def __init__(self, urm_train, eurm=False):
super(HybridGenRecommender, self).__init__(urm_train)
self.data_folder = Path(__file__).parent.parent.absolute()
self.eurm = eurm
self.num_users = urm_train.shape[0]
data = DataManager()
urm_train = check_matrix(urm_train.copy(), 'csr')
icm_price, icm_asset, icm_sub, icm_all = data.get_icm()
ucm_age, ucm_region, ucm_all = data.get_ucm()
recommender_1 = ItemKNNCBFRecommender(urm_train, icm_all)
recommender_1.fit(shrink=40, topK=20, feature_weighting='BM25')
# recommender_2 = UserKNNCBFRecommender(urm_train, ucm_all)
# recommender_2.fit(shrink=500, topK=1600, normalize=True)
recommender_2 = UserKNNCBFRecommender(urm_train, ucm_all)
recommender_2.fit(shrink=1777,
topK=1998,
similarity='tversky',
feature_weighting='BM25',
tversky_alpha=0.1604953616,
tversky_beta=0.9862348646)
self.recommender_1 = recommender_1
self.recommender_2 = recommender_2
def __init__(self,
data: DataObject,
k: int,
leave_k_out=0,
threshold=0,
probability=0.2):
super(Hybrid400AlphaRecommender, self).__init__(data.urm_train)
self.data = data
self.max_cutoff = 30
rec = ItemKNNCBFRecommender(data.urm_train, data.icm_all_augmented)
rec.fit(topK=10)
print(f"Not augmented {data.augmented_urm.nnz}")
data.augmented_urm = augment_with_item_similarity_best_scores(
data.augmented_urm,
rec.W_sparse,
500,
value=0.3,
remove_seen=False)
# print(f"After User CBF {data.augmented_urm.nnz}")
# data.augmented_urm = augment_with_best_recommended_items(data.augmented_urm, rec,
# data.urm_train_users_by_type[1][1], 1, value=0.2)
#
print(f"After Item CBF {data.augmented_urm.nnz}")
rec = Hybrid100AlphaRecommender(data)
rec.fit()
data.augmented_urm = augment_with_best_recommended_items(
data.augmented_urm,
rec,
data.urm_train_users_by_type[0][1],
1,
value=1)
# data.augmented_urm = augment_with_best_recommended_items(data.augmented_urm, rec,
# data.ids_warm_train_users, 2, value=0.1)
print(f"After User CBF {data.augmented_urm.nnz}")
# print(f"After User CBF {data.augmented_urm.nnz}")
rec = None
recs = Parallel(n_jobs=6)(delayed(
par(data,
leave_k_out=leave_k_out,
threshold=threshold,
probability=probability).split_and_fit)(i) for i in range(k))
self.hybrid_rec = Hybrid1CXAlphaRecommender(
data,
recommenders=recs,
recommended_users=data.ids_user,
max_cutoff=self.max_cutoff)
self.hybrid_rec.weights = np.array([
np.sqrt(np.array(fib(30)[::-1])).astype(np.int).tolist()
for _ in range(k)
])
class ItemKNNCBFOnlyColdRecommender(BaseSimilarityMatrixRecommender):
def __init__(self, data):
super(ItemKNNCBFOnlyColdRecommender, self).__init__(data.urm_train)
self.rec = ItemKNNCBFRecommender(data.urm_train, data.icm_all_augmented)
self.cold_item = np.concatenate((data.ids_cold_train_items, data.ids_cold_item))
self.data = data
def _compute_item_score_postprocess_for_cold_items(self, item_scores):
"""
In CBF no cold items are to be removed
:param item_scores:
:return:
"""
return item_scores
def fit(self, topK=50, shrink=100, similarity='cosine', normalize=True, feature_weighting="none",
**similarity_args):
self.rec.fit(topK=topK, shrink=shrink, similarity=similarity, normalize=normalize,
feature_weighting=feature_weighting, **similarity_args)
# def recommend(self, user_id_array, cutoff=None, remove_seen_flag=True, items_to_compute=None,
# remove_top_pop_flag=False, remove_CustomItems_flag=False, return_scores=False):
# recommended_items = self.rec.recommend(user_id_array=user_id_array, cutoff=cutoff, remove_seen_flag=False)
# recommended_items = np.array([x for x in recommended_items if
# x in self.cold_item and x not in self.data.urm_train[user_id_array].indices])
# recommended_items = np.pad(recommended_items, (0, cutoff - recommended_items.shape[0]), 'constant', constant_values=-1)
# return recommended_items
# no pad
def recommend(self, user_id_array, cutoff=None, remove_seen_flag=True, items_to_compute=None,
remove_top_pop_flag=False, remove_CustomItems_flag=False, return_scores=False):
recommended_items = self.rec.recommend(user_id_array=user_id_array, cutoff=cutoff, remove_seen_flag=False)
recommended_items = np.array([x for x in recommended_items if
x in self.cold_item and x not in self.data.urm_train[user_id_array].indices])
return recommended_items
class PipeHybrid001(RP3betaRecommender):
RECOMMENDER_NAME = "PipeHybrid001"
def __init__(self, URM_train, ICM_train,verbose=True):
super(PipeHybrid001, self).__init__(URM_train, verbose = verbose)
self.URM_train_recommendation = URM_train
self.ICM_train = ICM_train
self.__content_recommender = ItemKNNCBFRecommender(URM_train, ICM_train)
#print("fitting ItemKNNCBF...")
