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
"""
parser = DataParser()
URM_all = parser.get_URM_all()
ICM_obj = parser.get_ICM_all()
URM_train, URM_test = split_train_in_two_percentage_global_sample(
URM_all, train_percentage=0.80)
URM_train, URM_validation = split_train_in_two_percentage_global_sample(
URM_train, train_percentage=0.85)
"""
26-10-2020
> OPTIMIZATION ON THE RANGE [200, +INF)
Already done optimizations:
>
RECOMMENDER I'AM CONSIDERING (the fastest up to now)
> PureSVD
> ItemKNNCBF
> ItemKNNCF
> UserKNNCF
> P3A
> RP3beta
"""
f_range = (200, -1)
URM_validation = parser.filter_URM_test_by_range(URM_train, URM_validation,
f_range)
URM_test = parser.filter_URM_test_by_range(URM_train, URM_test, f_range)
output_folder_path = "result_experiments_v2/" + "range_" + str(
f_range[0]) + "-" + str(f_range[1]) + "/"
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
"""
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
]
content_algorithm_list= [
#ItemKNNCBFRecommender
]
"""
algorithm_in_sequence = [(ItemKNNCFRecommender, 'CF'),
(UserKNNCFRecommender, 'CF'),
(P3alphaRecommender, 'CF'),
(RP3betaRecommender, 'CF'),
(PureSVDRecommender, 'CF'),
(ItemKNNCBFRecommender, 'CBF')]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_validation = EvaluatorHoldout(URM_validation, cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
for algo, type in algorithm_in_sequence:
print(F"OPTIMIZING {algo.RECOMMENDER_NAME} - {type}")
if type == 'CF':
collaborative_algorithm_list = []
collaborative_algorithm_list.append(algo)
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
ICM_train=ICM_obj,
metric_to_optimize="MAP",
n_cases=50,
n_random_starts=50 * 0.3,
evaluator_validation_earlystopping=evaluator_validation,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test,
output_folder_path=output_folder_path,
allow_weighting=False, #LOOOK AT HEREEEEEEEEEEEEEEEEE
parallelizeKNN=False)
pool = multiprocessing.Pool(processes=int(
multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial,
collaborative_algorithm_list)
elif type == 'CBF':
content_algorithm_list = []
content_algorithm_list.append(algo)
runParameterSearch_Content_partial = partial(
runParameterSearch_Content,
URM_train=URM_train,
ICM_object=ICM_obj,
ICM_name='BookFeatures',
n_cases=50,
n_random_starts=50 * 0.3,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test,
metric_to_optimize="MAP",
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)
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, URM_valid_sub = split_train_in_two_percentage_global_sample(
URM_train, train_percentage=0.85, seed=seed)
output_folder_path = "result_experiments_v3/seed_" + str(seed) + '/'
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
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
#LinearHybrid002
]
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)
"""
# 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_sub,
evaluator_validation=evaluator_valid_sub,
evaluator_test=evaluator_valid_hybrid,
output_folder_path=output_folder_path,
allow_weighting=False,
#similarity_type_list = ["cosine", 'jaccard'],
parallelizeKNN=False)
pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial,
collaborative_algorithm_list)
user_id_array=user_id_array,
cutoff=cutoff,
remove_seen_flag=remove_seen_flag,
items_to_compute=items_to_compute,
remove_top_pop_flag=remove_top_pop_flag,
remove_custom_items_flag=remove_custom_items_flag,
return_scores=return_scores)
return round_robin_merging([ranking_list1, ranking_list2])
if __name__ == '__main__':
seed = 1205
parser = DataParser('../data')
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)
recommender = ListMerged001(URM_train)
recommender.fit()
result_dict = evaluator(recommender, URM_test, cutoff=10)
print("Round robin:")
print(result_dict)
result_dict = evaluator(recommender.ger_recommenders()[0],
URM_test,
cutoff=10)
print("RP3beta:")
print(result_dict)
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)
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
"""
parser = DataParser()
seed = 1666
URM_all = parser.get_URM_all()
ICM_obj = parser.get_ICM_all()
URM_train, URM_test = split_train_in_two_percentage_global_sample(
URM_all, train_percentage=0.85, seed=seed)
URM_train, URM_validation = split_train_in_two_percentage_global_sample(
URM_train, train_percentage=0.85, seed=seed)
k = 5
output_folder_path = "result_experiments_CV/"
