print_results_latex_table(
result_folder_path=output_folder_path,
results_file_prefix_name=ALGORITHM_NAME,
dataset_name=dataset_name,
metrics_to_report_list=["PRECISION", "RECALL", "NDCG"],
cutoffs_to_report_list=[10],
ICM_names_to_report_list=ICM_names_to_report_list,
other_algorithm_list=[MCRecML100k_RecommenderWrapper])
from functools import partial
if __name__ == '__main__':
ALGORITHM_NAME = "MCRec"
CONFERENCE_NAME = "KDD"
dataset_list = ["movielens100k"]
for dataset in dataset_list:
read_data_split_and_search_MCRec(dataset)
print_parameters_latex_table(
result_folder_path="result_experiments/{}/".format(CONFERENCE_NAME),
results_file_prefix_name=ALGORITHM_NAME,
experiment_subfolder_list=dataset_list,
ICM_names_to_report_list=["ICM_genre"],
other_algorithm_list=[MCRecML100k_RecommenderWrapper])
read_data_split_and_search_SpectralCF(dataset_name, cold_start=cold_start, cold_items=cold_start_items,
isKNN_multiprocess=isKNN_multiprocess,
isKNN_tune=isKNN_tune,
isSpectralCF_train_default=isSpectralCF_train_default,
print_results=print_results
)
else:
for dataset_name in dataset_list:
read_data_split_and_search_SpectralCF(dataset_name, cold_start=cold_start,
isKNN_multiprocess=isKNN_multiprocess,
isKNN_tune=isKNN_tune,
isSpectralCF_train_default=isSpectralCF_train_default,
print_results=print_results
)
# mantain compatibility with latex parameteres function
if cold_start and print_results:
for n_cold_item in cold_start_items_list:
print_parameters_latex_table(result_folder_path = "result_experiments/{}/".format(CONFERENCE_NAME),
results_file_prefix_name = "{}_cold_{}".format(ALGORITHM_NAME, n_cold_item),
experiment_subfolder_list = dataset_cold_start_list,
other_algorithm_list = [SpectralCF_RecommenderWrapper])
elif not cold_start and print_results:
print_parameters_latex_table(result_folder_path = "result_experiments/{}/".format(CONFERENCE_NAME),
results_file_prefix_name = ALGORITHM_NAME,
experiment_subfolder_list = dataset_list,
other_algorithm_list = [SpectralCF_RecommenderWrapper])
dataset_name=dataset_name,
results_file_prefix_name=ALGORITHM_NAME,
other_algorithm_list=[NeuMF_RecommenderWrapper],
n_validation_users=n_validation_users,
n_test_users=n_test_users,
n_decimals=2)
print_results_latex_table(result_folder_path=output_folder_path,
results_file_prefix_name=ALGORITHM_NAME,
dataset_name=dataset_name,
metrics_to_report_list=["HIT_RATE", "NDCG"],
cutoffs_to_report_list=[1, 5, 10],
other_algorithm_list=[NeuMF_RecommenderWrapper])
if __name__ == '__main__':
ALGORITHM_NAME = "NeuMF"
CONFERENCE_NAME = "WWW"
dataset_list = ["movielens1m", "pinterest"]
for dataset in dataset_list:
read_data_split_and_search_NeuCF(dataset)
print_parameters_latex_table(
result_folder_path="result_experiments/{}/".format(CONFERENCE_NAME),
results_file_prefix_name=ALGORITHM_NAME,
experiment_subfolder_list=dataset_list,
other_algorithm_list=[NeuMF_RecommenderWrapper])
cutoffs_to_report_list=[50, 100, 150, 200, 250, 300],
ICM_names_to_report_list=ICM_names_to_report_list,
other_algorithm_list=[CollaborativeVAE_RecommenderWrapper])
if __name__ == '__main__':
ALGORITHM_NAME = "CollaborativeVAE"
CONFERENCE_NAME = "KDD"
dataset_variant_list = ["a", "t"]
train_interactions_list = [1, 10]
for dataset_variant in dataset_variant_list:
for train_interactions in train_interactions_list:
read_data_split_and_search_CollaborativeVAE(
dataset_variant, train_interactions)
print_parameters_latex_table(
result_folder_path="result_experiments/{}/".format(CONFERENCE_NAME),
results_file_prefix_name=ALGORITHM_NAME,
experiment_subfolder_list=[
"citeulike_{}_{}".format(dataset_variant, train_interactions)
for dataset_variant in dataset_variant_list
for train_interactions in train_interactions_list
],
ICM_names_to_report_list=["ICM_title_abstract"],
other_algorithm_list=[CollaborativeVAE_RecommenderWrapper])
print_results_latex_table(
result_folder_path=output_folder_path,
results_file_prefix_name=ALGORITHM_NAME,
dataset_name=dataset_name,
metrics_to_report_list=["RECALL", "NDCG"],
cutoffs_to_report_list=[20, 50, 100],
other_algorithm_list=[MultiVAE_RecommenderWrapper])
from functools import partial
if __name__ == '__main__':
ALGORITHM_NAME = "Mult_VAE"
CONFERENCE_NAME = "WWW"
dataset_list = ["movielens20m", "netflixPrize"]
for dataset in dataset_list:
read_data_split_and_search_MultiVAE(dataset)
print_parameters_latex_table(
result_folder_path="result_experiments/{}/".format(CONFERENCE_NAME),
results_file_prefix_name=ALGORITHM_NAME,
experiment_subfolder_list=[
"{}_cold_user".format(dataset) for dataset in dataset_list
],
other_algorithm_list=[MultiVAE_RecommenderWrapper])
