ML-008: add statistical baseline model

Closes #19

app/ml/training.py

@@ -1,17 +1,44 @@
 from __future__ import annotations
 
 import logging
-from dataclasses import dataclass
+import math
+from collections import defaultdict
+from dataclasses import dataclass, field
 
 from app.ml.feature_store import FeatureStore
 
 logger = logging.getLogger(__name__)
 
 
-@dataclass
+@dataclass(frozen=True)
+class FeatureModel:
+    sample_count: int
+    mean: float
+    standard_deviation: float
+    minimum: float
+    maximum: float
+    slope: float
+    intercept: float
+
+    def forecast(self, current_value: float | None = None) -> float:
+        if current_value is not None:
+            return current_value + self.slope
+        return self.intercept + self.slope * self.sample_count
+
+    @property
+    def confidence(self) -> float:
+        sample_score = self.sample_count / (self.sample_count + 2)
+        scale = abs(self.mean) if abs(self.mean) > 1e-9 else 1.0
+        stability_score = 1.0 / (1.0 + self.standard_deviation / scale)
+        return min(0.99, max(0.05, sample_score * stability_score))
+
+
+@dataclass(frozen=True)
 class TrainedArtifact:
     artifact_id: str
     supported_sensors: tuple[str, ...]
+    feature_models: dict[str, dict[str, FeatureModel]] = field(default_factory=dict)
+    model_type: str = "statistical_baseline"
 
 
 class TrainingPipeline:
@@ -24,8 +51,33 @@ class TrainingPipeline:
         if not vectors:
             raise ValueError("FeatureStore enthält keine Trainingsdaten.")
 
-        sensors = tuple(sorted({vector.sensor_id for vector in vectors}))
-        artifact = TrainedArtifact(artifact_id=artifact_id, supported_sensors=sensors)
+        samples: dict[str, dict[str, list[float]]] = defaultdict(lambda: defaultdict(list))
+        for vector in vectors:
+            for feature_name, raw_value in vector.values.items():
+                value = float(raw_value)
+                if math.isfinite(value):
+                    samples[vector.sensor_id][feature_name].append(value)
+
+        feature_models = {
+            sensor_id: {
+                feature_name: _fit_feature(values)
+                for feature_name, values in sorted(features.items())
+                if values
+            }
+            for sensor_id, features in sorted(samples.items())
+        }
+        feature_models = {
+            sensor_id: models for sensor_id, models in feature_models.items() if models
+        }
+        if not feature_models:
+            raise ValueError("Trainingsdaten enthalten keine endlichen numerischen Werte.")
+
+        sensors = tuple(feature_models)
+        artifact = TrainedArtifact(
+            artifact_id=artifact_id,
+            supported_sensors=sensors,
+            feature_models=feature_models,
+        )
         self._artifacts[artifact_id] = artifact
         logger.info("Training abgeschlossen für %s mit %d Sensoren", artifact_id, len(sensors))
         return artifact
@@ -34,3 +86,32 @@ class TrainingPipeline:
         if artifact_id not in self._artifacts:
             raise KeyError(f"Artifact '{artifact_id}' nicht gefunden.")
         return self._artifacts[artifact_id]
+
+
+def _fit_feature(values: list[float]) -> FeatureModel:
+    sample_count = len(values)
+    mean = sum(values) / sample_count
+    variance = sum((value - mean) ** 2 for value in values) / sample_count
+    standard_deviation = math.sqrt(variance)
+
+    if sample_count == 1:
+        slope = 0.0
+        intercept = mean
+    else:
+        x_mean = (sample_count - 1) / 2
+        denominator = sum((index - x_mean) ** 2 for index in range(sample_count))
+        numerator = sum(
+            (index - x_mean) * (value - mean) for index, value in enumerate(values)
+        )
+        slope = numerator / denominator
+        intercept = mean - slope * x_mean
+
+    return FeatureModel(
+        sample_count=sample_count,
+        mean=mean,
+        standard_deviation=standard_deviation,
+        minimum=min(values),
+        maximum=max(values),
+        slope=slope,
+        intercept=intercept,
+    )