deepcarskit.data.dataloader

deepcarskit.data.dataloader.general_dataloader

class deepcarskit.data.dataloader.general_dataloader.FullSortEvalDataLoader(config, dataset, sampler, shuffle=False, used_ids=None)

Bases: recbole.data.dataloader.general_dataloader.FullSortEvalDataLoader

class deepcarskit.data.dataloader.general_dataloader.LabledDataSortEvalDataLoader(config, dataset, sampler, shuffle=False, used_ids=None)

Bases: deepcarskit.data.dataloader.general_dataloader.FullSortEvalDataLoader

FullSortEvalDataLoader is a dataloader for full-sort evaluation. In order to speed up calculation, this dataloader would only return then user part of interactions, positive items and used items. It would not return negative items.

Args:

config (Config): The config of dataloader. dataset (Dataset): The dataset of dataloader. sampler (Sampler): The sampler of dataloader. shuffle (bool, optional): Whether the dataloader will be shuffle after a round. Defaults to False.

used_item = all items that users have interacted in the training and evaluation set. positve_item = all items that users have interacted in the evaluation set. history_item = all items that users have interacted in the training set.

property pr_end

This property marks the end of dataloader.pr which is used in __next__().