hypertower/v4/figures/output/S8e_fused_clinical_importance.csv at 3d7777f010bba80a84973714f9786e526bce5f79

Files

T

rpotter6298 3d7777f010 Add new experiments and analysis scripts for dropzero features

- Introduced `fused_importance_with_axial.py` to evaluate the importance of Axial_Length in the fused-head model.
- Created JSON configurations for various experiments excluding zero-importance clinical features:
  - `cd_solo_bilateral_dropzero.json`: Bilateral clinical-only evaluation.
  - `cd_solo_single_dropzero.json`: Single-eye clinical-only evaluation.
  - `ensemble_refugelike_ckpt_dropzero.json`: Ensemble model with dropped zero-importance features.
  - `ensemble_single_refugelike_dropzero.json`: Single-eye ensemble model with dropped features.

2026-08-24 12:26:16 +02:00

857 B

Raw Blame History

1	feature	mean_drop_across_reps	std_drop_across_reps	baseline_auc_mean	baseline_auc_std	n_reps
2	Age	0.01915686274509804	0.005535822316487697	0.8955147058823529	0.01575126319974185	10
3	IOP_corr	0.015360294117647059	0.006440372950299282	0.8955147058823529	0.01575126319974185	10
4	Gender	0.010316176470588235	0.005983911392207313	0.8955147058823529	0.01575126319974185	10
5	Pachymetry	0.006735294117647063	0.006456431334319213	0.8955147058823529	0.01575126319974185	10
6	Phakic/Pseudophakic	0.0025857843137254933	0.005779537014891194	0.8955147058823529	0.01575126319974185	10
7	astigmatism	2.6960784313724555e-05	0.0012103203246870743	0.8955147058823529	0.01575126319974185	10
8	dioptre_2	-0.00013480392156862828	0.0007757846606353119	0.8955147058823529	0.01575126319974185	10
9	dioptre_1	-0.0029166666666666646	0.003095754152323194	0.8955147058823529	0.01575126319974185	10

857 B Raw Blame History

857 B

Raw Blame History