try:
self.__content_recommender.load_model('stored_recommenders/ItemKNNCBFRecommender/best_at_26_10_20')
except:
self.__content_recommender.fit(topK=140, shrink=1000, similarity='cosine', normalize=True,
feature_weighting='BM25') # best parameter up to now
self.__content_recommender.save_model('stored_recommenders/ItemKNNCBFRecommender/best_at_26_10_20')
#print("... done")
#print(f"URM_train shape: {URM_train.shape}")
#print(f"W_sparse knn shape: {self.__content_recommender.W_sparse.shape}")
self.URM_train = URM_train.dot(self.__content_recommender.W_sparse)
self._URM_train_format_checked = False
self._W_sparse_format_checked = False
def recommend(self, user_id_array, cutoff = None, remove_seen_flag=True, items_to_compute = None,
remove_top_pop_flag = False, remove_custom_items_flag = False, return_scores = False):
"""
redefinition using self.URM_train_recommendation, not the new URM train of the RP3Beta algorithm
"""
# If is a scalar transform it in a 1-cell array
if np.isscalar(user_id_array):
user_id_array = np.atleast_1d(user_id_array)
single_user = True
else:
single_user = False
if cutoff is None:
cutoff = self.URM_train_recommendation.shape[1] - 1
# Compute the scores using the model-specific function
# Vectorize over all users in user_id_array
scores_batch = self._compute_item_score(user_id_array, items_to_compute=items_to_compute)
for user_index in range(len(user_id_array)):
user_id = user_id_array[user_index]
if remove_seen_flag:
scores_batch[user_index,:] = self._remove_seen_on_scores(user_id, scores_batch[user_index, :])
# Sorting is done in three steps. Faster then plain np.argsort for higher number of items
# - Partition the data to extract the set of relevant items
# - Sort only the relevant items
# - Get the original item index
# relevant_items_partition = (-scores_user).argpartition(cutoff)[0:cutoff]
# relevant_items_partition_sorting = np.argsort(-scores_user[relevant_items_partition])
# ranking = relevant_items_partition[relevant_items_partition_sorting]
#
# ranking_list.append(ranking)
if remove_top_pop_flag:
scores_batch = self._remove_TopPop_on_scores(scores_batch)
if remove_custom_items_flag:
scores_batch = self._remove_custom_items_on_scores(scores_batch)
# relevant_items_partition is block_size x cutoff
relevant_items_partition = (-scores_batch).argpartition(cutoff, axis=1)[:,0:cutoff]
# Get original value and sort it
# [:, None] adds 1 dimension to the array, from (block_size,) to (block_size,1)
# This is done to correctly get scores_batch value as [row, relevant_items_partition[row,:]]
relevant_items_partition_original_value = scores_batch[np.arange(scores_batch.shape[0])[:, None], relevant_items_partition]
relevant_items_partition_sorting = np.argsort(-relevant_items_partition_original_value, axis=1)
ranking = relevant_items_partition[np.arange(relevant_items_partition.shape[0])[:, None], relevant_items_partition_sorting]
ranking_list = [None] * ranking.shape[0]
# Remove from the recommendation list any item that has a -inf score
# Since -inf is a flag to indicate an item to remove
for user_index in range(len(user_id_array)):
user_recommendation_list = ranking[user_index]
user_item_scores = scores_batch[user_index, user_recommendation_list]
not_inf_scores_mask = np.logical_not(np.isinf(user_item_scores))
user_recommendation_list = user_recommendation_list[not_inf_scores_mask]
ranking_list[user_index] = user_recommendation_list.tolist()
#TEST
"""
user_profile_array = self.URM_train[user_id_array[user_index]]
if np.empty(user_profile_array):
print(f"WARNING! {user_index} is a cold user!")
rec = TopPop(URM_train)
rec.fit()
ranking_list[user_index]=rec.recommend([user_id_array[user_index]], cutoff=cutoff)
"""
# Return single list for one user, instead of list of lists
if single_user:
ranking_list = ranking_list[0]
if return_scores:
return ranking_list, scores_batch
else:
return ranking_list
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)}_{ucf.RECOMMENDER_NAME}/', 'for_notebook_analysis')
icb = ItemKNNCBFRecommender(URM_train, ICM_all, verbose=False)
icb_params = {'topK': 65, 'shrink': 0, 'similarity': 'dice', 'normalize': True}
try:
icb.load_model(f'stored_recommenders/seed_{str(seed)}_{icb.RECOMMENDER_NAME}/', 'for_notebook_analysis')
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(seed)}_{icb.RECOMMENDER_NAME}/', 'for_notebook_analysis')
list_recommender = [sslim, icb, ucf]
best_recommender = HybridCombinationSearch(URM_train, ICM_all, list_recommender)
params = {'alpha': 0.6461624491197696, 'l1_ratio': 0.7617220099582368}
best_recommender.fit(**params)
user_ids = parser.get_ratings().user_id.unique()
cutoff = 20
user_recommendations_items = []
user_recommendations_user_id = []
target = []
for n_user in user_ids:
def hybrid_repo(is_test):
b = Builder()
ev = Evaluator()
ev.split()
ICM = b.build_ICM()
URM_train, URM_test = train_test_holdout(b.get_URM(), train_perc=0.8)
URM_train, URM_validation = train_test_holdout(URM_train, train_perc=0.9)
from ParameterTuning.AbstractClassSearch import EvaluatorWrapper
from Base.Evaluation.Evaluator import SequentialEvaluator
evaluator_validation = SequentialEvaluator(URM_validation, cutoff_list=[5])
evaluator_test = SequentialEvaluator(URM_test, cutoff_list=[5, 10])
evaluator_validation = EvaluatorWrapper(evaluator_validation)
evaluator_test = EvaluatorWrapper(evaluator_test)
from KNN.ItemKNNCFRecommender import ItemKNNCFRecommender
from ParameterTuning.BayesianSearch import BayesianSearch
recommender_class = ItemKNNCFRecommender
parameterSearch = BayesianSearch(recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
from ParameterTuning.AbstractClassSearch import DictionaryKeys
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800
]
hyperparamethers_range_dictionary["shrink"] = [
