From 3cf9af35152ac36a3409dd82a6f5cb4e207357e4 Mon Sep 17 00:00:00 2001
From: Pino <pino@it-s-center.de>
Date: Thu, 11 Jun 2026 00:38:45 +0200
Subject: [PATCH] ML-003: Predictor mit Sensor-Validierung und Batch-Interface

---
 app/ml/predictor.py        | 33 ++++++++++++++++++++++++++
 tests/ml/test_predictor.py | 48 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)
 create mode 100644 app/ml/predictor.py
 create mode 100644 tests/ml/test_predictor.py

diff --git a/app/ml/predictor.py b/app/ml/predictor.py
new file mode 100644
index 0000000..ff02d41
--- /dev/null
+++ b/app/ml/predictor.py
@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+import logging
+from functools import lru_cache
+from typing import Sequence
+
+from app.ml.feature_store import FeatureVector
+from app.ml.training import TrainingPipeline, TrainedArtifact
+
+logger = logging.getLogger(__name__)
+
+
+class Predictor:
+    def __init__(self, pipeline: TrainingPipeline) -> None:
+        self._pipeline = pipeline
+
+    def predict(self, artifact_id: str, entity: FeatureVector) -> str:
+        artifact = self._pipeline.export(artifact_id)
+        if entity.sensor_id not in artifact.supported_sensors:
+            raise ValueError(
+                f"Sensor '{entity.sensor_id}' wird vom Modell '{artifact_id}' nicht unterstützt."
+            )
+        return f"{artifact_id}:{entity.sensor_id}:{entity.values}"
+
+    def predict_batch(self, artifact_id: str, entities: Sequence[FeatureVector]) -> list[str]:
+        return [self.predict(artifact_id, entity) for entity in entities]
+
+    @staticmethod
+    def default_artifact(pipeline: TrainingPipeline) -> TrainedArtifact:
+        artifacts = list(pipeline._artifacts)
+        if not artifacts:
+            raise ValueError("Kein trainiertes Modell gefunden.")
+        return pipeline.export(artifacts[-1])
\ No newline at end of file
diff --git a/tests/ml/test_predictor.py b/tests/ml/test_predictor.py
new file mode 100644
index 0000000..3c09a53
--- /dev/null
+++ b/tests/ml/test_predictor.py
@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import pytest
+
+from app.ml.feature_store import FeatureStore, FeatureVector
+from app.ml.predictor import Predictor
+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 predictor() -> Predictor:
+    store = FeatureStore()
+    store.add_batch([_vector("sensor.kitchen", 19.0), _vector("sensor.bedroom", 18.5)])
+    pipeline = TrainingPipeline(store)
+    pipeline.run("artifact_v1")
+    return Predictor(pipeline)
+
+
+def test_predict_returns_expected_format() -> None:
+    p = predictor()
+    result = p.predict("artifact_v1", _vector("sensor.kitchen", 21.0))
+    assert result == "artifact_v1:sensor.kitchen:{'temperature': 21.0}"
+
+
+def test_predict_rejects_unknown_sensor() -> None:
+    p = predictor()
+    with pytest.raises(ValueError):
+        p.predict("artifact_v1", _vector("sensor.unknown", 10.0))
+
+
+def test_predict_batch_matches_single_calls() -> None:
+    p = predictor()
+    entities = [_vector("sensor.kitchen", 21.0), _vector("sensor.bedroom", 19.0)]
+    assert p.predict_batch("artifact_v1", entities) == [
+        p.predict("artifact_v1", item) for item in entities
+    ]
+
+
+def test_default_artifact_returns_last_registered() -> None:
+    store = FeatureStore()
+    store.add_batch([_vector("sensor.kitchen", 19.0), _vector("sensor.bedroom", 18.5)])
+    pipeline = TrainingPipeline(store)
+    pipeline.run("first")
+    pipeline.run("second")
+    assert Predictor.default_artifact(pipeline).artifact_id == "second"
\ No newline at end of file