score += self.RP3alpha_scores * self.weight_initial['RP3Alpha']
if exclude_seen:
score = self._filter_seen(user_id, score)
ranking = score.argsort()[::-1]
return ranking[:at]
################################################ Test ##################################################
if __name__ == '__main__':
test = False
split_users = True
max_map = 0
data = get_data()
group_cold = None
group_one = None
group_two = None
group_three = None
userCBF_args = {'topK': 1000, 'shrink': 7950}
P3alpha_args = {'topK': 66, 'alpha': 0.2731573847973295, 'normalize': True}
itemCF_args = {
'topK': 12,
'shrink': 88,
'similarity': 'tversky',
'normalize': True,
for values_, rows_, cols_ in res:
values.extend(values_)
rows.extend(rows_)
cols.extend(cols_)
# generate the sparse weight matrix
self.W_sparse = sps.csr_matrix((values, (rows, cols)),
shape=(n_items, n_items),
dtype=np.float32)
if __name__ == '__main__':
evaluate = True
train, test = split_train_leave_k_out_user_wise(get_data()['URM_all'],
k_out=1)
SLIMElasticNet_args = {'l1_ratio': 1e-05, 'alpha': 0.001, 'topK': 1000}
if evaluate:
evaluator = EvaluatorHoldout(test, [10],
target_users=get_data()['target_users'])
slel = SLIMElasticNetRecommender(train)
slel.fit(l1_ratio=SLIMElasticNet_args['l1_ratio'],
topK=SLIMElasticNet_args['topK'],
alpha=SLIMElasticNet_args['alpha'])
result, result_string = evaluator.evaluateRecommender(slel)
print(f"MAP: {result[10]['MAP']:.5f}")
for user_id in user_id_array:
scores = np.dot(self.user_factors[user_id], self.item_factors.T)
scores = np.squeeze(scores)
scores_list.append(scores)
return np.asarray(scores_list, dtype=np.float32)
def save_model(self, folder_path, file_name = None):
print("Saving not implemented...")
if __name__ == '__main__':
ALS_args = {
'n_factors': 433,
'iterations': 29,
'regularization': 1.707545716729426e-05,
'alpha_val' : 5
}
train, test = split_train_leave_k_out_user_wise(get_data()['URM_all'], k_out=1)
evaluator = EvaluatorHoldout(test, [10], target_users=get_data()['target_users'])
als = ALSRecommender(train)
als.fit(n_factors=ALS_args['n_factors'],
regularization=ALS_args['regularization'],
iterations=ALS_args['iterations'],
alpha_val=ALS_args['alpha_val'])
result, result_string = evaluator.evaluateRecommender(als)
print(f"MAP: {result[10]['MAP']:.5f}")
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
"""
URM_train, URM_test = split_train_leave_k_out_user_wise(
get_data()['URM_all'], k_out=1)
URM_train, URM_validation = split_train_leave_k_out_user_wise(URM_train,
k_out=1)
output_folder_path = "result_experiments/SKOPT_prova/"
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
collaborative_algorithm_list = [
# Random,
# TopPop,
# P3alphaRecommender,
# RP3betaRecommender,
# ItemKNNCFRecommender,
# HybridRecommender
ALSRecommender
# UserKNNCFRecommender,
# MatrixFactorization_BPR_Cython,
# MatrixFactorization_FunkSVD_Cython,
# PureSVDRecommender,
# IALSRecommender,
# SLIM_BPR_Cython,
# SLIMElasticNetRecommender
]
from Algorithms.Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_validation = EvaluatorHoldout(
URM_validation,
cutoff_list=[10],
target_users=get_data()['target_users'])
evaluator_test = EvaluatorHoldout(URM_test,
cutoff_list=[10],
target_users=get_data()['target_users'])
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
metric_to_optimize="MAP",
# TODO change num of iterations here
n_cases=100,
evaluator_validation_earlystopping=evaluator_validation,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test,
output_folder_path=output_folder_path)
from Algorithms.Utils.PoolWithSubprocess import PoolWithSubprocess
# pool = PoolWithSubprocess(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1)
# resultList = pool.map(runParameterSearch_Collaborative_partial, collaborative_algorithm_list)
# pool.close()
# pool.join()
for recommender_class in collaborative_algorithm_list:
try:
runParameterSearch_Collaborative_partial(recommender_class)
except Exception as e:
print("On recommender {} Exception {}".format(
recommender_class, str(e)))
traceback.print_exc()
def runParameterSearch_Collaborative(recommender_class,
URM_train,
URM_train_last_test=None,
metric_to_optimize="MAP",
evaluator_validation=None,
evaluator_test=None,
evaluator_validation_earlystopping=None,
output_folder_path="result_experiments/",
parallelizeKNN=True,
n_cases=35,
n_random_starts=5,
resume_from_saved=False,
save_model="best",
allow_weighting=True,
similarity_type_list=None):
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
# TODO CHANGE VALIDATION EVERY HERE
earlystopping_keywargs = {
"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validations_allowed": 5,
"validation_metric": metric_to_optimize,
}
URM_train = URM_train.copy()