0, 10, 50, 100, 200, 300, 500, 1000
]
hyperparamethers_range_dictionary["similarity"] = ["cosine"]
hyperparamethers_range_dictionary["normalize"] = [True, False]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS: dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
output_root_path = "result_experiments/"
import os
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
output_root_path += recommender_class.RECOMMENDER_NAME
n_cases = 2
metric_to_optimize = "MAP"
best_parameters = parameterSearch.search(recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path,
metric=metric_to_optimize)
itemKNNCF = ItemKNNCFRecommender(URM_train)
itemKNNCF.fit(**best_parameters)
from FW_Similarity.CFW_D_Similarity_Linalg import CFW_D_Similarity_Linalg
n_cases = 2
metric_to_optimize = "MAP"
best_parameters_ItemKNNCBF = parameterSearch.search(
recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path,
metric=metric_to_optimize)
itemKNNCBF = ItemKNNCBFRecommender(ICM, URM_train)
itemKNNCBF.fit(**best_parameters_ItemKNNCBF)
"""
#_____________________________________________________________________
from ParameterTuning.BayesianSearch import BayesianSearch
from ParameterTuning.AbstractClassSearch import DictionaryKeys
from ParameterTuning.AbstractClassSearch import EvaluatorWrapper
evaluator_validation_tuning = EvaluatorWrapper(evaluator_validation)
evaluator_test_tuning = EvaluatorWrapper(evaluator_test)
recommender_class = CFW_D_Similarity_Linalg
parameterSearch = BayesianSearch(recommender_class,
evaluator_validation=evaluator_validation_tuning,
evaluator_test=evaluator_test_tuning)
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800]
hyperparamethers_range_dictionary["add_zeros_quota"] = range(0, 1)
hyperparamethers_range_dictionary["normalize_similarity"] = [True, False]
recommenderDictionary = {DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train, ICM, itemKNNCF.W_sparse],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS: dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS: hyperparamethers_range_dictionary}
output_root_path = "result_experiments/"
import os
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
output_root_path += recommender_class.RECOMMENDER_NAME
n_cases = 2
metric_to_optimize = "MAP"
best_parameters_CFW_D = parameterSearch.search(recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path,
metric=metric_to_optimize)
CFW_weithing = CFW_D_Similarity_Linalg(URM_train, ICM, itemKNNCF.W_sparse)
CFW_weithing.fit(**best_parameters_CFW_D)
#___________________________________________________________________________________________-
"""
from GraphBased.P3alphaRecommender import P3alphaRecommender
P3alpha = P3alphaRecommender(URM_train)
P3alpha.fit()
from MatrixFactorization.PureSVD import PureSVDRecommender
#pureSVD = PureSVDRecommender(URM_train)
#pureSVD.fit()
rec = HybridRec.HybridRec()
S_UCM = b.get_S_UCM_KNN(b.get_UCM(ev.get_URM_train()), 600)
S_ICM = b.build_S_ICM_knn(b.build_ICM(), 250)
rec.fit(ev.get_URM_train(),
ev.get_target_playlists(),
ev.get_target_tracks(),
ev.num_playlists_to_test,
itemKNNCBF.W_sparse,
itemKNNCF.W_sparse,
P3alpha.W_sparse,
is_test=True,
alfa=0.7,
avg=0.3)
train_df = rec.recommend()
if is_test:
map5 = ev.map5(train_df)
print('Hybrid MAP@10:', map5)
return map5
else:
print('Prediction saved!')
train_df.to_csv(os.path.dirname(os.path.realpath(__file__))[:-19] +
"/all/sub.csv",
sep=',',
index=False)
return 0
#hybridrecommender = ItemKNNSimilarityHybridRecommender(URM_train, itemKNNCF.W_sparse, P3alpha.W_sparse)
#hybridrecommender.fit(alpha=0.5)
#print(evaluator_validation.evaluateRecommender(hybridrecommender))
"""
# URM_train, URM_test = splitURM(URM_all)
ICM_all = sps.load_npz('myFiles/ICM_all.npz')
URM_train = sps.load_npz('myFiles/Train_for_main.npz')
URM_test = sps.load_npz('myFiles/Test_for_main.npz')
# sps.save_npz('myFiles/URM_all.npz', URM_all, compressed=True)
# sps.save_npz('MyFiles/Train_for_main.npz', URM_train, compressed=True)
# sps.save_npz('MyFiles/Test_for_main.npz', URM_test, compressed=True)
URM_train = URM_train.tocsr()
URM_test = URM_test.tocsr()
# recommenderICF = ItemKNNCFRecommender(URM_train)
# recommenderICF.fit(shrink=30, topK=10, similarity='jaccard', normalize=True)
recommenderCB = ItemKNNCBFRecommender(URM_train, ICM_all)
recommenderCB.fit(shrink=112.2, topK=5, normalize=True, similarity='jaccard')
# recommenderTP = TopPopRecommender()
# recommenderTP.fit(URM_train)
# recommenderGRAPH = P3alphaRecommender(URM_train)
# recommenderGRAPH.fit(topK=10, alpha=0.22, implicit=True, normalize_similarity=True)
# recommenderBetaGRAPH = RP3betaRecommender(URM_train)
# recommenderBetaGRAPH.fit(topK=54, implicit=True, normalize_similarity=True, alpha=1e-6, beta=0.2, min_rating=0)
# recommenderSLIMELASTIC = SLIMElasticNetRecommender(URM_all)
# recommenderSLIMELASTIC.fit(topK=10, alpha=1e-4)
# recommenderSLIMELASTIC.save_model('model/', file_name='SLIM_ElasticNet')
# recommenderCYTHON = SLIM_BPR_Cython(URM_train, recompile_cython=False)
class LinearHybridC001(BaseItemSimilarityMatrixRecommender):
RECOMMENDER_NAME = "LinearHybridC001"
"""
This hybrid works for users who have a profile length shorter or equal to 2 interactions
"""
# 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(LinearHybridC001, self).__init__(URM_train, verbose=verbose)
self.URM_train = URM_train
self.ICM_train = ICM_train
# seed 1205: {'num_factors': 83, 'confidence_scaling': 'linear', 'alpha': 28.4278070726612, 'epsilon':
# 1.0234211788885077, 'reg': 0.0027328110246575004, 'epochs': 20}
self.__rec1 = IALSRecommender(URM_train, verbose=False)
self.__rec1_params = {
'num_factors': 83,
'confidence_scaling': 'linear',
'alpha': 28.4278070726612,
'epsilon': 1.0234211788885077,
'reg': 0.0027328110246575004,
'epochs': 15
} #### -5!!
