feat: add versioned DEB bias backtesting

tests/test_deb_evaluation_upgrade.py

@@ -0,0 +1,121 @@
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+from src.analysis.deb_evaluation import (
+    DEB_RAW_VERSION,
+    DEB_RECENT_BIAS_CORRECTED_VERSION,
+    backtest_deb_versions,
+    build_recent_bias_corrector,
+    evaluate_prediction_records,
+    write_backtest_report,
+)
+from src.database.runtime_state import DailyRecordRepository, RuntimeStateDB
+
+
+def test_deb_evaluation_reports_mae_rmse_bias_and_bucket_hits():
+    records = [
+        {"city": "ankara", "target_date": "2026-05-20", "prediction": 20.0, "actual": 21.0},
+        {"city": "ankara", "target_date": "2026-05-21", "prediction": 22.0, "actual": 21.0},
+        {"city": "ankara", "target_date": "2026-05-22", "prediction": 23.0, "actual": 23.0},
+    ]
+
+    metrics = evaluate_prediction_records(records, version=DEB_RAW_VERSION)
+
+    assert metrics["version"] == DEB_RAW_VERSION
+    assert metrics["samples"] == 3
+    assert metrics["mae"] == 0.667
+    assert metrics["rmse"] == 0.816
+    assert metrics["bias"] == 0.0
+    assert metrics["bucket_hit_rate"] == 0.333
+
+
+def test_recent_bias_corrector_uses_signed_error_without_rewriting_raw_deb():
+    history = [
+        {"city": "ankara", "target_date": "2026-05-20", "deb_prediction": 20.0, "actual_high": 22.0},
+        {"city": "ankara", "target_date": "2026-05-21", "deb_prediction": 21.0, "actual_high": 23.0},
+        {"city": "ankara", "target_date": "2026-05-22", "deb_prediction": 24.0, "actual_high": 25.0},
+    ]
+
+    corrector = build_recent_bias_corrector(history, lookback_days=30, min_samples=2)
+    corrected = corrector.apply("ankara", raw_prediction=24.0)
+
+    assert corrected["version"] == DEB_RECENT_BIAS_CORRECTED_VERSION
+    assert corrected["raw_prediction"] == 24.0
+    assert corrected["corrected_prediction"] > corrected["raw_prediction"]
+    assert corrected["bias_adjustment"] == 1.0
+    assert corrected["samples"] == 3
+
+
+def test_backtest_deb_versions_compares_raw_and_bias_corrected_versions():
+    history = [
+        {"city": "ankara", "target_date": "2026-05-20", "deb_prediction": 20.0, "actual_high": 22.0},
+        {"city": "ankara", "target_date": "2026-05-21", "deb_prediction": 21.0, "actual_high": 23.0},
+        {"city": "ankara", "target_date": "2026-05-22", "deb_prediction": 24.0, "actual_high": 25.0},
+        {"city": "ankara", "target_date": "2026-05-23", "deb_prediction": 24.0, "actual_high": 26.0},
+    ]
+
+    report = backtest_deb_versions(history, train_lookback_days=30)
+
+    assert report["schema_version"] == "deb_backtest_report.v1"
+    assert report["versions"][DEB_RAW_VERSION]["samples"] == 2
+    assert report["versions"][DEB_RECENT_BIAS_CORRECTED_VERSION]["samples"] == 2
+    assert (
+        report["versions"][DEB_RECENT_BIAS_CORRECTED_VERSION]["mae"]
+        < report["versions"][DEB_RAW_VERSION]["mae"]
+    )
+    assert report["rows"][0]["versions"][DEB_RAW_VERSION]["prediction"] == 24.0
+    assert report["rows"][0]["versions"][DEB_RECENT_BIAS_CORRECTED_VERSION]["prediction"] == 24.8
+
+
+def test_write_backtest_report_persists_versioned_json_and_csv(tmp_path):
+    history = [
+        {"city": "ankara", "target_date": "2026-05-20", "deb_prediction": 20.0, "actual_high": 22.0},
+        {"city": "ankara", "target_date": "2026-05-21", "deb_prediction": 21.0, "actual_high": 23.0},
+        {"city": "ankara", "target_date": "2026-05-22", "deb_prediction": 24.0, "actual_high": 25.0},
+    ]
+    report = backtest_deb_versions(history)
+    json_path = tmp_path / "deb-backtest.json"
+    csv_path = tmp_path / "deb-backtest.csv"
+
+    write_backtest_report(report, json_path=json_path, csv_path=csv_path)
+
+    assert json_path.read_text(encoding="utf-8").startswith("{\n  \"schema_version\": \"deb_backtest_report.v1\"")
+    csv_text = csv_path.read_text(encoding="utf-8")
+    assert "deb_v1_raw_prediction" in csv_text
+    assert "deb_v1_recent_bias_corrected_prediction" in csv_text
+
+
+def test_backtest_deb_versions_cli_reads_sqlite_and_writes_outputs(tmp_path):
+    db_path = tmp_path / "polyweather.db"
+    db = RuntimeStateDB(str(db_path))
+    repo = DailyRecordRepository(db)
+    repo.upsert_record("ankara", "2026-05-20", {"deb_prediction": 20.0, "actual_high": 22.0})
+    repo.upsert_record("ankara", "2026-05-21", {"deb_prediction": 21.0, "actual_high": 23.0})
+    repo.upsert_record("ankara", "2026-05-22", {"deb_prediction": 24.0, "actual_high": 25.0})
+    json_path = tmp_path / "report.json"
+    csv_path = tmp_path / "report.csv"
+
+    result = subprocess.run(
+        [
+            sys.executable,
+            str(Path("scripts") / "backtest_deb_versions.py"),
+            "--db",
+            str(db_path),
+            "--output-json",
+            str(json_path),
+            "--output-csv",
+            str(csv_path),
+        ],
+        cwd=Path(__file__).resolve().parents[1],
+        text=True,
+        capture_output=True,
+        check=False,
+    )
+
+    assert result.returncode == 0, result.stderr
+    payload = json.loads(json_path.read_text(encoding="utf-8"))
+    assert payload["schema_version"] == "deb_backtest_report.v1"
+    assert payload["versions"][DEB_RAW_VERSION]["samples"] == 1
+    assert csv_path.exists()

