ML-004: Training-Feedback und Evaluation-Metriken

tests/ml/test_evaluation.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+import pytest
+
+from app.ml.evaluation import Evaluator
+from app.ml.feature_store import FeatureStore, FeatureVector
+from app.ml.training import TrainingPipeline
+
+
+def _vector(sensor_id: str, temperature: float, label: str | None = None) -> FeatureVector:
+    return FeatureVector(sensor_id=sensor_id, values={"temperature": temperature}, label=label)
+
+
+def evaluator_factory() -> Evaluator:
+    store = FeatureStore()
+    store.add_batch([_vector("sensor.kitchen", 19.0), _vector("sensor.bedroom", 18.5)])
+    pipeline = TrainingPipeline(store)
+    pipeline.run("artifact_v1")
+    return Evaluator(pipeline)
+
+
+def test_evaluate_returns_report_with_metrics() -> None:
+    evaluator = evaluator_factory()
+    report = evaluator.evaluate("artifact_v1", ["artifact_v1:sensor.kitchen:{'temperature': 21.0}", "artifact_v1:sensor.bedroom:{'temperature': 18.5}"])
+    assert report.artifact_id == "artifact_v1"
+    assert report.sample_size == 2
+    assert {metric.name for metric in report.metrics} == {"coverage", "unknown_rate"}
+
+
+def test_evaluate_without_training_raises_value_error() -> None:
+    evaluator = Evaluator(TrainingPipeline(FeatureStore()))
+    with pytest.raises(ValueError):
+        evaluator.evaluate("artifact_v1", [])