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
collaborative = True
content_algorithm_list = [
#ItemKNNCBFRecommender
]
collaborative_algorithm_list = [
#Random,
#TopPop,
#P3alphaRecommender,
#RP3betaRecommender,
ItemKNNCFRecommender,
#UserKNNCFRecommender,
#MatrixFactorization_BPR_Cython,
#MatrixFactorization_FunkSVD_Cython,
#PureSVDRecommender,
#SLIM_BPR_Cython,
#SLIMElasticNetRecommender,
#IALSRecommender,
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_validation = EvaluatorHoldout(URM_validation, cutoff_list=[5])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
if not collaborative:
runParameterSearch_Content_partial = partial(
runParameterSearch_Content,
URM_train=URM_train,
ICM_object=ICM_obj,
ICM_name='1BookFeatures',
n_cases=50,
n_random_starts=20,
metric_to_optimize="MAP",
output_folder_path=output_folder_path,
parallelizeKNN=False,
allow_weighting=True,
#similarity_type_list = ['cosine']
k=k,
seed=seed)
pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Content_partial, content_algorithm_list)
else:
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
metric_to_optimize="MAP",
n_cases=50,
n_random_starts=20,
#evaluator_test = evaluator_test,
output_folder_path=output_folder_path,
similarity_type_list=["cosine"],
parallelizeKNN=False,
allow_weighting=False,
k=k,
seed=seed)
pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial,
collaborative_algorithm_list)
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 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)
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
"""
parser = DataParser()
seed = 1666
URM_all = parser.get_URM_all()
ICM_obj = parser.get_ICM_all()
#URM_train, URM_test = split_train_in_two_percentage_global_sample(URM_all, train_percentage=0.85, seed=seed)
#URM_train, URM_validation = split_train_in_two_percentage_global_sample(URM_train, train_percentage=0.85, seed=seed)
k = 5
output_folder_path = "result_experiments_CV/"
collaborative_algorithm_list = [
HybridCombinationSearchCV
#HybridSuperLinear
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
icb = (ItemKNNCBFRecommender), {
'topK': 164,
'shrink': 8,
'similarity': 'jaccard',
'normalize': True
}
icbsup = (SpecialItemKNNCBFRecommender), {
'topK': 1000,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
icbcf = (ItemKNN_CBF_CF), {
'topK': 1000,
'shrink': 1000,
'similarity': 'asymmetric',
'normalize': True,
'asymmetric_alpha': 0.241892724784089,
'feature_weighting': 'TF-IDF',
'icm_weight': 1.0
}
icf = (ItemKNNCFRecommender), {
'topK': 1000,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'TF-IDF'
}
ucf = (UserKNNCFRecommender), {
'topK': 163,
'shrink': 846,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'TF-IDF'
}
p3a = (RP3betaRecommender), {
'topK': 926,
'alpha': 0.4300109351916609,
'beta': 0.01807360750913967,
'normalize_similarity': False
}
rp3b = (P3alphaRecommender), {
'topK': 575,
'alpha': 0.48009885897470206,
'normalize_similarity': False
}
sbpr = (SLIM_BPR_Cython, {
'topK': 1000,
'epochs': 130,
'symmetric': False,
'sgd_mode': 'adam',
'lambda_i': 1e-05,
'lambda_j': 1e-05,
'learning_rate': 0.0001
})
sslim = (SSLIMElasticNet, {
'beta': 0.567288665094892,
'topK': 1000,
'l1_ratio': 1e-05,
'alpha': 0.001
})
combo_algorithm_list = [
icb, icbsup, icbcf, icf, ucf, p3a, rp3b, sbpr, sslim
]
list_already_seen = []
combinations_already_seen = combinations(list_already_seen, 3)
"""
(icb, icf, p3a), (icb, icf, rp3b), (icb, icf, sen), (icb, p3a, rp3b), (icb, p3a, sen),
(icb, rp3b, sen), (icf, p3a, rp3b), (icf, p3a, sen)
"""
combination_to_be_done = list(combinations(combo_algorithm_list, 3))
for rec_perm in combination_to_be_done:
if rec_perm not in combinations_already_seen:
recommender_names = '_'.join(
[r[0].RECOMMENDER_NAME for r in rec_perm])
output_folder_path = "result_experiments_CV2/seed_" + str(
seed) + '/linear/' + recommender_names + '/'
print(F"\nTESTING THE COMBO {recommender_names}")
if ((icb in rec_perm) or
(icbsup in rec_perm)) and not ((icb in rec_perm) and
(icbsup in rec_perm)):
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_all,
ICM_train=ICM_obj,
metric_to_optimize="MAP",
n_cases=50,
n_random_starts=20,
output_folder_path=output_folder_path,
parallelizeKNN=False,
allow_weighting=False,
k=k,
seed=seed,
list_rec=rec_perm,
level='hybrid_search')
pool = multiprocessing.Pool(processes=int(
multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial,
collaborative_algorithm_list)