tests/test_deb_model_family.py

@@ -1,5 +1,6 @@
 from src.analysis.deb_algorithm import (
     _collapse_forecasts_for_deb,
+    calculate_deb_prediction,
     calculate_dynamic_weights,
 )
 
@@ -91,6 +92,42 @@ def test_deb_weighted_path_uses_deduped_family_values(monkeypatch):
     assert "家族去重" in info
 
 
+def test_calculate_deb_prediction_keeps_raw_and_adds_versioned_bias_correction(monkeypatch):
+    monkeypatch.setattr(
+        "src.analysis.deb_algorithm.load_history",
+        lambda _: {
+            "ankara": {
+                "2026-04-14": {
+                    "actual_high": 22.0,
+                    "deb_prediction": 20.0,
+                    "forecasts": {"ECMWF": 20.0, "GFS": 20.0},
+                },
+                "2026-04-15": {
+                    "actual_high": 23.0,
+                    "deb_prediction": 21.0,
+                    "forecasts": {"ECMWF": 21.0, "GFS": 21.0},
+                },
+                "2026-04-16": {
+                    "actual_high": 25.0,
+                    "deb_prediction": 24.0,
+                    "forecasts": {"ECMWF": 24.0, "GFS": 24.0},
+                },
+            }
+        },
+    )
+
+    result = calculate_deb_prediction(
+        "ankara",
+        {"ECMWF": 24.0, "GFS": 24.0},
+    )
+
+    assert result["raw_prediction"] == 24.0
+    assert result["prediction"] == 25.0
+    assert result["version"] == "deb_v1_recent_bias_corrected"
+    assert result["bias_adjustment"] == 1.0
+    assert result["bias_samples"] == 3
+
+
 def test_compute_hourly_model_errors_basic():
     from src.analysis.deb_algorithm import compute_hourly_model_errors