HabitatAssigner

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

class HabitatAssigner(*args, **kwargs)

Bases: Protocol

Assign habitat labels to one subject using a fitted model.

Keeping this separate from the fitter is what enforces train/predict consistency structurally rather than by convention: prediction has no way to re-learn anything, because everything it needs is inside the model.

The model is supplied to the CONSTRUCTOR, not to the call. Two consequences follow: the assigner becomes an ordinary one-argument callable (a subject-level operator like every other step), and an assigner cannot be constructed without a fitted model, so “predicting before fitting” becomes unrepresentable.

property spec: Spec

Return the algorithm specification.

property model: HabitatModel

Return the fitted habitat definition this assigner projects.

__call__(supervoxel_map: Supervoxelization) → HabitatMap

Project the fitted habitat definition onto one subject.

Parameters:

supervoxel_map – Supervoxelization of the subject to label.

Returns:

The subject’s habitat label image, tagged with the model’s id.

Raises:

CompatibilityError – If the supervoxel features do not provide the feature names the model requires.

__init__(*args, **kwargs)