instancelib.instances.text module

class instancelib.instances.text.MemoryTextInstance(identifier, data, vector, representation=None, tokenized=None, map_to_original=None, split_marker=None)

Bases: DataPoint[Union[KT, UUID], str, VT, str], TextInstance[Union[KT, UUID], VT], Generic[KT, VT]

Parameters:

• identifier (Union[TypeVar(KT), UUID]) –

• data (str) –

• vector (Optional[TypeVar(VT)]) –

• representation (Optional[str]) –

• tokenized (Optional[Sequence[str]]) –

• map_to_original (Optional[ndarray[Any, dtype[Any]]]) –

• split_marker (Optional[Any]) –

property map_to_original: ndarray[Any, dtype[Any]] | None

property split_marker: Any | None

property tokenized: Sequence[str] | None

class instancelib.instances.text.TextInstance(*args, **kwds)

Bases: Instance[KT, str, VT, str], ABC, Generic[KT, VT]

abstract property map_to_original: ndarray[Any, dtype[Any]] | None

abstract property split_marker: Any | None

abstract property tokenized: Sequence[str] | None

class instancelib.instances.text.TextInstanceProvider(instances)

Bases: AbstractMemoryProvider[MemoryTextInstance[KT, VT], Union[KT, UUID], str, VT, str], Generic[KT, VT]

Parameters:

instances (Iterable[TypeVar(InstanceType, bound= Instance[Any, Any, Any, Any])]) –

children: Dict[KT, Set[KT]]

static construct(*args, **kwargs)

Parameters:

• args (Any) –

• kwargs (Any) –

Return type:

MemoryTextInstance[TypeVar(KT), TypeVar(VT)]

create(*args, **kwargs)

Create a new instance of type InstanceType. The created instance is subsequently added to the provider.

Note: The number of arguments and keyword arguments may differ in actual implementation, so there are no standard arguments.

Returns:

The new instance Type

Return type:

InstanceType

Parameters:

• args (Any) –

• kwargs (Any) –

dictionary: Dict[KT, InstanceType]

parents: Dict[KT, KT]