← Back to API reference

neuralset.extractors.meta.CroppedExtractor

pydantic model neuralset.extractors.meta.CroppedExtractor

Crop a extractor to a given offset and duration.

Parameters:

• extractor (BaseExtractor) – The extractor to crop.

• offset (float) – The offset (in seconds) from the start of the event to begin the crop.

• duration (PositiveFloat | None) – The duration (in seconds) of the crop. If None, the crop extends to the end of the event.

• frequency (Literal["native"]) – The frequency of the cropped extractor. Must be “native”. Never used

Fields:

• duration (Annotated[float, annotated_types.Gt(gt=0)] | None)

• event_types (str | tuple[str, ...])

• extractor (neuralset.extractors.base.BaseExtractor)

• frequency (Literal['native'])

• offset (float)

field event_types: str | tuple[str, ...] = 'Event'

field extractor: BaseExtractor [Required]

field offset: float = 0

field duration: Annotated[float, Gt(gt=0)] | None = None

field frequency: Literal['native'] = 'native'

prepare(obj: Any) → None

Pre-compute and cache extractor data for a collection of events.

This method triggers _get_data on every matching event so that expensive computation (e.g. model inference) is done once and cached. It then calls the extractor on a single event to populate the output shape, which is needed when allow_missing=True.

Call prepare before using the extractor in a dataloader.

Parameters:

obj (DataFrame or sequence of Event or sequence of Segment) – The structure containing the events. When calling prepare on several objects, prefer passing a list of events or segments over a DataFrame to avoid redundant conversion overhead.

requirements: tp.ClassVar[tuple[str, ...]] = ()

← Back to API reference