.__rec1_params = { 'topK': 190, 'shrink': 0, 'similarity': 'cosine', 'normalize': True } self.seed = seed icb = ItemKNNCBFRecommender(URM_train, ICM_train, verbose=False) icb_params = { 'topK': 65, 'shrink': 0, 'similarity': 'dice', 'normalize': True } rp3b = RP3betaRecommender(URM_train, verbose=False) rp3b_params = { 'topK': 1000, 'alpha': 0.38192761611274967, 'beta': 0.0, 'normalize_similarity': False } sen = SLIMElasticNetRecommender(URM_train, verbose=False) sen_params = { 'topK': 992, 'l1_ratio': 0.004065081925341167, 'alpha': 0.003725005053334143 } if not self.__submission: try: icb.load_model( f'stored_recommenders/seed_{str(self.seed)}_{icb.RECOMMENDER_NAME}/', f'best_for_{self.RECOMMENDER_NAME}') print(f"{icb.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {icb.RECOMMENDER_NAME} ...") icb.fit(**icb_params) print(f"done.") icb.save_model( f'stored_recommenders/seed_{str(self.seed)}_{icb.RECOMMENDER_NAME}/', f'best_for_{self.RECOMMENDER_NAME}') try: rp3b.load_model( f'stored_recommenders/seed_{str(self.seed)}_{rp3b.RECOMMENDER_NAME}/', f'best_for_{self.RECOMMENDER_NAME}') print(f"{rp3b.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {rp3b.RECOMMENDER_NAME} ...") rp3b.fit(**rp3b_params) print(f"done.") rp3b.save_model( f'stored_recommenders/seed_{str(self.seed)}_{rp3b.RECOMMENDER_NAME}/', f'best_for_{self.RECOMMENDER_NAME}') try: sen.load_model( f'stored_recommenders/seed_{str(self.seed)}_{sen.RECOMMENDER_NAME}/', f'best_for_{self.RECOMMENDER_NAME}') print(f"{sen.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {sen.RECOMMENDER_NAME} ...") sen.fit(**sen_params) print(f"done.") sen.save_model( f'stored_recommenders/seed_{str(self.seed)}_{sen.RECOMMENDER_NAME}/', f'best_for_{self.RECOMMENDER_NAME}') else: icb.fit(**icb_params) rp3b.fit(**rp3b_params) sen.fit(**sen_params) self.__rec2 = HiddenMergedRecommender(URM_train, ICM_train, [icb, rp3b, sen], verbose=False) self.__rec2_params = { 'alpha': 0.6355738550417837, 'l1_ratio': 0.6617849709204384, 'topK': 538 } self.__a = self.__b = None
def read_data_split_and_search(): """ This function provides a simple example on how to tune parameters of a given algorithm The BayesianSearch object will save: - A .txt file with all the cases explored and the recommendation quality - A _best_model file which contains the trained model and can be loaded with recommender.load_model() - A _best_parameter file which contains a dictionary with all the fit parameters, it can be passed to recommender.fit(**_best_parameter) - A _best_result_validation file which contains a dictionary with the results of the best solution on the validation - A _best_result_test file which contains a dictionary with the results, on the test set, of the best solution chosen using the validation set """ seed = 1205 parser = DataParser() URM_all = parser.get_URM_all() ICM_obj = parser.get_ICM_all() # SPLIT TO GET TEST PARTITION URM_train, URM_test = split_train_in_two_percentage_global_sample(URM_all, train_percentage=0.90, seed=seed) # SPLIT TO GET THE HYBRID VALID PARTITION URM_train, URM_valid_hybrid = split_train_in_two_percentage_global_sample(URM_train, train_percentage=0.85, seed=seed) collaborative_algorithm_list = [ # EASE_R_Recommender # PipeHybrid001, # Random, # TopPop, # P3alphaRecommender, # RP3betaRecommender, # ItemKNNCFRecommender, # UserKNNCFRecommender, # MatrixFactorization_BPR_Cython, # MatrixFactorization_FunkSVD_Cython, # PureSVDRecommender, # NMFRecommender, # PureSVDItemRecommender # SLIM_BPR_Cython, # SLIMElasticNetRecommender # IALSRecommender # MF_MSE_PyTorch # MergedHybrid000 # LinearHybrid002ggg HybridCombinationSearch ] content_algorithm_list = [ # ItemKNNCBFRecommender ] from Base.Evaluation.Evaluator import EvaluatorHoldout evaluator_valid_hybrid = EvaluatorHoldout(URM_valid_hybrid, cutoff_list=[10]) evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10]) """ earlystopping_keywargs = {"validation_every_n": 5, "stop_on_validation": True, "evaluator_object": evaluator_valid_hybrid, "lower_validations_allowed": 5, "validation_metric": 'MAP', } print('IALS training...') ials = IALSRecommender(URM_train, verbose=False) ials_params = {'num_factors': 83, 'confidence_scaling': 'linear', 'alpha': 28.4278070726612, 'epsilon': 1.0234211788885077, 'reg': 0.0027328110246575004, 'epochs': 20} ials.fit(**ials_params, **earlystopping_keywargs) print("Done") print("PureSVD training...") psvd = PureSVDRecommender(URM_train, verbose=False) psvd_params = {'num_factors': 711} psvd.fit(**psvd_params) print("Done") """ rp3b = RP3betaRecommender(URM_train, verbose=False) rp3b_params = {'topK': 1000, 'alpha': 0.38192761611274967, 'beta': 0.0, 'normalize_similarity': False} try: rp3b.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{rp3b.RECOMMENDER_NAME}_for_second_search') print(f"{rp3b.