openstef 3.4.70__tar.gz → 3.4.72__tar.gz

{openstef-3.4.70 → openstef-3.4.72}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.70
+Version: 3.4.72
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -16,7 +16,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: holidays==0.21
 Requires-Dist: joblib==1.3.2
-Requires-Dist: lightgbm~=3.3
+Requires-Dist: lightgbm>=4.0
 Requires-Dist: matplotlib~=3.7
 Requires-Dist: mlflow~=2.3
 Requires-Dist: networkx~=3.1

{openstef-3.4.70 → openstef-3.4.72}/openstef/model/model_creator.py

@@ -73,7 +73,6 @@ valid_model_kwargs = {
         "n_jobs",
         "silent",
         "importance_type",
-        "early_stopping_rounds",
     ],
     ModelType.XGB_QUANTILE: [
         "quantiles",

{openstef-3.4.70 → openstef-3.4.72}/openstef/model/objective.py

@@ -7,6 +7,8 @@ from typing import Any, Callable, Optional
 
 import optuna
 import pandas as pd
+from lightgbm import early_stopping
+from xgboost.callback import EarlyStopping
 
 from openstef.enums import ModelType
 from openstef.metrics import metrics
@@ -130,31 +132,42 @@ class RegressorObjective:
         # Configure evals for early stopping
         eval_set = [(train_x, train_y), (valid_x, valid_y)]
 
-        # get the parameters used in this trial
+        # Get the parameters used in this trial
         hyper_params = self.get_params(trial)
 
-        # insert parameters into model
+        # Insert parameters into model
         self.model.set_params(**hyper_params)
 
-        # create the specific pruning callback
+        callbacks = []
+
+        # Create the early stopping callback
+        early_stopping_callback = self.get_early_stopping_callback()
+        if early_stopping_callback is not None:
+            callbacks.append(early_stopping_callback)
+
+        # Create the specific pruning callback
         pruning_callback = self.get_pruning_callback(trial)
-        if pruning_callback is None:
-            callbacks = None
-        else:
-            callbacks = [pruning_callback]
+        if pruning_callback is not None:
+            callbacks.append(pruning_callback)
+
+        # Pass verbose argument to fit call if model is not LGB
+        fit_kwargs = {}
+        if self.model_type not in [ModelType.XGB, ModelType.LGB]:
+            fit_kwargs["early_stopping_rounds"] = EARLY_STOPPING_ROUNDS
+        elif self.model_type != ModelType.LGB:
+            fit_kwargs["verbose"] = self.verbose
 
         # validation_0 and validation_1 are available
         self.model.fit(
             train_x,
             train_y,
             eval_set=eval_set,
-            early_stopping_rounds=EARLY_STOPPING_ROUNDS,
-            verbose=self.verbose,
             eval_metric=self.eval_metric,
             callbacks=callbacks,
+            **fit_kwargs,
         )
 
-        self.model.feature_importance_dataframe = self.model.set_feature_importance()
+        self.model.feature_importance_dataframe = self.model.get_feature_importance()
 
         # Do confidence interval determination
         self.model = StandardDeviationGenerator(
@@ -203,6 +216,9 @@ class RegressorObjective:
     def get_pruning_callback(self, trial: optuna.trial.FrozenTrial):
         return None
 
+    def get_early_stopping_callback(self):
+        return None
+
     def get_trial_track(self) -> dict:
         """Get a dictionary of al trials.
 
