ML-006: Training- und Evaluations-Workflow vorbereiten

tests/ml/test_training_evaluation.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+from app.ml.evaluation import Evaluator, EvalReport, Metric
+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 test_end_to_end_training_then_evaluation() -> None:
+    store = FeatureStore()
+    store.add_batch([_vector("sensor.kitchen", 19.0), _vector("sensor.bedroom", 18.5)])
+    pipeline = TrainingPipeline(store)
+    artifact = pipeline.run("artifact_v1")
+
+    evaluator = Evaluator(pipeline)
+    predictions = [
+        "artifact_v1:sensor.kitchen:{'temperature': 21.0}",
+        "artifact_v1:sensor.bedroom:{'temperature': 18.5}",
+    ]
+    report = evaluator.evaluate(artifact.artifact_id, predictions)
+    assert isinstance(report, EvalReport)
+    assert report.sample_size == len(predictions)
+    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"
+    assert metric.value == 0.85
+    assert metric.threshold == 0.8