unitxt.collections_operators module

class unitxt.collections_operators.Chunk(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, size: int)

Bases: FieldOperator

class unitxt.collections_operators.Dictify(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, with_keys: ~typing.List[str])

Bases: FieldOperator

class unitxt.collections_operators.DuplicateByList(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str, to_field: str | None = None, use_deep_copy: bool = False)

Bases: StreamOperator

class unitxt.collections_operators.DuplicateBySubLists(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str, to_field: str | None = None, use_deep_copy: bool = False)

Bases: StreamOperator

class unitxt.collections_operators.Explode(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str, to_field: str | None = None, use_deep_copy: bool = False)

Bases: DuplicateByList

class unitxt.collections_operators.Filter(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, values: ~typing.List[~typing.Any])

Bases: FieldOperator

class unitxt.collections_operators.Get(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, item: ~typing.Any)

Bases: FieldOperator

class unitxt.collections_operators.GetLength(__tags__: Dict[str, str] = {}, data_classification_policy: List[str] = None, caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: List[List[str]] | Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.collections_operators.Slice(__tags__: Dict[str, str] = {}, data_classification_policy: List[str] = None, caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: List[List[str]] | Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, start: int | None = None, stop: int | None = None, step: int | None = None)

Bases: FieldOperator

class unitxt.collections_operators.Wrap(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, inside: str)

Bases: FieldOperator