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {rp3b.RECOMMENDER_NAME} ...") rp3b.fit(**rp3b_params) print(f"done.") rp3b.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{rp3b.RECOMMENDER_NAME}_for_second_search') p3a = P3alphaRecommender(URM_train, verbose=False) p3a_params = {'topK': 131, 'alpha': 0.33660811631883863, 'normalize_similarity': False} try: p3a.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{p3a.RECOMMENDER_NAME}_for_second_search') print(f"{p3a.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {p3a.RECOMMENDER_NAME} ...") p3a.fit(**p3a_params) print(f"done.") p3a.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{p3a.RECOMMENDER_NAME}_for_second_search') icf = ItemKNNCFRecommender(URM_train, verbose=False) icf_params = {'topK': 55, 'shrink': 1000, 'similarity': 'asymmetric', 'normalize': True, 'asymmetric_alpha': 0.0} try: icf.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{icf.RECOMMENDER_NAME}_for_second_search') print(f"{icf.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {icf.RECOMMENDER_NAME} ...") icf.fit(**icf_params) print(f"done.") icf.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{icf.RECOMMENDER_NAME}_for_second_search') ucf = UserKNNCFRecommender(URM_train, verbose=False) ucf_params = {'topK': 190, 'shrink': 0, 'similarity': 'cosine', 'normalize': True} try: ucf.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{ucf.RECOMMENDER_NAME}_for_second_search') print(f"{ucf.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {ucf.RECOMMENDER_NAME} ...") ucf.fit(**ucf_params) print(f"done.") ucf.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{ucf.RECOMMENDER_NAME}_for_second_search') icb = ItemKNNCBFRecommender(URM_train, ICM_obj, verbose=False) icb_params = {'topK': 65, 'shrink': 0, 'similarity': 'dice', 'normalize': True} try: icb.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{icb.RECOMMENDER_NAME}_for_second_search') print(f"{icb.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {icf.RECOMMENDER_NAME} ...") icb.fit(**icb_params) print(f"done.") icb.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{icb.RECOMMENDER_NAME}_for_second_search') sen = SLIMElasticNetRecommender(URM_train, verbose=False) sen_params = {'topK': 992, 'l1_ratio': 0.004065081925341167, 'alpha': 0.003725005053334143} try: sen.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{sen.RECOMMENDER_NAME}_for_second_search') print(f"{sen.RECOMMENDER_NAME} loaded.") except: print(f"Fitting {sen.RECOMMENDER_NAME} ...") sen.fit(**sen_params) print(f"done.") sen.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/', f'{sen.RECOMMENDER_NAME}_for_second_search') print("\nStart.") list_recommender = [icb, icf, ucf, p3a, rp3b, sen] list_already_seen = [] combinations_already_seen = [] """ (icb, icf, p3a), (icb, icf, rp3b), (icb, icf, sen), (icb, p3a, rp3b), (icb, p3a, sen), (icb, rp3b, sen), (icf, p3a, rp3b), (icf, p3a, sen) """ for rec_perm in combinations(list_recommender, 3): if rec_perm not in combinations_already_seen: recommender_names = '_'.join([r.RECOMMENDER_NAME for r in rec_perm]) output_folder_path = "result_experiments_v3/seed_" + str( seed) + '/linear_combination/' + recommender_names + '/' print(F"\nTESTING THE COMBO {recommender_names}") # If directory does not exist, create if not os.path.exists(output_folder_path): os.makedirs(output_folder_path) # TODO: setta I GIUSTI EVALUATOR QUI!!!! runParameterSearch_Collaborative_partial = partial(runParameterSearch_Collaborative, URM_train=URM_train, ICM_train=ICM_obj, metric_to_optimize="MAP", n_cases=50, n_random_starts=20, evaluator_validation_earlystopping=evaluator_valid_hybrid, evaluator_validation=evaluator_valid_hybrid, #evaluator_test=evaluator_test, output_folder_path=output_folder_path, allow_weighting=False, # similarity_type_list = ["cosine", 'jaccard'], parallelizeKNN=False, list_rec=rec_perm) pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1) pool.map(runParameterSearch_Collaborative_partial, collaborative_algorithm_list)
import numpy as np import os import scipy.sparse as sps from DataParser import DataParser from Data_manager.split_functions.split_train_validation_random_holdout import \ split_train_in_two_percentage_global_sample from SLIM_ElasticNet.SLIMElasticNetRecommender import SLIMElasticNetRecommender if __name__ == '__main__': parser = DataParser() URM_all = parser.get_URM_all() random_seed = 1205 URM_train, URM_test = split_train_in_two_percentage_global_sample(URM_all, train_percentage=0.85, seed=random_seed) slim = SLIMElasticNetRecommender(URM_train) slim.fit(topK=140, l1_ratio=1e-5, alpha=0.386) slim.save_model('stored_recommenders/slim_elastic_net/', f'best_{random_seed}_23_10_20')