Promote focused small-building detector

2026-07-13 12:15:27 +02:00
parent b3f7c3ca63
commit 1689dce928
20 changed files with 546 additions and 61 deletions
@@ -119,6 +119,7 @@ def audit_feature_collection(payload: dict[str, Any], geod: Any, shape: Any) ->
    reference_ids: set[str] = set()
    false_negative_areas: list[float] = []
    matched_reference_areas: list[float] = []
+    reference_records: dict[str, dict[str, Any]] = {}
    bucket_counts = {
        label: {"false_negative": 0, "matched_reference": 0, "total_reference": 0, "false_negative_rate": None}
        for label, _, _ in AREA_BUCKETS
@@ -144,6 +145,11 @@ def audit_feature_collection(payload: dict[str, Any], geod: Any, shape: Any) ->
        bucket = area_bucket(area_m2)
        reference_id = stable_reference_id(feature, geometry)
        reference_ids.add(reference_id)
+        reference_records[reference_id] = {
+            "area_m2": area_m2,
+            "area_bucket": bucket,
+            "feature": feature,
+        }
        bucket_role = "false_negative" if role == "false_negative" else "matched_reference"
        bucket_counts[bucket][bucket_role] += 1
        bucket_counts[bucket]["total_reference"] += 1
@@ -161,6 +167,7 @@ def audit_feature_collection(payload: dict[str, Any], geod: Any, shape: Any) ->
    return {
        "false_negative_ids": false_negative_ids,
        "reference_ids": reference_ids,
+        "reference_records": reference_records,
        "false_negative_count": len(false_negative_areas),
        "matched_reference_count": len(matched_reference_areas),
        "total_reference_count": total_reference,
@@ -285,6 +292,7 @@ def run_audit(portfolio_args: list[str], output_dir: Path) -> tuple[Path, Path]:
            )

    sample_reports: list[dict[str, Any]] = []
+    persistent_evidence_features: list[dict[str, Any]] = []
    for sample_slug in sorted(expected_slugs):
        portfolio_rows = []
        false_negative_sets = []
@@ -297,7 +305,7 @@ def run_audit(portfolio_args: list[str], output_dir: Path) -> tuple[Path, Path]:
                {
                    key: value
                    for key, value in raw.items()
-                    if key not in {"false_negative_ids", "reference_ids"}
+                    if key not in {"false_negative_ids", "reference_ids", "reference_records"}
                }
            )
        if any(reference_ids != reference_sets[0] for reference_ids in reference_sets[1:]):
@@ -309,16 +317,61 @@ def run_audit(portfolio_args: list[str], output_dir: Path) -> tuple[Path, Path]:
                f"Sample {sample_slug} has different reference populations across portfolios ({counts})"
            )
        persistent_ids = sorted(set.intersection(*false_negative_sets))
+        reference_records = portfolio_samples[parsed_portfolios[0][0]][sample_slug]["reference_records"]
+        persistent_areas = [float(reference_records[reference_id]["area_m2"]) for reference_id in persistent_ids]
+        persistent_bucket_counts = {
+            label: {"count": 0, "share": 0.0}
+            for label, _, _ in AREA_BUCKETS
+        }
+        for reference_id in persistent_ids:
+            record = reference_records[reference_id]
+            persistent_bucket_counts[record["area_bucket"]]["count"] += 1
+            source_feature = record["feature"]
+            properties = dict(source_feature.get("properties") or {})
+            properties.update(
+                {
+                    "qa_evidence_role": "persistent_false_negative",
+                    "sample_slug": sample_slug,
+                    "persistent_reference_id": reference_id,
+                    "area_m2": record["area_m2"],
+                    "area_bucket": record["area_bucket"],
+                    "compared_portfolios": labels,
+                }
+            )
+            persistent_evidence_features.append(
+                {
+                    "type": "Feature",
+                    "id": f"{sample_slug}:{reference_id}",
+                    "properties": properties,
+                    "geometry": source_feature["geometry"],
+                }
+            )
+        if persistent_ids:
+            for values in persistent_bucket_counts.values():
+                values["share"] = values["count"] / len(persistent_ids)
        sample_reports.append(
            {
                "sample_slug": sample_slug,
                "reference_population_count": len(reference_sets[0]),
                "persistent_false_negative_count": len(persistent_ids),
                "persistent_reference_ids": persistent_ids,
+                "persistent_false_negative_area_m2": area_stats(persistent_areas),
+                "persistent_area_buckets": persistent_bucket_counts,
                "portfolios": portfolio_rows,
            }
        )

+    output_dir = output_dir.expanduser().resolve()
+    output_dir.mkdir(parents=True, exist_ok=True)
+    persistent_geojson_path = output_dir / "persistent_false_negatives.geojson"
+    persistent_geojson_path.write_text(
+        json.dumps(
+            {"type": "FeatureCollection", "features": persistent_evidence_features},
+            indent=2,
+            sort_keys=True,
+        ),
+        encoding="utf-8",
+    )
    report = {
        "generated_at": datetime.now(timezone.utc).isoformat(),
        "schema_version": 1,
@@ -328,10 +381,9 @@ def run_audit(portfolio_args: list[str], output_dir: Path) -> tuple[Path, Path]:
        "portfolios": portfolio_meta,
        "sample_count": len(sample_reports),
        "samples": sample_reports,
+        "persistent_evidence_geojson_path": str(persistent_geojson_path),
        "recommendations": build_recommendations(sample_reports),
    }
-    output_dir = output_dir.expanduser().resolve()
-    output_dir.mkdir(parents=True, exist_ok=True)
    json_path = output_dir / "detection_false_negative_audit.json"
    json_path.write_text(json.dumps(report, indent=2, sort_keys=True), encoding="utf-8")

@@ -345,18 +397,26 @@ def run_audit(portfolio_args: list[str], output_dir: Path) -> tuple[Path, Path]:
        "",
        "## AOI comparison",
        "",
-        "| AOI | Persistent misses | "
+        "| AOI | Persistent misses | Persistent tiny/small | Persistent median m2 | "
        + " | ".join(f"{label} FN rate" for label, _ in parsed_portfolios)
        + " |",
-        "|---|---:|" + "---:|" * len(parsed_portfolios),
+        "|---|---:|---:|---:|" + "---:|" * len(parsed_portfolios),
    ]
    for sample in sample_reports:
        rates = [
            f"{(row['false_negative_rate'] or 0.0):.3f}"
            for row in sample["portfolios"]
        ]
+        persistent_buckets = sample["persistent_area_buckets"]
+        persistent_small_count = sum(
+            persistent_buckets[key]["count"]
+            for key in ("tiny_lt_25_m2", "small_25_100_m2")
+        )
+        persistent_median = sample["persistent_false_negative_area_m2"]["median"]
+        persistent_median_text = f"{persistent_median:.1f}" if persistent_median is not None else "n/a"
        lines.append(
            f"| {sample['sample_slug']} | {sample['persistent_false_negative_count']} | "
+            f"{persistent_small_count} | {persistent_median_text} | "
            + " | ".join(rates)
            + " |"
        )