recbole.quick_start¶
- recbole.quick_start.quick_start.load_data_and_model(model_file)[source]¶
Load filtered dataset, split dataloaders and saved model.
- Parameters
model_file (str) – The path of saved model file.
- Returns
config (Config): An instance object of Config, which record parameter information in
model_file.model (AbstractRecommender): The model load from
model_file.dataset (Dataset): The filtered dataset.
train_data (AbstractDataLoader): The dataloader for training.
valid_data (AbstractDataLoader): The dataloader for validation.
test_data (AbstractDataLoader): The dataloader for testing.
- Return type
tuple
- recbole.quick_start.quick_start.objective_function(config_dict=None, config_file_list=None, saved=True)[source]¶
The default objective_function used in HyperTuning
- Parameters
config_dict (dict, optional) – Parameters dictionary used to modify experiment parameters. Defaults to
None.config_file_list (list, optional) – Config files used to modify experiment parameters. Defaults to
None.saved (bool, optional) – Whether to save the model. Defaults to
True.
- recbole.quick_start.quick_start.run(model, dataset, config_file_list=None, config_dict=None, saved=True, nproc=1, world_size=- 1, ip='localhost', port='5678', group_offset=0)[source]¶
- recbole.quick_start.quick_start.run_recbole(model=None, dataset=None, config_file_list=None, config_dict=None, saved=True, queue=None)[source]¶
A fast running api, which includes the complete process of training and testing a model on a specified dataset
- Parameters
model (str, optional) – Model name. Defaults to
None.dataset (str, optional) – Dataset name. Defaults to
None.config_file_list (list, optional) – Config files used to modify experiment parameters. Defaults to
None.config_dict (dict, optional) – Parameters dictionary used to modify experiment parameters. Defaults to
None.saved (bool, optional) – Whether to save the model. Defaults to
True.queue (torch.multiprocessing.Queue, optional) – The queue used to pass the result to the main process. Defaults to
None.