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)