Expand YOLO training AOIs safely

backend/tests/test_sprint131_operator_sample_expansion.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import importlib.util
+import math
 from pathlib import Path
 import sys
 
@@ -43,6 +44,40 @@ def test_operator_sample_registry_includes_kempen_reference_and_background_candi
     assert all(module.SAMPLES[slug].sample_role == "background_candidate" for slug in expected_background_slugs)
 
 
+def test_operator_training_expansion_preserves_geographically_separate_holdouts() -> None:
+    module = load_sample_preparer()
+
+    expected_expansion = {"olen_center", "lille_center", "oud_turnhout_center", "kasterlee_center"}
+    expected_holdouts = {"turnhout", "retie", "westerlo", "arendonk_heide"}
+
+    assert module.TRAINING_EXPANSION_SAMPLE_SLUGS == frozenset(expected_expansion)
+    assert module.DEFAULT_VALIDATION_SAMPLE_SLUGS == frozenset(expected_holdouts)
+    assert all(module.SAMPLES[slug].sample_role == "reference" for slug in expected_expansion)
+    assert all(not module.SAMPLES[slug].allow_empty_reference for slug in expected_expansion)
+    assert all(module.recommended_split_for_sample(module.SAMPLES[slug]) == "train" for slug in expected_expansion)
+    assert all(module.recommended_split_for_sample(module.SAMPLES[slug]) == "val" for slug in expected_holdouts)
+
+    def distance_m(left, right) -> float:
+        radius_m = 6_371_008.8
+        left_lat = math.radians(left.center_lat)
+        right_lat = math.radians(right.center_lat)
+        delta_lat = right_lat - left_lat
+        delta_lon = math.radians(right.center_lon - left.center_lon)
+        haversine = (
+            math.sin(delta_lat / 2) ** 2
+            + math.cos(left_lat) * math.cos(right_lat) * math.sin(delta_lon / 2) ** 2
+        )
+        return 2 * radius_m * math.asin(math.sqrt(haversine))
+
+    reference_holdouts = expected_holdouts - {"arendonk_heide"}
+    for expansion_slug in expected_expansion:
+        expansion = module.SAMPLES[expansion_slug]
+        assert min(
+            distance_m(expansion, module.SAMPLES[holdout_slug])
+            for holdout_slug in reference_holdouts
+        ) >= 2_000
+
+
 def test_operator_background_candidates_are_unique_enough_for_hard_negative_training() -> None:
     module = load_sample_preparer()