# seed 1205: {'topK': 225, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True, 'feature_weighting':
# 'BM25'}
self.__rec2 = ItemKNNCBFRecommender(URM_train,
ICM_train,
verbose=False)
self.__rec2_params = {
'topK': 225,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
# seed 1205: {'topK': 220, 'shrink': 175, 'similarity': 'cosine', 'normalize': False}
self.__rec3 = ItemKNNCFRecommender(URM_train, verbose=False)
self.__rec3_params = {
'topK': 220,
'shrink': 175,
'similarity': 'cosine',
'normalize': False
}
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec2.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec3.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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")
evaluator_validation = EvaluatorHoldout(URM_validation, cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
itemKNNCF = ItemKNNCFRecommender(URM_train)
itemKNNCF.fit(shrink=24, topK=10)
recommenderCYTHON = SLIM_BPR_Cython(URM_train, recompile_cython=False)
recommenderCYTHON.fit(epochs=2000,
batch_size=200,
sgd_mode='sdg',
learning_rate=1e-5,
topK=10)
recommenderCB = ItemKNNCBFRecommender(URM_train, ICM_all)
recommenderCB.fit(shrink=24, topK=10)
recommenderELASTIC = SLIMElasticNetRecommender(URM_train)
# recommenderELASTIC.fit(topK=10)
# recommenderELASTIC.save_model('model/', file_name='SLIM_ElasticNet')
recommenderELASTIC.load_model('model/', file_name='SLIM_ElasticNet_train')
# recommenderAlphaGRAPH = P3alphaRecommender(URM_train)
# recommenderAlphaGRAPH.fit(topK=10, alpha=0.22, implicit=True, normalize_similarity=True)
recommenderBetaGRAPH = RP3betaRecommender(URM_train)
recommenderBetaGRAPH.fit(topK=10,
implicit=True,
normalize_similarity=True,
alpha=0.41,
beta=0.049)
class LinearHybrid008(BaseItemSimilarityMatrixRecommender):
RECOMMENDER_NAME = "LinearHybrid008"
# 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(LinearHybrid008, self).__init__(URM_train, verbose=verbose)
self.URM_train = URM_train
self.ICM_train = ICM_train
self.__rec1 = SSLIMElasticNet(URM_train, ICM_train, verbose=False)
self.__rec1_params = {
'beta': 0.4849594591575789,
'topK': 1000,
'l1_ratio': 1e-05,
'alpha': 0.001
}
self.__rec2 = ItemKNNCBFRecommender(URM_train,
ICM_train,
verbose=False)
self.__rec2_params = {
'topK': 65,
'shrink': 0,
'similarity': 'dice',
'normalize': True
}
self.__rec3 = UserKNNCFRecommender(URM_train, verbose=False)
self.__rec3_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec2.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec3.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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)
# normalization
item_weights_1_max = item_weights_1.max()
item_weights_2_max = item_weights_2.max()
item_weights_3_max = item_weights_3.max()
if not item_weights_1_max == 0:
item_weights_1 /= item_weights_1_max
if not item_weights_2_max == 0:
item_weights_2 /= item_weights_2_max
if not item_weights_3_max == 0:
item_weights_3 /= item_weights_3_max
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, eurm=False):
super(HybridNormOrigRecommender, self).__init__(urm_train)
self.data_folder = Path(__file__).parent.parent.absolute()
self.eurm = eurm
self.num_users = urm_train.shape[0]
data = DataManager()
urm_train = check_matrix(urm_train.copy(), 'csr')
icm_price, icm_asset, icm_sub, icm_all = data.get_icm()
ucm_age, ucm_region, ucm_all = data.get_ucm()
recommender_1 = ItemKNNCBFRecommender(urm_train, icm_all)
recommender_1.fit(shrink=40, topK=20, feature_weighting='BM25')
recommender_7 = UserKNNCBFRecommender(urm_train, ucm_all)
recommender_7.fit(shrink=1777,
topK=1998,
similarity='tversky',
feature_weighting='BM25',
tversky_alpha=0.1604953616,
tversky_beta=0.9862348646)
# recommender_1 = HybridGenRecommender(urm_train, eurm=self.eurm)
# recommender_1.fit()
# recommender_2 = ItemKNNCFRecommender(urm_train)
# recommender_2.fit(shrink=30, topK=20)
recommender_2 = ItemKNNCFRecommender(urm_train)
recommender_2.fit(topK=5,
shrink=500,
feature_weighting='BM25',
similarity='tversky',
normalize=False,
tversky_alpha=0.0,
tversky_beta=1.0)
recommender_3 = UserKNNCFRecommender(urm_train)
recommender_3.fit(shrink=2, topK=600, normalize=True)
# recommender_3 = UserKNNCFRecommender(urm_train)
# recommender_3.fit(topK=697, shrink=1000, feature_weighting='TF-IDF', similarity='tversky', normalize=False,
# tversky_alpha=1.0, tversky_beta=1.0)
recommender_4 = RP3betaRecommender(urm_train)
recommender_4.fit(topK=16,
alpha=0.03374950051351756,
beta=0.24087176329409027,
normalize_similarity=False)
recommender_5 = SLIM_BPR_Cython(urm_train)
recommender_5.fit(lambda_i=0.0926694015,
lambda_j=0.001697250,
learning_rate=0.002391,
epochs=65,
topK=200)
recommender_6 = ALSRecommender(urm_train)
recommender_6.fit(alpha=5, iterations=40, reg=0.3)
self.recommender_1 = recommender_1
self.recommender_2 = recommender_2
self.recommender_3 = recommender_3
self.recommender_4 = recommender_4
self.recommender_5 = recommender_5
self.recommender_6 = recommender_6
self.recommender_7 = recommender_7
if self.eurm:
if Path(self.data_folder / 'Data/uicm_orig_sparse.npz').is_file():
print("Previous uicm_sparse found")
self.score_matrix_1 = sps.load_npz(self.data_folder /
'Data/uicm_sparse.npz')
else:
print("uicm_sparse not found, create new one...")
