scvi.dataloaders.ConcatDataLoader

class scvi.dataloaders.ConcatDataLoader(adata_manager, indices_list, shuffle=False, batch_size=128, data_and_attributes=None, drop_last=False, distributed_sampler=False, **data_loader_kwargs)

DataLoader that supports a list of list of indices to load.

Parameters:

• adata_manager (AnnDataManager) – AnnDataManager object that has been created via setup_anndata.

• indices_list (list[list[int]]) – List where each element is a list of indices in the adata to load

• shuffle (bool (default: False)) – Whether the data should be shuffled

• batch_size (int (default: 128)) – minibatch size to load each iteration

• data_and_attributes (dict | None (default: None)) – Dictionary with keys representing keys in data registry (adata_manager.data_registry) and value equal to desired numpy loading type (later made into torch tensor). If None, defaults to all registered data.

• drop_last (bool | int (default: False)) – If True and the dataset is not evenly divisible by batch_size, the last incomplete batch is dropped. If False and the dataset is not evenly divisible by batch_size, then the last batch will be smaller than batch_size.

• distributed_sampler (bool (default: False)) – EXPERIMENTAL Whether to use BatchDistributedSampler as the sampler. If True, sampler must be None.

• data_loader_kwargs – Keyword arguments for DataLoader

Attributes table

multiprocessing_context
dataset
batch_size
num_workers
pin_memory
drop_last
timeout
sampler
pin_memory_device
prefetch_factor

Methods table

check_worker_number_rationality()

Attributes

ConcatDataLoader.multiprocessing_context

ConcatDataLoader.dataset: Dataset[_T_co]

ConcatDataLoader.batch_size: int | None

ConcatDataLoader.num_workers: int

ConcatDataLoader.pin_memory: bool

ConcatDataLoader.drop_last: bool

ConcatDataLoader.timeout: float

ConcatDataLoader.sampler: Sampler | Iterable

ConcatDataLoader.pin_memory_device: str

ConcatDataLoader.prefetch_factor: int | None

Methods

ConcatDataLoader.check_worker_number_rationality()

Return type:

None