@@ -272,6 +288,15 @@ class XGBRegressorObjective(RegressorObjective):
             trial, observation_key=f"validation_1-{self.eval_metric}"
         )
 
+    def get_early_stopping_callback(self):
+        return EarlyStopping(
+            rounds=EARLY_STOPPING_ROUNDS,
+            metric_name=self.eval_metric,
+            data_name=f"validation_1",
+            maximize=False,
+            save_best=True,
+        )
+
     @classmethod
     def get_default_values(cls) -> dict:
         default_parameter_values = super().get_default_values()
@@ -319,6 +344,11 @@ class LGBRegressorObjective(RegressorObjective):
             trial, metric=metric, valid_name="valid_1"
         )
 
+    def get_early_stopping_callback(self):
+        return early_stopping(
+            stopping_rounds=EARLY_STOPPING_ROUNDS, verbose=self.verbose
+        )
+
 
 class XGBQuantileRegressorObjective(RegressorObjective):
     def __init__(self, *args, **kwargs):

{openstef-3.4.70 → openstef-3.4.72}/openstef/model/regressors/arima.py

@@ -126,7 +126,7 @@ class ARIMAOpenstfRegressor(OpenstfRegressor):
             predictions = self.predict_quantile(start, end, exog=x, quantile=quantile)
         return predictions
 
-    def set_feature_importance(self):
+    def get_feature_importance(self):
         """Because report needs 'weight' and 'gain' as importance metrics, we set the values to these names.
 
         - 'weight' is corresponding to the coefficients values

{openstef-3.4.70 → openstef-3.4.72}/openstef/model/regressors/regressor.py

@@ -59,7 +59,7 @@ class OpenstfRegressor(BaseEstimator):
         """
 
     @abstractmethod
-    def fit(self, x: np.array, y: np.array, **kwargs) -> RegressorMixin:
+    def fit(self, x: pd.DataFrame, y: pd.DataFrame, **kwargs) -> RegressorMixin:
         """Fits the regressor.
 
         Args:
@@ -72,7 +72,7 @@ class OpenstfRegressor(BaseEstimator):
 
         """
 
-    def set_feature_importance(self) -> Union[pd.DataFrame, None]:
+    def get_feature_importance(self) -> Union[pd.DataFrame, None]:
         """Get feature importance.
 
         Returns:

{openstef-3.4.70 → openstef-3.4.72}/openstef/model/regressors/xgb.py

@@ -36,13 +36,10 @@ class XGBOpenstfRegressor(XGBRegressor, OpenstfRegressor):
         x: np.array,
         y: np.array,
         *,
-        early_stopping_rounds: Optional[int] = None,
         callbacks: Optional[list] = None,
         eval_metric: Optional[str] = None,
         **kwargs
     ):
-        if early_stopping_rounds is not None:
-            self.set_params(early_stopping_rounds=early_stopping_rounds)
         if callbacks is not None:
             self.set_params(callbacks=callbacks)
         if eval_metric is not None:

{openstef-3.4.70 → openstef-3.4.72}/openstef/pipeline/train_model.py

@@ -495,10 +495,9 @@ def train_pipeline_step_train_model(
         train_x,
         train_y,
         eval_set=eval_set,
-        verbose=False,
     )
     # Gets the feature importance df or None if we don't have feature importance
-    model.feature_importance_dataframe = model.set_feature_importance()
+    model.feature_importance_dataframe = model.get_feature_importance()
 
     logger.info("Fitted a new model, not yet stored")
 

{openstef-3.4.70 → openstef-3.4.72}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.70
+Version: 3.4.72
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -16,7 +16,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: holidays==0.21
 Requires-Dist: joblib==1.3.2
-Requires-Dist: lightgbm~=3.3
+Requires-Dist: lightgbm>=4.0
 Requires-Dist: matplotlib~=3.7
 Requires-Dist: mlflow~=2.3
 Requires-Dist: networkx~=3.1

{openstef-3.4.70 → openstef-3.4.72}/openstef.egg-info/requires.txt

@@ -1,6 +1,6 @@
 holidays==0.21
 joblib==1.3.2
-lightgbm~=3.3
+lightgbm>=4.0
 matplotlib~=3.7
 mlflow~=2.3
 networkx~=3.1

{openstef-3.4.70 → openstef-3.4.72}/setup.py

@@ -33,7 +33,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.70",
+    version="3.4.72",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),