self.score_matrix_1 = self.recommender_1._compute_item_matrix_score(
np.arange(self.num_users))
sps.save_npz(self.data_folder / 'Data/uicm_orig_sparse.npz',
self.score_matrix_1)
self.score_matrix_2 = self.recommender_2._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_3 = self.recommender_3._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_4 = self.recommender_4._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_5 = self.recommender_5._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_6 = self.recommender_6._compute_item_score(
np.arange(self.num_users))
self.score_matrix_1 = normalize(self.score_matrix_2,
norm='max',
axis=1)
self.score_matrix_2 = normalize(self.score_matrix_2,
norm='max',
axis=1)
self.score_matrix_3 = normalize(self.score_matrix_3,
norm='max',
axis=1)
self.score_matrix_4 = normalize(self.score_matrix_4,
norm='max',
axis=1)
self.score_matrix_5 = normalize(self.score_matrix_5,
norm='max',
axis=1)
self.score_matrix_6 = normalize(self.score_matrix_6,
norm='max',
axis=1)
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)
if __name__ == '__main__':
seed = 1205
parser = DataParser()
URM_all = parser.get_URM_all()
ICM_all = parser.get_ICM_all()
URM_train, URM_test = split_train_in_two_percentage_global_sample(
URM_all, train_percentage=0.85, seed=seed)
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
rec1 = ItemKNNCBFRecommender(URM_train, ICM_all)
rec2 = SLIMElasticNetRecommender(URM_train)
# 'topK': 40, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True, 'feature_weighting': 'BM25'
rec1.fit(topK=40,
shrink=1000,
similarity='cosine',
feature_weighting='BM25')
# topK': 140, 'l1_ratio': 1e-05, 'alpha': 0.386
rec2.fit(topK=140, l1_ratio=1e-5, alpha=0.386)
print("recomenders are ready")
merged_recommender = MergedHybrid000(URM_train,
content_recommender=rec1,
collaborative_recommender=rec2)
for alpha in np.arange(0, 1, 0.1):
merged_recommender.fit(alpha)
result, _ = evaluator_test.evaluateRecommender(merged_recommender)
print(alpha, result[10]['MAP'])
class LinearHybrid003(BaseItemSimilarityMatrixRecommender):
RECOMMENDER_NAME = "LinearHybrid003"
# 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(LinearHybrid003, self).__init__(URM_train, verbose=verbose)
self.URM_train = URM_train
self.ICM_train = ICM_train
# seed 1205: 'topK': 190, 'shrink': 0, 'similarity': 'cosine', 'normalize': True
self.__rec1 = UserKNNCFRecommender(URM_train, verbose=False)
self.__rec1_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
self.__rec2 = P3alphaRecommender(URM_train, verbose=False)
self.__rec2_params = {
'topK': 131,
'alpha': 0.33660811631883863,
'normalize_similarity': False
}
# seed 1205: 'topK': 205, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True, 'feature_weighting': 'BM25'
self.__rec3 = ItemKNNCBFRecommender(URM_train,
ICM_train,
verbose=False)
self.__rec3_params = {
'topK': 205,
'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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec2.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec3.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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 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)
# SPLIT TO GET THE sub_rec VALID PARTITION
URM_train_bis, URM_valid_sub = 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_sub = EvaluatorHoldout(URM_valid_sub, cutoff_list=[10])
evaluator_valid_hybrid = EvaluatorHoldout(URM_valid_hybrid,
cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
"""
# TODO: setta I GIUSTI EVALUATOR QUI!!!!
runParameterSearch_Content_partial = partial(runParameterSearch_Content,
URM_train=URM_train,
ICM_object=ICM_obj,
ICM_name='1BookFeatures',
n_cases = 50,
n_random_starts = 20,
evaluator_validation= evaluator_valid_sub,
evaluator_test = evaluator_valid_hybrid,
metric_to_optimize = "MAP",
output_folder_path=output_folder_path,
parallelizeKNN = False,
allow_weighting = True,
#similarity_type_list = ['cosine']
)
pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1)
pool.map(runParameterSearch_Content_partial, content_algorithm_list)
"""
print("Rp3beta training...")
rp3b = RP3betaRecommender(URM_train, verbose=False)
rp3b_params = {
'topK': 1000,
'alpha': 0.38192761611274967,
'beta': 0.0,
'normalize_similarity': False
}
rp3b.fit(**rp3b_params)
print("Done")
print("P3alpha training...")
p3a = P3alphaRecommender(URM_train, verbose=False)
p3a_params = {
'topK': 131,
'alpha': 0.33660811631883863,
'normalize_similarity': False
}
p3a.fit(**p3a_params)
print("Done")
print("ItemKnnCF training...")
icf = ItemKNNCFRecommender(URM_train, verbose=False)
icf_params = {
'topK': 100,
'shrink': 1000,
'similarity': 'asymmetric',
'normalize': True,
'asymmetric_alpha': 0.0
}
icf.fit(**icf_params)
print("Done")
print("UserKnnCF training...")
ucf = UserKNNCFRecommender(URM_train, verbose=False)
ucf_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
ucf.fit(**ucf_params)
print("Done")
print("ItemKnnCBF training...")
icb = ItemKNNCBFRecommender(URM_train, ICM_obj, verbose=False)
icb_params = {
'topK': 205,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
icb.fit(**icb_params)
print("Done")
print("SlimBPR training...")
sbpr = SLIM_BPR_Cython(URM_train, verbose=False)
sbpr_params = {
'topK': 979,
'epochs': 130,
'symmetric': False,
'sgd_mode': 'adam',
'lambda_i': 0.004947329669424629,
'lambda_j': 1.1534760845071758e-05,
'learning_rate': 0.0001
}
sbpr.fit(**sbpr_params)
print("Done")
print("SlimElasticNet training...")
