datumaro.plugins.data_formats.arrow.base#

Classes

`ArrowBase`(root_path, *, file_paths[, ctx])
`ArrowSubsetBase`(lookup, ...)
`Metadata`(infos, categories, media_type)

class datumaro.plugins.data_formats.arrow.base.ArrowSubsetBase(lookup: ~typing.Dict[str, ~datumaro.components.dataset_base.DatasetItem], infos: ~typing.Dict[str, ~typing.Any], categories: ~typing.Dict[~datumaro.components.annotation.AnnotationType, ~datumaro.components.annotation.Categories], subset: str, media_type: ~typing.Type[~datumaro.components.media.MediaElement] = <class 'datumaro.components.media.Image'>, ann_types: ~typing.Set[~datumaro.components.annotation.AnnotationType] | None = None)[source]#

Bases: SubsetBase

get(item_id: str, subset: str | None = None) → DatasetItem | None[source]#: Provides random access to dataset items.

class datumaro.plugins.data_formats.arrow.base.Metadata(infos: Dict, categories: Dict, media_type: Type[datumaro.components.media.MediaElement])[source]#

Bases: object

infos: Dict#

categories: Dict#

media_type: Type[MediaElement]#

class datumaro.plugins.data_formats.arrow.base.ArrowBase(root_path: str, *, file_paths: List[str], ctx: ImportContext | None = None)[source]#

Bases: DatasetBase

infos() → Dict[str, Any][source]#: Returns meta-info of dataset.

categories() → Dict[AnnotationType, Categories][source]#: Returns metainfo about dataset labels.

get(item_id: str, subset: str | None = None) → DatasetItem | None[source]#: Provides random access to dataset items.

property lookup: Dict[str, Dict[str, int]]#

subsets() → Dict[str, IDataset][source]#: Enumerates subsets in the dataset. Each subset can be a dataset itself.

get_subset(name: str) → IDataset[source]#