ML-008: add statistical baseline model

Closes #19

tests/ml/test_evaluation.py

@@ -24,14 +24,15 @@ def test_evaluate_returns_report_with_metrics() -> None:
     report = evaluator.evaluate(
         "artifact_v1",
         [
-            "artifact_v1:sensor.kitchen:{'temperature': 21.0}",
-            "artifact_v1:sensor.bedroom:{'temperature': 18.5}",
+            _vector("sensor.kitchen", 21.0),
+            _vector("sensor.bedroom", 18.5),
         ],
     )
     assert report.artifact_id == "artifact_v1"
     assert report.sample_size == 2
-    assert {metric.name for metric in report.metrics} == {"coverage", "unknown_rate"}
+    assert {metric.name for metric in report.metrics} == {"mae", "rmse", "coverage"}
     assert next(metric.value for metric in report.metrics if metric.name == "coverage") == 1.0
+    assert next(metric.value for metric in report.metrics if metric.name == "mae") == 0.0
 
 
 def test_evaluate_without_training_raises_value_error() -> None:
@@ -40,16 +41,16 @@ def test_evaluate_without_training_raises_value_error() -> None:
         evaluator.evaluate("artifact_v1", [])
 
 
-def test_coverage_is_bounded_and_requires_exact_sensor_match() -> None:
+def test_coverage_counts_only_supported_sensor_features() -> None:
     evaluator = evaluator_factory()
     report = evaluator.evaluate(
         "artifact_v1",
         [
-            "artifact_v1:sensor.kitchen:{'note': 'sensor.bedroom'}",
-            "artifact_v1:sensor.kitchen_extra:{}",
-            "malformed",
+            _vector("sensor.kitchen", 21.0),
+            FeatureVector(sensor_id="sensor.kitchen", values={"humidity": 50.0}),
+            _vector("sensor.kitchen_extra", 20.0),
         ],
     )
 
     metrics = {metric.name: metric.value for metric in report.metrics}
-    assert metrics == {"coverage": pytest.approx(1 / 3), "unknown_rate": pytest.approx(2 / 3)}
+    assert metrics["coverage"] == pytest.approx(1 / 3)

tests/ml/test_model_registry.py

@@ -19,6 +19,24 @@ def test_registry_loads_persisted_artifacts_after_restart(tmp_path: Path) -> Non
     assert restarted.load_artifact("model-v1") == artifact
 
 
+def test_registry_persists_statistical_parameters(tmp_path: Path) -> None:
+    from app.ml.feature_store import FeatureStore, FeatureVector
+    from app.ml.training import TrainingPipeline
+
+    store = FeatureStore()
+    store.add_batch(
+        [
+            FeatureVector("sensor.kitchen", {"temperature": 19.0}),
+            FeatureVector("sensor.kitchen", {"temperature": 20.0}),
+        ]
+    )
+    artifact = TrainingPipeline(store).run("model-v1")
+
+    ModelRegistry(tmp_path).register(artifact)
+
+    assert ModelRegistry(tmp_path).load_artifact("model-v1") == artifact
+
+
 def test_registry_replaces_persisted_artifact_after_restart(tmp_path: Path) -> None:
     registry = ModelRegistry(tmp_path)
     registry.register(TrainedArtifact("model-v1", ("sensor.kitchen",)))

tests/ml/test_predictor.py

@@ -13,16 +13,26 @@ def _vector(sensor_id: str, temperature: float, label: str | None = None) -> Fea
 
 def predictor() -> Predictor:
     store = FeatureStore()
-    store.add_batch([_vector("sensor.kitchen", 19.0), _vector("sensor.bedroom", 18.5)])
+    store.add_batch(
+        [
+            _vector("sensor.kitchen", 19.0),
+            _vector("sensor.kitchen", 20.0),
+            _vector("sensor.bedroom", 18.5),
+        ]
+    )
     pipeline = TrainingPipeline(store)
     pipeline.run("artifact_v1")
     return Predictor(pipeline)
 
 
-def test_predict_returns_expected_format() -> None:
+def test_predict_returns_statistical_forecast() -> None:
     p = predictor()
     result = p.predict("artifact_v1", _vector("sensor.kitchen", 21.0))
-    assert result == "artifact_v1:sensor.kitchen:{'temperature': 21.0}"
+    assert result.artifact_id == "artifact_v1"
+    assert result.sensor_id == "sensor.kitchen"
+    assert result.predictions == {"temperature": 22.0}
+    assert 0.0 < result.confidence <= 1.0
+    assert result.model_type == "statistical_baseline"
 
 
 def test_predict_rejects_unknown_sensor() -> None:
@@ -45,4 +55,4 @@ def test_default_artifact_returns_last_registered() -> None:
     pipeline = TrainingPipeline(store)
     pipeline.run("first")
     pipeline.run("second")
-    assert Predictor.default_artifact(pipeline).artifact_id == "second"
+    assert Predictor.default_artifact(pipeline).artifact_id == "second"

tests/ml/test_training.py

@@ -27,6 +27,11 @@ def test_run_returns_trained_artifact() -> None:
     artifact = pipeline.run("artifact_v1")
     assert artifact.artifact_id == "artifact_v1"
     assert artifact.supported_sensors == ("sensor.bedroom", "sensor.kitchen")
+    kitchen = artifact.feature_models["sensor.kitchen"]["temperature"]
+    assert kitchen.sample_count == 2
+    assert kitchen.mean == 19.5
+    assert kitchen.slope == 1.0
+    assert kitchen.forecast() == 21.0
 
 
 def test_run_without_data_raises_value_error() -> None:

tests/ml/test_training_evaluation.py

@@ -16,18 +16,18 @@ def test_end_to_end_training_then_evaluation() -> None:
     artifact = pipeline.run("artifact_v1")
 
     evaluator = Evaluator(pipeline)
-    predictions = [
-        "artifact_v1:sensor.kitchen:{'temperature': 21.0}",
-        "artifact_v1:sensor.bedroom:{'temperature': 18.5}",
+    samples = [
+        _vector("sensor.kitchen", 21.0),
+        _vector("sensor.bedroom", 18.5),
     ]
-    report = evaluator.evaluate(artifact.artifact_id, predictions)
+    report = evaluator.evaluate(artifact.artifact_id, samples)
     assert isinstance(report, EvalReport)
-    assert report.sample_size == len(predictions)
+    assert report.sample_size == len(samples)
     assert any(metric.name == "coverage" for metric in report.metrics)
 
 
 def test_metric_helpers_are_serializable() -> None:
-    metric = Metric(name="coverage", value=0.85, threshold=0.8)
-    assert metric.name == "coverage"
+    metric = Metric(name="mae", value=0.85, threshold=1.0)
+    assert metric.name == "mae"
     assert metric.value == 0.85
-    assert metric.threshold == 0.8
+    assert metric.threshold == 1.0