sen = SLIMElasticNetRecommender(URM_train, verbose=False)
sen_params = {
'topK': 992,
'l1_ratio': 0.004065081925341167,
'alpha': 0.003725005053334143
}
sen.fit(**sen_params)
print("Done")
list_recommender = [rp3b, p3a, icf, ucf, icb, sen, sbpr]
list_already_seen = [rp3b, p3a, icf, ucf, icb]
for rec_perm in combinations(list_recommender, 3):
if rec_perm not in combinations(list_already_seen, 3):
recommender_names = '_'.join(
[r.RECOMMENDER_NAME for r in rec_perm])
output_folder_path = "result_experiments_v3/seed_" + str(
seed) + '/' + 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)
class LinearHybridW001(BaseItemSimilarityMatrixRecommender):
RECOMMENDER_NAME = "LinearHybridW001"
"""
This hybrid works for users who have a profile length greater than or equal to 3 interactions
"""
# 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(LinearHybridW001, self).__init__(URM_train, verbose=verbose)
self.URM_train = URM_train
self.ICM_train = ICM_train
# seed 1205: {'topK': 205, 'shrink': 1000, 'similarity': 'cosine',
# 'normalize': True, 'feature_weighting': 'BM25'}
self.__rec1 = ItemKNNCBFRecommender(URM_train,ICM_train, verbose=False)
self.__rec1_params = {'topK': 205, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True,
'feature_weighting': 'BM25'}
# seed 1205: {'topK': 565, 'shrink': 554, 'similarity': 'tversky', 'normalize': True,
# 'tversky_alpha': 1.9109121434662428, 'tversky_beta': 1.7823834698905734}
self.__rec2 = ItemKNNCFRecommender(URM_train, verbose=False)
self.__rec2_params = {'topK': 565, 'shrink': 554, 'similarity': 'tversky', 'normalize': True,
'tversky_alpha': 1.9109121434662428, 'tversky_beta': 1.7823834698905734}
# seed 1205: {'topK': 753, 'alpha': 0.3873710051288722, 'beta': 0.0, 'normalize_similarity': False}
self.__rec3 = RP3betaRecommender(URM_train, verbose=False)
self.__rec3_params = {'topK': 753, 'alpha': 0.3873710051288722, 'beta': 0.0, 'normalize_similarity': False}
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(f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec2.load_model(f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
try:
self.__rec3.load_model(f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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(f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
f'best_for_{self.RECOMMENDER_NAME}')
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 runParameterSearch_Collaborative(recommender_class,
URM_train,
ICM_1,
ICM_2,
metric_to_optimize="PRECISION",
evaluator_validation=None,
evaluator_test=None,
evaluator_validation_earlystopping=None,
output_root_path="result_experiments/",
parallelizeKNN=True,
n_cases=100):
from ParameterTuning.AbstractClassSearch import DictionaryKeys
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
try:
output_root_path_rec_name = output_root_path + recommender_class.RECOMMENDER_NAME
parameterSearch = BayesianSearch(
recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
if recommender_class in [TopPop, Random]:
recommender = recommender_class(URM_train)
recommender.fit()
output_file = open(
output_root_path_rec_name + "_BayesianSearch.txt", "a")
result_dict, result_baseline = evaluator_validation.evaluateRecommender(
recommender)
output_file.write(
"ParameterSearch: Best result evaluated on URM_validation. Results: {}"
.format(result_baseline))
pickle.dump(
result_dict.copy(),
open(output_root_path_rec_name + "_best_result_validation",
"wb"),
protocol=pickle.HIGHEST_PROTOCOL)
result_dict, result_baseline = evaluator_test.evaluateRecommender(
recommender)
output_file.write(
"ParameterSearch: Best result evaluated on URM_test. Results: {}"
.format(result_baseline))
pickle.dump(result_dict.copy(),
open(output_root_path_rec_name + "_best_result_test",
"wb"),
protocol=pickle.HIGHEST_PROTOCOL)
output_file.close()
return
##########################################################################################################
if recommender_class is UserKNNCFRecommender:
similarity_type_list = ['cosine']
run_KNNCFRecommender_on_similarity_type_partial = partial(
run_KNNCFRecommender_on_similarity_type,
parameterSearch=parameterSearch,
URM_train=URM_train,
n_cases=n_cases,
output_root_path=output_root_path_rec_name,
metric_to_optimize=metric_to_optimize)
if parallelizeKNN:
pool = PoolWithSubprocess(processes=int(2), maxtasksperchild=1)
resultList = pool.map(
run_KNNCFRecommender_on_similarity_type_partial,
similarity_type_list)
else:
for similarity_type in similarity_type_list:
run_KNNCFRecommender_on_similarity_type_partial(
similarity_type)
return
##########################################################################################################
if recommender_class is ItemKNNCFRecommender:
similarity_type_list = ['cosine']
run_KNNCFRecommender_on_similarity_type_partial = partial(
run_KNNCFRecommender_on_similarity_type,
parameterSearch=parameterSearch,
URM_train=URM_train,
n_cases=n_cases,
output_root_path=output_root_path_rec_name,
metric_to_optimize=metric_to_optimize)
if parallelizeKNN:
pool = PoolWithSubprocess(processes=int(2), maxtasksperchild=1)
resultList = pool.map(
run_KNNCFRecommender_on_similarity_type_partial,
similarity_type_list)
else:
for similarity_type in similarity_type_list:
run_KNNCFRecommender_on_similarity_type_partial(
similarity_type)
return
##########################################################################################################
# if recommender_class is MultiThreadSLIM_RMSE:
#
# hyperparamethers_range_dictionary = {}
# hyperparamethers_range_dictionary["topK"] = [50, 100]
# hyperparamethers_range_dictionary["l1_penalty"] = [1e-2, 1e-3, 1e-4]
# hyperparamethers_range_dictionary["l2_penalty"] = [1e-2, 1e-3, 1e-4]
#
#
# recommenderDictionary = {DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
# DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
# DictionaryKeys.FIT_POSITIONAL_ARGS: dict(),
# DictionaryKeys.FIT_KEYWORD_ARGS: dict(),
# DictionaryKeys.FIT_RANGE_KEYWORD_ARGS: hyperparamethers_range_dictionary}
#
#
##########################################################################################################
if recommender_class is P3alphaRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800
]
hyperparamethers_range_dictionary["alpha"] = range(0, 2)
hyperparamethers_range_dictionary["normalize_similarity"] = [
True, False
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is HybridRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["w_itemcf"] = [
x * 0.1 + 1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_usercf"] = [
x * 0.1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_cbart"] = [