if URM_train_last_test is not None:
URM_train_last_test = URM_train_last_test.copy()
try:
output_file_name_root = recommender_class.RECOMMENDER_NAME
parameterSearch = SearchBayesianSkopt(
recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
if recommender_class in [TopPop, GlobalEffects, Random]:
"""
TopPop, GlobalEffects and Random have no parameters therefore only one evaluation is needed
"""
parameterSearch = SearchSingleCase(
recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
if URM_train_last_test is not None:
recommender_input_args_last_test = recommender_input_args.copy(
)
recommender_input_args_last_test.CONSTRUCTOR_POSITIONAL_ARGS[
0] = URM_train_last_test
else:
recommender_input_args_last_test = None
parameterSearch.search(
recommender_input_args,
recommender_input_args_last_test=
recommender_input_args_last_test,
fit_hyperparameters_values={},
output_folder_path=output_folder_path,
output_file_name_root=output_file_name_root,
resume_from_saved=resume_from_saved,
save_model=save_model,
)
return
##########################################################################################################
if recommender_class in [ItemKNNCFRecommender, UserKNNCFRecommender]:
if similarity_type_list is None:
similarity_type_list = [
'cosine', 'jaccard', 'tanimoto', "asymmetric", "dice",
"tversky"
]
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
if URM_train_last_test is not None:
recommender_input_args_last_test = recommender_input_args.copy(
)
recommender_input_args_last_test.CONSTRUCTOR_POSITIONAL_ARGS[
0] = URM_train_last_test
else:
recommender_input_args_last_test = None
run_KNNCFRecommender_on_similarity_type_partial = partial(
run_KNNRecommender_on_similarity_type,
recommender_input_args=recommender_input_args,
parameter_search_space={},
parameterSearch=parameterSearch,
n_cases=n_cases,
n_random_starts=n_random_starts,
resume_from_saved=resume_from_saved,
save_model=save_model,
output_folder_path=output_folder_path,
output_file_name_root=output_file_name_root,
metric_to_optimize=metric_to_optimize,
allow_weighting=allow_weighting,
recommender_input_args_last_test=
recommender_input_args_last_test)
if parallelizeKNN:
pool = multiprocessing.Pool(
processes=multiprocessing.cpu_count(), maxtasksperchild=1)
pool.map(run_KNNCFRecommender_on_similarity_type_partial,
similarity_type_list)
pool.close()
pool.join()
else:
for similarity_type in similarity_type_list:
run_KNNCFRecommender_on_similarity_type_partial(
similarity_type)
return
##########################################################################################################
if recommender_class is P3alphaRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["topK"] = Integer(5, 1000)
hyperparameters_range_dictionary["alpha"] = Real(low=0,
high=2,
prior='uniform')
hyperparameters_range_dictionary[
"normalize_similarity"] = Categorical([True, False])
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
##########################################################################################################
if recommender_class is RP3betaRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["topK"] = Integer(70, 500)
hyperparameters_range_dictionary["alpha"] = Real(low=0,
high=2,
prior='uniform')
hyperparameters_range_dictionary["beta"] = Real(low=0,
high=2,
prior='uniform')
hyperparameters_range_dictionary[
"normalize_similarity"] = Categorical([True, False])
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
##########################################################################################################
if recommender_class is MatrixFactorization_FunkSVD_Cython:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["sgd_mode"] = Categorical(
["sgd", "adagrad", "adam"])
hyperparameters_range_dictionary["epochs"] = Categorical([500])
hyperparameters_range_dictionary["use_bias"] = Categorical(
[True, False])
hyperparameters_range_dictionary["batch_size"] = Categorical(
[1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024])
hyperparameters_range_dictionary["num_factors"] = Integer(1, 200)
hyperparameters_range_dictionary["item_reg"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["user_reg"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["learning_rate"] = Real(
low=1e-4, high=1e-1, prior='log-uniform')
hyperparameters_range_dictionary[
"negative_interactions_quota"] = Real(low=0.0,
high=0.5,
prior='uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS=earlystopping_keywargs)
##########################################################################################################
if recommender_class is MatrixFactorization_AsySVD_Cython:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["sgd_mode"] = Categorical(
