ML-002: Trainingspipeline mit Tainted-Data-Check

app/ml/training.py

@@ -0,0 +1,37 @@
+from __future__ import annotations
+
+import logging
+from dataclasses import dataclass
+from typing import Sequence
+
+from app.ml.feature_store import FeatureVector, FeatureStore
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class TrainedArtifact:
+    artifact_id: str
+    supported_sensors: tuple[str, ...]
+
+
+class TrainingPipeline:
+    def __init__(self, store: FeatureStore) -> None:
+        self._store = store
+        self._artifacts: dict[str, TrainedArtifact] = {}
+
+    def run(self, artifact_id: str) -> TrainedArtifact:
+        vectors = self._store.all()
+        if not vectors:
+            raise ValueError("FeatureStore enthält keine Trainingsdaten.")
+
+        sensors = tuple({vector.sensor_id for vector in vectors})
+        artifact = TrainedArtifact(artifact_id=artifact_id, supported_sensors=sensors)
+        self._artifacts[artifact_id] = artifact
+        logger.info("Training abgeschlossen für %s mit %d Sensoren", artifact_id, len(sensors))
+        return artifact
+
+    def export(self, artifact_id: str) -> TrainedArtifact:
+        if artifact_id not in self._artifacts:
+            raise KeyError(f"Artifact '{artifact_id}' nicht gefunden.")
+        return self._artifacts[artifact_id]