x * 0.1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_cbalb"] = [
x * 0.1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_slim"] = [
x * 0.1 for x in range(0, 10)
]
#hyperparamethers_range_dictionary["w_svd"] = [x * 0.05 for x in range(0, 20)]
#hyperparamethers_range_dictionary["w_rp3"] = [x * 0.05 for x in range(0, 20)]
item = ItemKNNCFRecommender(URM_train)
user = UserKNNCFRecommender(URM_train)
SLIM = MultiThreadSLIM_ElasticNet(URM_train=URM_train)
item.fit(topK=800, shrink=10, similarity='cosine', normalize=True)
user.fit(topK=70, shrink=22, similarity='cosine', normalize=True)
SLIM.fit(l1_penalty=1e-05,
l2_penalty=0,
positive_only=True,
topK=150,
alpha=0.00415637376180466)
CBArt = ItemKNNCBFRecommender(ICM=ICM_1, URM_train=URM_train)
CBArt.fit(topK=160,
shrink=5,
similarity='cosine',
normalize=True,
feature_weighting="none")
CBAlb = ItemKNNCBFRecommender(ICM=ICM_2, URM_train=URM_train)
CBAlb.fit(topK=160,
shrink=5,
similarity='cosine',
normalize=True,
feature_weighting="none")
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"ICM_Art": ICM_1,
"ICM_Alb": ICM_2,
"item": item,
"user": user,
"SLIM": SLIM,
"CBArt": CBArt,
"CBAlb": CBAlb,
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is RP3betaRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800
]
hyperparamethers_range_dictionary["alpha"] = range(0, 2)
hyperparamethers_range_dictionary["beta"] = range(0, 2)
hyperparamethers_range_dictionary["normalize_similarity"] = [True]
hyperparamethers_range_dictionary["implicit"] = [True]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is MatrixFactorization_FunkSVD_Cython:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["sgd_mode"] = ["adagrad", "adam"]
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["num_factors"] = range(
100, 1000, 20)
hyperparamethers_range_dictionary["reg"] = [0.0, 1e-3, 1e-6, 1e-9]
hyperparamethers_range_dictionary["learning_rate"] = [
1e-2, 1e-3, 1e-4, 1e-5
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validatons_allowed": 20,
"validation_metric": metric_to_optimize
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is FunkSVD:
hyperparamethers_range_dictionary = {}
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["num_factors"] = range(
100, 1000, 20)
hyperparamethers_range_dictionary["reg"] = [
0.0, 1e-03, 1e-06, 1e-09
]
hyperparamethers_range_dictionary["learning_rate"] = [1e-02, 1e-03]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is MatrixFactorization_AsySVD_Cython:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["sgd_mode"] = ["adagrad", "adam"]
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["num_factors"] = range(
100, 500, 10)
hyperparamethers_range_dictionary["batch_size"] = [
100, 200, 300, 400
]
hyperparamethers_range_dictionary["positive_reg"] = [
0.0, 1e-3, 1e-6, 1e-9
]
hyperparamethers_range_dictionary["negative_reg"] = [
0.0, 1e-3, 1e-6, 1e-9
]
hyperparamethers_range_dictionary["learning_rate"] = [
1e-2, 1e-3, 1e-4, 1e-5
]
hyperparamethers_range_dictionary["user_reg"] = [
1e-3, 1e-4, 1e-5, 1e-6
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {
'positive_threshold': 1
},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validatons_allowed": 20,
"validation_metric": metric_to_optimize
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is PureSVDRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["num_factors"] = list(
range(0, 250, 5))
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
#########################################################################################################
if recommender_class is SLIM_BPR_Cython:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [800, 900, 1000, 1200]
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["sgd_mode"] = ["adagrad"]
hyperparamethers_range_dictionary["lambda_i"] = [1e-6]
hyperparamethers_range_dictionary["lambda_j"] = [1e-9]
hyperparamethers_range_dictionary["learning_rate"] = [
0.01, 0.001, 1e-4, 1e-5, 0.1
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {
'train_with_sparse_weights': True,
'symmetric': True,
'positive_threshold': 1
},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"validation_every_n": 10,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validatons_allowed": 3,
"validation_metric": metric_to_optimize
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is MultiThreadSLIM_ElasticNet:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
3300, 4300, 5300, 6300, 7300
]
hyperparamethers_range_dictionary["l1_penalty"] = [
1e-5, 1e-6, 1e-4, 1e-3
]
hyperparamethers_range_dictionary["l2_penalty"] = [1e-4]
hyperparamethers_range_dictionary["alpha"] = range(0, 1)
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
#########################################################################################################
## Final step, after the hyperparameter range has been defined for each type of algorithm
best_parameters = parameterSearch.search(
recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path_rec_name,
metric=metric_to_optimize)
except Exception as e:
print("On recommender {} Exception {}".format(recommender_class,
str(e)))
traceback.print_exc()
error_file = open(output_root_path + "ErrorLog.txt", "a")
error_file.write("On recommender {} Exception {}\n".format(
recommender_class, str(e)))
error_file.close()
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)
URM_valid_hybrid = parser.filter_URM_test_by_range(URM_train,
URM_valid_hybrid,
(3, -1))
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")
"""
print("Rp3beta training...")
rp3b = RP3betaRecommender(URM_train, verbose=False)
rp3b_params = {
'topK': 753,
'alpha': 0.3873710051288722,
'beta': 0.0,
'normalize_similarity': False
}
rp3b.fit(**rp3b_params)
print("Done")
print("P3alpha training...")
p3a = P3alphaRecommender(URM_train, verbose=False)
p3a_params = {
'topK': 438,
'alpha': 0.41923120471415165,
'normalize_similarity': False
}
p3a.fit(**p3a_params)
print("Done")
print("ItemKnnCF training...")
icf = ItemKNNCFRecommender(URM_train, verbose=False)
icf_params = {
'topK': 565,
'shrink': 554,
'similarity': 'tversky',
'normalize': True,
'tversky_alpha': 1.9109121434662428,
'tversky_beta': 1.7823834698905734
}
icf.fit(**icf_params)
print("Done")
print("UserKnnCF training...")
ucf = UserKNNCFRecommender(URM_train, verbose=False)
ucf_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
ucf.fit(**ucf_params)
print("Done")
print("ItemKnnCBF training...")
icb = ItemKNNCBFRecommender(URM_train, ICM_obj, verbose=False)
icb_params = {
'topK': 205,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
icb.fit(**icb_params)
print("Done")
"""
print("SlimElasticNet training...")