["sgd", "adagrad", "adam"])
hyperparameters_range_dictionary["epochs"] = Categorical([500])
hyperparameters_range_dictionary["use_bias"] = Categorical(
[True, False])
hyperparameters_range_dictionary["batch_size"] = Categorical([1])
hyperparameters_range_dictionary["num_factors"] = Integer(1, 200)
hyperparameters_range_dictionary["item_reg"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["user_reg"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["learning_rate"] = Real(
low=1e-4, high=1e-1, prior='log-uniform')
hyperparameters_range_dictionary[
"negative_interactions_quota"] = Real(low=0.0,
high=0.5,
prior='uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS=earlystopping_keywargs)
##########################################################################################################
if recommender_class is MatrixFactorization_BPR_Cython:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["sgd_mode"] = Categorical(
["sgd", "adagrad", "adam"])
hyperparameters_range_dictionary["epochs"] = Categorical([1500])
hyperparameters_range_dictionary["num_factors"] = Integer(1, 200)
hyperparameters_range_dictionary["batch_size"] = Categorical(
[1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024])
hyperparameters_range_dictionary["positive_reg"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["negative_reg"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["learning_rate"] = Real(
low=1e-4, high=1e-1, prior='log-uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={
**earlystopping_keywargs, "positive_threshold_BPR": None
})
##########################################################################################################
if recommender_class is IALSRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["num_factors"] = Integer(1, 200)
hyperparameters_range_dictionary[
"confidence_scaling"] = Categorical(["linear", "log"])
hyperparameters_range_dictionary["alpha"] = Real(
low=1e-3, high=50.0, prior='log-uniform')
hyperparameters_range_dictionary["epsilon"] = Real(
low=1e-3, high=10.0, prior='log-uniform')
hyperparameters_range_dictionary["reg"] = Real(low=1e-5,
high=1e-2,
prior='log-uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS=earlystopping_keywargs)
##########################################################################################################
if recommender_class is PureSVDRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["num_factors"] = Integer(1, 350)
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
##########################################################################################################
if recommender_class is NMFRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["num_factors"] = Integer(1, 350)
hyperparameters_range_dictionary["solver"] = Categorical(
["coordinate_descent", "multiplicative_update"])
hyperparameters_range_dictionary["init_type"] = Categorical(
["random", "nndsvda"])
hyperparameters_range_dictionary["beta_loss"] = Categorical(
["frobenius", "kullback-leibler"])
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
#########################################################################################################
if recommender_class is SLIM_BPR_Cython:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["topK"] = Integer(5, 70)
hyperparameters_range_dictionary["epochs"] = Categorical([7000])
hyperparameters_range_dictionary["symmetric"] = Categorical(
[True, False])
hyperparameters_range_dictionary["sgd_mode"] = Categorical(
["sgd", "adagrad", "adam"])
hyperparameters_range_dictionary["lambda_i"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["lambda_j"] = Real(
low=1e-5, high=1e-2, prior='log-uniform')
hyperparameters_range_dictionary["learning_rate"] = Real(
low=1e-4, high=1e-1, prior='log-uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={
**earlystopping_keywargs, "positive_threshold_BPR": None,
'train_with_sparse_weights': None
})
##########################################################################################################
if recommender_class is SLIMElasticNetRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["topK"] = Integer(5, 1000)
hyperparameters_range_dictionary["l1_ratio"] = Real(
low=1e-5, high=1.0, prior='log-uniform')
hyperparameters_range_dictionary["alpha"] = Real(low=1e-3,
high=1.0,
prior='uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
##########################################################################################################
if recommender_class is ALSRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["n_factors"] = Integer(5, 1000)
hyperparameters_range_dictionary["regularization"] = Real(
low=1e-5, high=1.0, prior='log-uniform')
