Promote focused small-building detector

backend/tests/test_sprint131_operator_sample_expansion.py

@@ -51,7 +51,7 @@ def test_operator_training_expansion_preserves_geographically_separate_holdouts(
     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 expected_holdouts.issubset(module.DEFAULT_VALIDATION_SAMPLE_SLUGS)
     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)
@@ -78,6 +78,51 @@ def test_operator_training_expansion_preserves_geographically_separate_holdouts(
         ) >= 2_000
 
 
+def test_small_building_expansion_has_separate_training_and_validation_centers() -> None:
+    module = load_sample_preparer()
+
+    expected_training = {
+        "beerse_center",
+        "rijkevorsel_center",
+        "hoogstraten_center",
+        "vorselaar_center",
+    }
+    expected_validation = {"vosselaar_center", "grobbendonk_center"}
+
+    assert module.SMALL_BUILDING_TRAINING_SAMPLE_SLUGS == frozenset(expected_training)
+    assert module.SMALL_BUILDING_VALIDATION_SAMPLE_SLUGS == frozenset(expected_validation)
+    assert expected_validation.issubset(module.DEFAULT_VALIDATION_SAMPLE_SLUGS)
+    assert all(module.SAMPLES[slug].sample_role == "reference" for slug in expected_training | expected_validation)
+    assert all(
+        module.recommended_split_for_sample(module.SAMPLES[slug]) == "train"
+        for slug in expected_training
+    )
+    assert all(
+        module.recommended_split_for_sample(module.SAMPLES[slug]) == "val"
+        for slug in expected_validation
+    )
+
+    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))
+
+    protected_holdouts = expected_validation | {"turnhout", "retie", "westerlo"}
+    for training_slug in expected_training:
+        training_sample = module.SAMPLES[training_slug]
+        assert min(
+            distance_m(training_sample, module.SAMPLES[holdout_slug])
+            for holdout_slug in protected_holdouts
+        ) >= 2_000
+
+
 def test_operator_background_candidates_are_unique_enough_for_hard_negative_training() -> None:
     module = load_sample_preparer()