sen = SLIMElasticNetRecommender(URM_train, verbose=False)
sen_params = {'topK': 954, 'l1_ratio': 3.87446082207643e-05, 'alpha': 0.07562657698792305}
sen.fit(**sen_params)
print("Done")
"""
list_recommender = [icb, icf, ucf, p3a, rp3b]
list_already_seen = []
for rec_perm in combinations(list_recommender, 3):
if rec_perm not in combinations(list_already_seen, 3):
recommender_names = '_'.join(
[r.RECOMMENDER_NAME for r in rec_perm])
output_folder_path = "result_experiments_v3/seed_" + str(
seed) + '_3--1' + '/' + 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)
def __init__(self, urm_train, eurm=False):
super(HybridGen2Recommender, self).__init__(urm_train)
self.eurm = eurm
self.data_folder = Path(__file__).parent.parent.absolute()
self.num_users = urm_train.shape[0]
urm_train = check_matrix(urm_train.copy(), 'csr')
data = DataManager()
if Path(self.data_folder /
'Data/icm_sparse.npz').is_file() and self.eurm:
print("Previous icm_sparse found")
else:
_, _, _, icm_all = data.get_icm()
args = {
'topK': 6,
'shrink': 5,
'feature_weighting': 'TF-IDF',
'similarity': 'cosine',
'normalize': False
}
recommender_1 = ItemKNNCBFRecommender(urm_train, icm_all)
recommender_1.fit(**args)
self.recommender_1 = recommender_1
if Path(self.data_folder /
'Data/ucm_sparse.npz').is_file() and self.eurm:
print("Previous ucm_sparse found")
else:
ucm_age, ucm_region, ucm_all = data.get_ucm()
recommender_2 = UserKNNCBFRecommender(urm_train, ucm_all)
recommender_2.fit(shrink=1777,
topK=1998,
similarity='tversky',
feature_weighting='BM25',
tversky_alpha=0.1604953616,
tversky_beta=0.9862348646)
self.recommender_2 = recommender_2
if self.eurm:
beta = 0.6
if Path(self.data_folder / 'Data/icm_sparse.npz').is_file():
self.score_matrix_1 = sps.load_npz(self.data_folder /
'Data/icm_sparse.npz')
else:
print("icm_sparse not found, create new one...")
self.score_matrix_1 = self.recommender_1._compute_item_matrix_score(
np.arange(self.num_users))
user_score_matrix_1 = normalize(self.score_matrix_1,
norm='max',
axis=1)
item_score_matrix_1 = normalize(self.score_matrix_1.tocsc(),
norm='max',
axis=0)
self.score_matrix_1 = item_score_matrix_1 * beta + user_score_matrix_1.tocsr(
) * (1 - beta)
sps.save_npz(self.data_folder / 'Data/icm_sparse.npz',
self.score_matrix_1)
if Path(self.data_folder / 'Data/ucm_sparse.npz').is_file():
self.score_matrix_2 = sps.load_npz(self.data_folder /
'Data/ucm_sparse.npz')
else:
print("ucm_sparse not found, create new one...")
self.score_matrix_2 = self.recommender_2._compute_item_matrix_score(
np.arange(self.num_users))
user_score_matrix_2 = normalize(self.score_matrix_2,
norm='max',
axis=1)
item_score_matrix_2 = normalize(self.score_matrix_2.tocsc(),
norm='max',
axis=0)
self.score_matrix_2 = item_score_matrix_2 * beta + user_score_matrix_2.tocsr(
) * (1 - beta)
sps.save_npz(self.data_folder / 'Data/ucm_sparse.npz',
self.score_matrix_2)
+ "hybrid_opt"
output_root_path += filename
output_file = open(output_root_path, "a")
P3alpha = P3alphaRecommender(URM_train)
P3alpha.fit(topK=100, alpha=0.7905462550621185, implicit=True, normalize_similarity=True)
# print("-------------------")
# print("--P3alpha fitted---")
# print("-------------------")
UserBased = UserKNNCFRecommender(URM_train)
UserBased.fit(topK=300, shrink=200)
ContentBased = ItemKNNCBFRecommender(ICM, URM_train)
ContentBased.fit(topK=50, shrink=100)
# print("-------------------")
# print("--KNNCBF fitted---")
# print("-------------------")
ItemKNNCF = ItemKNNCFRecommender(URM_train)
ItemKNNCF.fit(topK=300, shrink=100)
# print("-------------------")
# print("---KNNCF fitted----")
# print("-------------------")
PureSVD = PureSVDRecommender(URM_train)
PureSVD.fit(num_factors=240)
# print("-------------------")
# print("---PureSVD fitted--")
# print("-------------------")
#hybridRecommender = ItemKNNSimilarityHybridRecommender(URM_train, ItemKNNCF.W_sparse, ContentBased.W_sparse)
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
SLIM = MultiThreadSLIM_ElasticNet(URM_train=URM_train)
SLIM.fit(l1_penalty=1e-05,
l2_penalty=0,
positive_only=True,
topK=300,
alpha=4e-5)
item = ItemKNNCFRecommender(URM_train)
W_sparse_CF = item.fit(topK=800,
shrink=8,
similarity='cosine',
normalize=True)
CBAlb = ItemKNNCBFRecommender(ICM=ICM_Alb, URM_train=URM_train)
CBAlb.fit(topK=10,
shrink=16,
similarity='cosine',
normalize=True,
feature_weighting="none")
CBArt = ItemKNNCBFRecommender(ICM=ICM_Art, URM_train=URM_train)
CBArt.fit(topK=12,
shrink=16,
similarity='cosine',
normalize=True,
feature_weighting="none")
user = UserKNNCFRecommender(URM_train)
user.fit(topK=300, shrink=2, similarity='cosine', normalize=True)
p3 = RP3betaRecommender(URM_train=URM_train)
p3.fit(alpha=0.94,
beta=0.3,
min_rating=0,
topK=300,
rec2 = RP3betaRecommender(datas[j].urm_train)
rec2.fit(topK=5000, alpha=0.35, beta=0.025, implicit=True)
rec3 = ItemKNNCFRecommender(datas[j].urm_train)
rec3.fit(topK=200,
shrink=1000,
similarity="jaccard",
feature_weighting="TF-IDF")
rec4 = UserKNNCBFRecommender(datas[j].ucm_all, datas[j].urm_train)
rec4.fit(topK=5000,
shrink=5,
feature_weighting="TF-IDF",
similarity="euclidean")
rec5 = ItemKNNCBFRecommender(datas[j].urm_train,
datas[j].icm_all_augmented)
rec5.fit(topK=100,
shrink=1,
feature_weighting="TF-IDF",
similarity="cosine")
base_recommenders.append([rec1, rec2, rec3, rec4, rec5])
# TODO: Edit here
# Insert the type of users to test the recommenders
n, t_users, description = datas[j].urm_train_users_by_type[1]
tested_users.append(t_users)
# TODO: Edit here
# This code auto assign the weights
# It is possible to manually assign the weights
# For example, we can assign the weights of a previously tuned recommender
cached_hybrid_rec = Hybrid1CXAlphaRecommender(datas[j],
base_recommenders[j],