hopwise.data.dataloader.knowledge_dataloader¶

Classes¶

`KGDataLoader`	`KGDataLoader` is a dataloader which would return the triplets with negative examples
`KnowledgeBasedDataLoader`	`KnowledgeBasedDataLoader` is used for knowledge based model.
`KnowledgePathEvalDataLoader`	`FullSortRecEvalDataLoader` is a dataloader for full-sort evaluation for the recommendation (Rec) task.

Module Contents¶

class hopwise.data.dataloader.knowledge_dataloader.KGDataLoader(config, dataset, sampler, shuffle=False)¶

Bases: hopwise.data.dataloader.abstract_dataloader.AbstractDataLoader

KGDataLoader is a dataloader which would return the triplets with negative examples in a knowledge graph.

Parameters:

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

shuffle¶

Whether the dataloader will be shuffle after a round. However, in KGDataLoader, it’s guaranteed to be True.

Type:: bool

logger¶

neg_sample_num = 1¶

neg_prefix¶

hid_field¶

tid_field¶

neg_tid_field¶

sample_size¶

_init_batch_size_and_step()¶: Initializing step and batch_size.

collate_fn(index)¶: Collect the sampled index, and apply neg_sampling or other methods to get the final data.

class hopwise.data.dataloader.knowledge_dataloader.KnowledgeBasedDataLoader(config, dataset, sampler, kg_sampler, shuffle=False)¶

KnowledgeBasedDataLoader is used for knowledge based model. It has three states, which is saved in state. In different states, _next_batch_data() will return different Interaction. Detailed, please see state.

Parameters:

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

state¶

This dataloader has three states:

In the first state, this dataloader would only return the user-item interaction. In the second state, this dataloader would only return the triplets with negative examples in a knowledge graph. In the last state, this dataloader would return both knowledge graph information and user-item interaction information.

Type:: KGDataLoaderState

logger¶

general_dataloader¶

kg_dataloader¶

shuffle = False¶

state = None¶

update_config(config)¶

__iter__()¶

__next__()¶

__len__()¶

set_mode(state)¶

Set the mode of KnowledgeBasedDataLoader, it can be set to three states:

KGDataLoaderState.RS
KGDataLoaderState.KG
KGDataLoaderState.RSKG

The state of KnowledgeBasedDataLoader would affect the result of _next_batch_data().

Parameters:: state (KGDataLoaderState) – the state of KnowledgeBasedDataLoader.

get_model(model)¶: Let the general_dataloader get the model, used for dynamic sampling.

knowledge_shuffle(epoch_seed)¶: Reset the seed to ensure that each subprocess generates the same index squence.

class hopwise.data.dataloader.knowledge_dataloader.KnowledgePathEvalDataLoader(config, dataset, sampler, shuffle=False)¶

Bases: hopwise.data.dataloader.general_dataloader.FullSortRecEvalDataLoader

FullSortRecEvalDataLoader is a dataloader for full-sort evaluation for the recommendation (Rec) task.

Parameters:

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.

inference_tokenized_dataset¶

_init_batch_size_and_step()¶: Initializing step and batch_size.

collate_fn(index)¶: Collect the sampled index, and apply neg_sampling or other methods to get the final data.