[Feature] Eval package evaluation

`evaluate_model` in `PackageBasedModel` and `EnviFormer` now use evaluation packages if any are present instead of the random splits.

Co-authored-by: Liam Brydon <62733830+MyCreativityOutlet@users.noreply.github.com>
Reviewed-on: enviPath/enviPy#148
Co-authored-by: liambrydon <lbry121@aucklanduni.ac.nz>
Co-committed-by: liambrydon <lbry121@aucklanduni.ac.nz>
This commit is contained in:
2025-10-08 19:03:21 +13:00
committed by jebus
parent 36879c266b
commit 22f0bbe10b
3 changed files with 195 additions and 168 deletions

View File

@ -20,7 +20,7 @@ class EnviFormerTest(TestCase):
with self.settings(MODEL_DIR=tmpdir):
threshold = float(0.5)
data_package_objs = [self.BBD_SUBSET]
eval_packages_objs = []
eval_packages_objs = [self.BBD_SUBSET]
mod = EnviFormer.create(self.package, data_package_objs, eval_packages_objs, threshold=threshold)
mod.build_dataset()