feat: add routed model training pipeline

tests/test_training_dataset.py

@@ -6,6 +6,7 @@ from lmpm.training.dataset import (
     TrainingDataError,
     load_sqlite_training_dataset,
 )
+from lmpm.training.workflow import train_sqlite_database
 
 MATERIAL_SCHEMA = """
 CREATE TABLE material_records (
@@ -150,3 +151,20 @@ def test_database_without_material_table_raises_expected_error(tmp_path):
 
     with pytest.raises(TrainingDataError, match="material_records"):
         load_sqlite_training_dataset(database_path)
+
+
+def test_sqlite_workflow_trains_and_saves_every_target_model(tmp_path):
+    database_path = create_database(tmp_path)
+    artifact_path = tmp_path / "lmpm.joblib"
+
+    bundle = train_sqlite_database(database_path, artifact_path)
+
+    assert artifact_path.exists()
+    assert set(bundle.models) == {
+        "is_cut_through",
+        "carbonized_edge_width",
+        "etching_depth",
+        "is_fire_smolder",
+        "pattern_clarity_score",
+        "presentation_balance_score",
+    }

tests/test_training_models.py

@@ -0,0 +1,98 @@
+import numpy as np
+import pytest
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.gaussian_process import GaussianProcessRegressor
+
+from lmpm.training.dataset import (
+    CATEGORICAL_FEATURE_FIELDS,
+    NUMERIC_FEATURE_FIELDS,
+    TrainingDataset,
+    TrainingRecord,
+)
+from lmpm.training.models import (
+    build_estimator,
+    load_training_bundle,
+    save_training_bundle,
+    train_models,
+)
+from lmpm.training.routing import default_model_routes
+
+
+def make_record(number: int, material_name: str) -> TrainingRecord:
+    features = {
+        field: float(number + index + 1)
+        for index, field in enumerate(NUMERIC_FEATURE_FIELDS)
+    }
+    features.update(
+        {
+            CATEGORICAL_FEATURE_FIELDS[0]: "bidirectional",
+            CATEGORICAL_FEATURE_FIELDS[1]: "20x20",
+        }
+    )
+    return TrainingRecord(
+        metadata={
+            "experiment_id": f"LAS-2026-{number:04d}",
+            "material_name": material_name,
+        },
+        features=features,
+        targets={
+            "is_cut_through": number % 2 == 0,
+            "carbonized_edge_width": number / 10,
+            "etching_depth": number * 10.0,
+            "is_fire_smolder": False,
+            "pattern_clarity_score": float(number),
+            "presentation_balance_score": float(10 - number),
+        },
+    )
+
+
+def training_dataset() -> TrainingDataset:
+    return TrainingDataset(
+        records=(
+            make_record(1, "Acrylic"),
+            make_record(2, "Acrylic"),
+            make_record(3, "Basswood"),
+            make_record(4, "Basswood"),
+        )
+    )
+
+
+def test_model_factory_builds_the_routed_estimator_types():
+    routes = {route.target_name: route for route in default_model_routes()}
+
+    assert isinstance(
+        build_estimator(routes["etching_depth"]), GaussianProcessRegressor
+    )
+    assert isinstance(build_estimator(routes["is_cut_through"]), RandomForestClassifier)
+
+
+def test_training_runs_leakage_safe_lomo_and_persists_bundle(tmp_path):
+    bundle = train_models(training_dataset())
+
+    evaluation = bundle.evaluations["etching_depth"]
+    assert [fold.held_out_material for fold in evaluation.folds] == [
+        "Acrylic",
+        "Basswood",
+    ]
+    assert evaluation.mean_metrics["mae"] is not None
+    assert bundle.models["etching_depth"].route.model_family == (
+        "gaussian_process_regressor"
+    )
+
+    features = bundle.models["etching_depth"].preprocessor.transform(training_dataset())
+    predictions = bundle.models["etching_depth"].estimator.predict(features.values)
+    assert isinstance(predictions, np.ndarray)
+    assert predictions.shape == (4,)
+
+    artifact_path = save_training_bundle(bundle, tmp_path / "models.joblib")
+    restored = load_training_bundle(artifact_path)
+    assert restored.report() == bundle.report()
+
+
+def test_training_requires_two_distinct_materials():
+    dataset = TrainingDataset(
+        records=(make_record(1, "Acrylic"), make_record(2, "Acrylic"))
+    )
+
+    with pytest.raises(ValueError, match="at least two materials"):
+        train_models(dataset)