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
"""
from Data_manager.Movielens1M.Movielens1MReader import Movielens1MReader
from Data_manager.DataSplitter_k_fold_stratified import DataSplitter_Warm_k_fold
dataset_object = Movielens1MReader()
dataSplitter = DataSplitter_Warm_k_fold(dataset_object)
dataSplitter.load_data()
URM_train, URM_validation, URM_test = dataSplitter.get_holdout_split()
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,
UserKNNCFRecommender,
# MatrixFactorization_BPR_Cython,
# MatrixFactorization_FunkSVD_Cython,
# PureSVDRecommender,
# SLIM_BPR_Cython,
# SLIMElasticNetRecommender
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_validation = EvaluatorHoldout(URM_validation, cutoff_list=[5])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[5, 10])
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
metric_to_optimize="MAP",
n_cases=8,
evaluator_validation_earlystopping=evaluator_validation,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test,
output_folder_path=output_folder_path)
from 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 run_recommender(recommender_class):
temp_save_file_folder = "./result_experiments/__temp_model/"
if not os.path.isdir(temp_save_file_folder):
os.makedirs(temp_save_file_folder)
try:
dataset_object = Movielens1MReader()
dataSplitter = DataSplitter_leave_k_out(dataset_object, k_out_value=2)
dataSplitter.load_data()
URM_train, URM_validation, URM_test = dataSplitter.get_holdout_split()
write_log_string(log_file, "On Recommender {}\n".format(recommender_class))
recommender_object = recommender_class(URM_train)
if isinstance(recommender_object, Incremental_Training_Early_Stopping):
fit_params = {"epochs": 15}
else:
fit_params = {}
recommender_object.fit(**fit_params)
write_log_string(log_file, "Fit OK, ")
evaluator = EvaluatorHoldout(URM_test, [5], exclude_seen=True)
_, results_run_string = evaluator.evaluateRecommender(recommender_object)
write_log_string(log_file, "EvaluatorHoldout OK, ")
evaluator = EvaluatorNegativeItemSample(URM_test, URM_train, [5], exclude_seen=True)
_, _ = evaluator.evaluateRecommender(recommender_object)
write_log_string(log_file, "EvaluatorNegativeItemSample OK, ")
recommender_object.saveModel(temp_save_file_folder, file_name="temp_model")
write_log_string(log_file, "saveModel OK, ")
recommender_object = recommender_class(URM_train)
recommender_object.loadModel(temp_save_file_folder, file_name="temp_model")
evaluator = EvaluatorHoldout(URM_test, [5], exclude_seen=True)
_, results_run_string_2 = evaluator.evaluateRecommender(recommender_object)
write_log_string(log_file, "loadModel OK, ")
shutil.rmtree(temp_save_file_folder, ignore_errors=True)
write_log_string(log_file, " PASS\n")
write_log_string(log_file, results_run_string + "\n\n")
except Exception as e:
print("On Recommender {} Exception {}".format(recommender_class, str(e)))
log_file.write("On Recommender {} Exception {}\n\n\n".format(recommender_class, str(e)))
log_file.flush()
traceback.print_exc()