identify_precise_features
Note
This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.
- identify_precise_features(experiments: Mapping[str, DataFrame], *, lcl_threshold: float = 0.5, include: Sequence[str] = (), exclude: Sequence[str] = ()) PreciseFeatureSet[source]
Select the features that clear the LCL threshold in EVERY experiment.
- Parameters:
experiments – Experiment name to cohort-level panel (e.g.
{"repeatability": ..., "reproducibility_radius": ..., "reproducibility_binwidth": ...}); at least one.lcl_threshold – Lower-confidence-limit cutoff;
0.5is the paper’s “at least good” boundary.include – Expert overrides added regardless of the criteria (the paper used this for NGTDM Coarseness); must name real features.
exclude – Features removed regardless of the criteria.
- Returns:
The precise feature set with the evidence panels attached.
- Raises:
HABITAPIError – If no experiment is given, the feature sets differ, or an override names an unknown feature.
