ML-008: add statistical baseline model

Closes #19

app/ml/registry/model_registry.py

@@ -2,13 +2,14 @@ from __future__ import annotations
 
 import json
 import logging
+import math
 import os
 from pathlib import Path
 import re
 from threading import RLock
 from collections.abc import Iterable
 
-from app.ml.training import TrainedArtifact
+from app.ml.training import FeatureModel, TrainedArtifact
 
 logger = logging.getLogger(__name__)
 
@@ -52,19 +53,26 @@ class ModelRegistry:
                 raw = json.loads(source.read_text(encoding="utf-8"))
                 artifact_id = raw["artifact_id"]
                 supported_sensors = raw["supported_sensors"]
+                model_type = raw.get("model_type", "metadata")
+                raw_feature_models = raw.get("feature_models", {})
                 if not isinstance(artifact_id, str) or not isinstance(supported_sensors, list):
                     raise ValueError("invalid artifact structure")
+                if not isinstance(model_type, str):
+                    raise ValueError("model_type must be a string")
                 self._validate_artifact_id(artifact_id)
                 if source.name != f"{artifact_id}.json":
                     raise ValueError("artifact id does not match filename")
                 if not all(isinstance(sensor, str) for sensor in supported_sensors):
                     raise ValueError("supported_sensors must contain strings")
+                feature_models = _deserialize_feature_models(raw_feature_models)
             except (KeyError, TypeError, ValueError, json.JSONDecodeError) as exc:
                 raise ValueError(f"Ungültiges Modell-Artefakt: {source.name}") from exc
 
             self._artifacts[artifact_id] = TrainedArtifact(
                 artifact_id=artifact_id,
                 supported_sensors=tuple(supported_sensors),
+                feature_models=feature_models,
+                model_type=model_type,
             )
 
     def _persist(self, artifact: TrainedArtifact) -> None:
@@ -73,6 +81,22 @@ class ModelRegistry:
         payload = {
             "artifact_id": artifact.artifact_id,
             "supported_sensors": list(artifact.supported_sensors),
+            "model_type": artifact.model_type,
+            "feature_models": {
+                sensor_id: {
+                    feature_name: {
+                        "sample_count": model.sample_count,
+                        "mean": model.mean,
+                        "standard_deviation": model.standard_deviation,
+                        "minimum": model.minimum,
+                        "maximum": model.maximum,
+                        "slope": model.slope,
+                        "intercept": model.intercept,
+                    }
+                    for feature_name, model in sorted(models.items())
+                }
+                for sensor_id, models in sorted(artifact.feature_models.items())
+            },
         }
         temporary.write_text(
             json.dumps(payload, ensure_ascii=True, sort_keys=True) + "\n",
@@ -88,3 +112,51 @@ class ModelRegistry:
                 "artifact_id darf nur Buchstaben, Ziffern, Punkt, Unterstrich "
                 "und Bindestrich enthalten."
             )
+
+
+def _deserialize_feature_models(raw: object) -> dict[str, dict[str, FeatureModel]]:
+    if not isinstance(raw, dict):
+        raise ValueError("feature_models must be an object")
+
+    result: dict[str, dict[str, FeatureModel]] = {}
+    for sensor_id, raw_features in raw.items():
+        if not isinstance(sensor_id, str) or not isinstance(raw_features, dict):
+            raise ValueError("invalid sensor feature models")
+        features: dict[str, FeatureModel] = {}
+        for feature_name, raw_model in raw_features.items():
+            if not isinstance(feature_name, str) or not isinstance(raw_model, dict):
+                raise ValueError("invalid feature model")
+            sample_count = raw_model.get("sample_count")
+            if not isinstance(sample_count, int) or isinstance(sample_count, bool) or sample_count < 1:
+                raise ValueError("sample_count must be a positive integer")
+            values = {
+                key: _finite_number(raw_model.get(key))
+                for key in (
+                    "mean",
+                    "standard_deviation",
+                    "minimum",
+                    "maximum",
+                    "slope",
+                    "intercept",
+                )
+            }
+            features[feature_name] = FeatureModel(
+                sample_count=sample_count,
+                mean=values["mean"],
+                standard_deviation=values["standard_deviation"],
+                minimum=values["minimum"],
+                maximum=values["maximum"],
+                slope=values["slope"],
+                intercept=values["intercept"],
+            )
+        result[sensor_id] = features
+    return result
+
+
+def _finite_number(value: object) -> float:
+    if not isinstance(value, (int, float)) or isinstance(value, bool):
+        raise ValueError("feature model values must be finite numbers")
+    converted = float(value)
+    if not math.isfinite(converted):
+        raise ValueError("feature model values must be finite numbers")
+    return converted