harden model registry persistence and evaluation

app/ml/evaluation.py

@@ -1,11 +1,10 @@
 from __future__ import annotations
 
 import logging
-from dataclasses import dataclass, field
-from typing import Sequence
+from collections.abc import Sequence
+from dataclasses import dataclass
 
-from app.ml.feature_store import FeatureVector
-from app.ml.training import TrainingPipeline, TrainedArtifact
+from app.ml.training import TrainingPipeline
 
 logger = logging.getLogger(__name__)
 
@@ -29,15 +28,16 @@ class Evaluator:
         self._pipeline = pipeline
 
     def evaluate(self, artifact_id: str, predictions: Sequence[str]) -> EvalReport:
-        artifacts = list(self._pipeline._artifacts)
-        if not artifacts:
-            raise ValueError("Kein trainiertes Modell für Evaluation vorhanden.")
+        try:
+            supported_sensors = set(self._pipeline.export(artifact_id).supported_sensors)
+        except KeyError as exc:
+            raise ValueError("Kein trainiertes Modell für Evaluation vorhanden.") from exc
 
-        supported_sensors = self._pipeline.export(artifact_id).supported_sensors
-        unknown_hits = sum(1 for prediction in predictions if ":" not in prediction)
-        supported_references = sum(1 for sensor in supported_sensors for prediction in predictions if sensor in prediction)
+        parsed_sensors = [_prediction_sensor(prediction) for prediction in predictions]
+        supported_hits = sum(sensor in supported_sensors for sensor in parsed_sensors)
+        unknown_hits = sum(sensor not in supported_sensors for sensor in parsed_sensors)
         sample_size = len(predictions)
-        coverage = supported_references / sample_size if sample_size else 0.0
+        coverage = supported_hits / sample_size if sample_size else 0.0
         unknown_rate = unknown_hits / sample_size if sample_size else 0.0
 
         coverage_metric = Metric(name="coverage", value=coverage, threshold=0.8)
@@ -54,4 +54,11 @@ class Evaluator:
             coverage,
             unknown_rate,
         )
-        return report
+        return report
+
+
+def _prediction_sensor(prediction: str) -> str | None:
+    parts = prediction.split(":", 2)
+    if len(parts) != 3 or not parts[0] or not parts[1]:
+        return None
+    return parts[1]