hyperparameters_range_dictionary["iterations"] = Integer(10, 30)
hyperparameters_range_dictionary["alpha_val"] = Integer(1, 40)
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
#########################################################################################################
if recommender_class is HybridRecommender:
hyperparameters_range_dictionary = {}
hyperparameters_range_dictionary["weight_itemcf"] = Real(
low=0.0, high=2.0, prior='uniform')
# hyperparameters_range_dictionary["weight_slim"] = Real(low=0.0, high=6.0, prior='uniform')
hyperparameters_range_dictionary["weight_p3"] = Real(
low=0.0, high=2.0, prior='uniform')
hyperparameters_range_dictionary["weight_rp3"] = Real(
low=0.0, high=2.0, prior='uniform')
hyperparameters_range_dictionary["weight_als"] = Real(
low=0.0, high=2.0, prior='uniform')
recommender_input_args = SearchInputRecommenderArgs(
CONSTRUCTOR_POSITIONAL_ARGS=[URM_train,
get_data()['UCM']],
CONSTRUCTOR_KEYWORD_ARGS={},
FIT_POSITIONAL_ARGS=[],
FIT_KEYWORD_ARGS={})
#########################################################################################################
if URM_train_last_test is not None:
recommender_input_args_last_test = recommender_input_args.copy()
recommender_input_args_last_test.CONSTRUCTOR_POSITIONAL_ARGS[
0] = URM_train_last_test
else:
recommender_input_args_last_test = None
## Final step, after the hyperparameter range has been defined for each type of algorithm
parameterSearch.search(
recommender_input_args,
parameter_search_space=hyperparameters_range_dictionary,
n_cases=n_cases,
n_random_starts=n_random_starts,
resume_from_saved=resume_from_saved,
save_model=save_model,
output_folder_path=output_folder_path,
output_file_name_root=output_file_name_root,
metric_to_optimize=metric_to_optimize,
recommender_input_args_last_test=recommender_input_args_last_test)
except Exception as e:
print("On recommender {} Exception {}".format(recommender_class,
str(e)))
traceback.print_exc()
error_file = open(output_folder_path + "ErrorLog.txt", "a")
error_file.write("On recommender {} Exception {}\n".format(
recommender_class, str(e)))
error_file.close()
def save_model(self, folder_path, file_name = None):
print("Saving not implemented...")
if __name__ == '__main__':
evaluate = False
weight_itemcf = 0.06469128422082827
weight_p3 = 0.04997541987671707
weight_rp3 = 0.030600333541027876
weight_als = 0.0
weight_slimEl = 1.0
train, test = split_train_leave_k_out_user_wise(get_data()['URM_all'], k_out=1)
ucm = get_data()['UCM']
if evaluate:
evaluator = EvaluatorHoldout(test, [10], target_users=get_data()['target_users'])
hybrid = HybridRecommender(train, ucm)
hybrid.fit(weight_itemcf=weight_itemcf, weight_p3=weight_p3, weight_rp3=weight_rp3, weight_als=weight_als, weight_slimel=weight_slimEl)
result, result_string = evaluator.evaluateRecommender(hybrid)
print(f"MAP: {result[10]['MAP']:.5f}")
else:
urm_all = train + test
hybrid = HybridRecommender(urm_all, ucm)
hybrid.fit(weight_itemcf=weight_itemcf, weight_p3=weight_p3, weight_rp3=weight_rp3, weight_als=weight_als, weight_slimel=weight_slimEl)
if self.topK != False:
self.W_sparse = similarityMatrixTopK(self.W_sparse, k=self.topK)
self.W_sparse = check_matrix(self.W_sparse, format='csr')
self.RM = self.URM_train.dot(self.W_sparse)
def get_expected_ratings(self, user_id):
expected_recommendations = self.RM[user_id].todense()
return np.squeeze(np.asarray(expected_recommendations))
if __name__ == '__main__':
train, test = split_train_leave_k_out_user_wise(get_data()['URM_all'],
k_out=1)
urm = train + test
evaluator = EvaluatorHoldout(test, [10])
rp3 = RP3betaRecommender(urm)
rp3.fit(alpha=0.032949920239451876,
beta=0.14658580479486563,
normalize_similarity=True,
topK=75)
# rp3.evaluate_MAP_target(test, get_data()['target_users'])
# result, result_string = evaluator.evaluateRecommender(rp3)
write_output(rp3, get_data()['target_users'])
#print(f"MAP: {result[10]['MAP']:.5f}")
neg_item_id = np.random.randint(0, self.n_items)
if neg_item_id not in userSeenItems:
return pos_item_id, neg_item_id
def sampleTriple(self):
"""
Randomly samples a user and then samples randomly a seen and not seen item
:return: user_id, pos_item_id, neg_item_id
"""
user_id = self.sampleUser()
pos_item_id, neg_item_id = self.sampleItemPair(user_id)
return user_id, pos_item_id, neg_item_id
if __name__ == '__main__':
train, test = split_train_leave_k_out_user_wise(get_data()['URM_all'],
k_out=1)
evaluator = EvaluatorHoldout(test, [10],
target_users=get_data()['target_users'])
slim = SLIM_BPR(train)
slim.fit(1)
result, result_string = evaluator.evaluateRecommender(slim)
# write_output(itemCF, get_data()['target_users'])
print(f"MAP: {result[10]['MAP']:.5f}")