ML-002: Trainingspipeline mit Tainted-Data-Check

app/ml/__init__.py

@@ -1,5 +1,5 @@
+
 """Machine-Learning-Grundbausteine für SillyHome Next."""
-
+__all__ = ["FeatureStore", "FeatureVector"]
 from app.ml.feature_store import FeatureStore, FeatureVector
-
+from app.ml.training import TrainedArtifact, TrainingPipeline
-__all__ = ["FeatureStore", "FeatureVector"]

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]

tests/ml/test_training.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import pytest
+
+from app.ml.feature_store import FeatureStore, FeatureVector
+from app.ml.training import TrainingPipeline, TrainedArtifact
+
+
+def _vector(sensor_id: str, temperature: float, label: str | None = None) -> FeatureVector:
+    return FeatureVector(sensor_id=sensor_id, values={"temperature": temperature}, label=label)
+
+
+def store_with_data() -> TrainingPipeline:
+    store = FeatureStore()
+    store.add_batch(
+        [
+            _vector("sensor.kitchen", 19.0),
+            _vector("sensor.kitchen", 20.0),
+            _vector("sensor.bedroom", 18.5),
+        ]
+    )
+    return TrainingPipeline(store)
+
+
+def test_run_returns_trained_artifact() -> None:
+    pipeline = store_with_data()
+    artifact = pipeline.run("artifact_v1")
+    assert artifact.artifact_id == "artifact_v1"
+    assert artifact.supported_sensors == ("sensor.bedroom", "sensor.kitchen")
+
+
+def test_run_without_data_raises_value_error() -> None:
+    pipeline = TrainingPipeline(FeatureStore())
+    with pytest.raises(ValueError):
+        pipeline.run("artifact_v1")
+
+
+def test_export_returns_registered_artifact() -> None:
+    pipeline = store_with_data()
+    pipeline.run("artifact_v1")
+    exported = pipeline.export("artifact_v1")
+    assert exported == pipeline.export("artifact_v1")
+
+
+def test_export_missing_artifact_raises_key_error() -> None:
+    pipeline = store_with_data()
+    with pytest.raises(KeyError):
+        pipeline.export("artifact_v1")