openstef-models 4.1.2__tar.gz → 4.2.2__tar.gz

{openstef_models-4.1.2 → openstef_models-4.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef-models
-Version: 4.1.2
+Version: 4.2.2
 Summary: Core models for OpenSTEF
 Project-URL: Documentation, https://openstef.github.io/openstef/index.html
 Project-URL: Homepage, https://lfenergy.org/projects/openstef/

{openstef_models-4.1.2 → openstef_models-4.2.2}/pyproject.toml

@@ -7,7 +7,7 @@ requires = [ "hatchling" ]
 
 [project]
 name = "openstef-models"
-version = "4.1.2"
+version = "4.2.2"
 description = "Core models for OpenSTEF"
 readme = "README.md"
 keywords = [ "energy", "forecasting", "machinelearning" ]

{openstef_models-4.1.2 → openstef_models-4.2.2}/src/openstef_models/models/forecasting/lgbm_forecaster.py

@@ -111,6 +111,12 @@ class LGBMHyperParams(HyperParams):
         description="Fraction of features used when constructing each tree. Range: (0,1]",
     )
 
+    # Early Stopping
+    early_stopping_rounds: int | None = Field(
+        default=None,
+        description="Training will stop if performance doesn't improve for this many rounds. Requires validation data.",
+    )
+
     @classmethod
     def forecaster_class(cls) -> "type[LGBMForecaster]":
         """Create a LightGBM forecaster instance from this configuration.
@@ -184,10 +190,6 @@ class LGBMForecaster(Forecaster, ExplainableForecaster, ContributionsMixin):
         alias="seed",
         description="Random seed for reproducibility.",
     )
-    early_stopping_rounds: int | None = Field(
-        default=None,
-        description="Training stops if performance doesn't improve for this many rounds.",
-    )
 
     _lgbm_model: MultiQuantileRegressor = PrivateAttr()
 
@@ -229,7 +231,7 @@ class LGBMForecaster(Forecaster, ExplainableForecaster, ContributionsMixin):
             "colsample_bytree": self.hyperparams.colsample_bytree,
             # General parameters
             "random_state": self.random_state,
-            "early_stopping_rounds": self.early_stopping_rounds,
+            "early_stopping_rounds": self.hyperparams.early_stopping_rounds,
             "verbosity": self.verbosity,
             "n_jobs": self.n_jobs,
         }

{openstef_models-4.1.2 → openstef_models-4.2.2}/src/openstef_models/models/forecasting/lgbmlinear_forecaster.py

@@ -111,6 +111,12 @@ class LGBMLinearHyperParams(HyperParams):
         description="Fraction of features used when constructing each tree. Range: (0,1]",
     )
 
+    # Early Stopping
+    early_stopping_rounds: int | None = Field(
+        default=None,
+        description="Training will stop if performance doesn't improve for this many rounds. Requires validation data.",
+    )
+
     @classmethod
     def forecaster_class(cls) -> "type[LGBMLinearForecaster]":
         """Get forecaster class for these hyperparams.
@@ -185,10 +191,6 @@ class LGBMLinearForecaster(Forecaster, ExplainableForecaster, ContributionsMixin
         alias="seed",
         description="Random seed for reproducibility.",
     )
-    early_stopping_rounds: int | None = Field(
-        default=None,
-        description="Training stops if performance doesn't improve for this many rounds.",
-    )
 
     _lgbmlinear_model: MultiQuantileRegressor = PrivateAttr()
 
@@ -230,7 +232,7 @@ class LGBMLinearForecaster(Forecaster, ExplainableForecaster, ContributionsMixin
             "colsample_bytree": self.hyperparams.colsample_bytree,
             # General parameters
             "random_state": self.random_state,
-            "early_stopping_rounds": self.early_stopping_rounds,
+            "early_stopping_rounds": self.hyperparams.early_stopping_rounds,
             "verbosity": self.verbosity,
             "n_jobs": self.n_jobs,
         }

{openstef_models-4.1.2 → openstef_models-4.2.2}/src/openstef_models/utils/multi_quantile_regressor.py

@@ -84,6 +84,9 @@ class MultiQuantileRegressor(BaseEstimator, RegressorMixin):
         """
         # Pass model-specific eval arguments
         kwargs = {}
+
+        x_array = np.asarray(X)
+
         for model in self._models:
             # Check if early stopping is supported
             # Check that eval_set is supported
@@ -91,21 +94,20 @@ class MultiQuantileRegressor(BaseEstimator, RegressorMixin):
                 model.set_params(early_stopping_rounds=None)
 
             if eval_set is not None and self.learner_eval_sample_weight_param is not None:
+                kwargs["eval_set"] = [
+                    (x_array if eval_x is X else np.asarray(eval_x), eval_y) for eval_x, eval_y in eval_set
+                ]
                 kwargs[self.learner_eval_sample_weight_param] = eval_sample_weight
-
-            if "early_stopping_rounds" in self.hyperparams and self.learner_eval_sample_weight_param is not None:
-                model.set_params(early_stopping_rounds=self.hyperparams["early_stopping_rounds"])
+                if "early_stopping_rounds" in self.hyperparams:
+                    model.set_params(early_stopping_rounds=self.hyperparams["early_stopping_rounds"])
 
             if feature_name:
                 self.model_feature_names = feature_name
             else:
                 self.model_feature_names = []
 
-            if eval_sample_weight is not None and self.learner_eval_sample_weight_param:
-                kwargs[self.learner_eval_sample_weight_param] = eval_sample_weight
-
             model.fit(  # type: ignore
-                X=np.asarray(X),
+                X=x_array,
                 y=y,
                 sample_weight=sample_weight,
                 **kwargs,

{openstef_models-4.1.2 → openstef_models-4.2.2}/tests/unit/utils/test_multi_quantile_regressor.py

@@ -117,3 +117,28 @@ def test_is_fitted_true_after_fit(dataset: tuple[pd.DataFrame, pd.Series], basel
 
     # Assert
     assert model.is_fitted
+
+
+def test_fit_forwards_eval_set_for_early_stopping_lgbm(dataset: tuple[pd.DataFrame, pd.Series]):
+    # Arrange
+    quantiles = [Quantile(0.1), Quantile(0.5), Quantile(0.9)]
+    early_stopping_rounds = 3
+    X, y = dataset
+    y = y.to_numpy()
+    X_train, y_train = X.iloc[:80], y[:80]  # noqa: N806
+    X_val, y_val = X.iloc[80:], y[80:]  # noqa: N806
+    model = MultiQuantileRegressor(
+        base_learner=LGBMRegressor,
+        quantile_param="alpha",
+        quantiles=quantiles,
+        hyperparams={"objective": "quantile", "n_estimators": 10, "early_stopping_rounds": early_stopping_rounds},
+    )
+
+    # Act
+    model.fit(X_train, y_train, eval_set=[(X_train, y_train), (X_val, y_val)])
+
+    # Assert
+    for estimator in model.models:
+        assert isinstance(estimator, LGBMRegressor)
+        assert estimator.get_params()["early_stopping_rounds"] == early_stopping_rounds
+        assert estimator.evals_result_