openstef 3.4.77__tar.gz → 3.4.78__tar.gz

{openstef-3.4.77 → openstef-3.4.78}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.77
+Version: 3.4.78
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.77 → openstef-3.4.78}/openstef/data_classes/prediction_job.py

@@ -140,6 +140,10 @@ class PredictionJobDataClass(BaseModel):
     data_prep_class: Optional[DataPrepDataClass] = Field(
         None, description="The import string for the custom data prep class"
     )
+    model_run_id: Optional[str] = Field(
+        None,
+        description="The specific model run number that should be used for the forecast. If not set, the latest model run will be used.",
+    )
 
     fallback_strategy: Optional[FallbackStrategy] = Field(
         FallbackStrategy.EXTREME_DAY,

{openstef-3.4.77 → openstef-3.4.78}/openstef/model/serializer.py

@@ -18,6 +18,7 @@ from mlflow.store.artifact.artifact_repository_registry import get_artifact_repo
 from xgboost import XGBModel  # Temporary for backward compatibility
 
 from openstef.data_classes.model_specifications import ModelSpecificationDataClass
+from openstef.data_classes.prediction_job import PredictionJobDataClass
 from openstef.logging.logger_factory import get_logger
 from openstef.metrics.reporter import Report
 from openstef.model.regressors.regressor import OpenstfRegressor
@@ -143,20 +144,30 @@ class MLflowSerializer:
     def load_model(
         self,
         experiment_name: str,
+        model_run_id: Optional[str] = None,
     ) -> tuple[OpenstfRegressor, ModelSpecificationDataClass]:
-        """Load sklearn compatible model from MLFlow.
+        """ Load an sklearn-compatible model from MLflow.
 
+        This method retrieves a trained model and its specifications from MLflow 
+        based on the provided PredictionJobDataClass instance. It supports loading 
+        a specific model run if a run number is provided.
+            
         Args:
-            experiment_name: Name of the experiment, often the id of the predition job.
+                experiment_name (str): Name of the experiment, often the id of the predition job.
+                model_run_id (Optional[str]): The specific model run number that should be used for the forecast.
+
+        Returns:
+            tuple[OpenstfRegressor, ModelSpecificationDataClass]: A tuple containing 
+                the loaded model and its specifications.
 
-        Raises:
-            LookupError: If model is not found in MLflow.
+            LookupError: If the model is not found in MLflow or if an error occurs 
+                during the loading process.
 
         """
         try:
             models_df = self._find_models(
-                self.experiment_name_prefix + experiment_name, max_results=1
-            )  # return the latest finished run of the model
+                self.experiment_name_prefix + experiment_name, max_results=1, model_run_id=model_run_id)
+             # return the latest finished run of the model
             if not models_df.empty:
                 latest_run = models_df.iloc[0]  # Use .iloc[0] to only get latest run
             else:
@@ -172,7 +183,7 @@ class MLflowSerializer:
             )  # Path without file:///
             self.logger.info("Model successfully loaded with MLflow")
             return loaded_model, model_specs
-        except (AttributeError, MlflowException, OSError) as exception:
+        except (AttributeError, MlflowException, OSError) as exception:            
             raise LookupError("Model not found. First train a model!") from exception
 
     def get_model_age(
@@ -205,8 +216,13 @@ class MLflowSerializer:
         experiment_name: str,
         max_results: Optional[int] = 100,
         filter_string: str = "attribute.status = 'FINISHED'",
+        model_run_id: Optional[int] = None,
     ) -> pd.DataFrame:
         """Finds trained models for specific experiment_name sorted by age in descending order."""
+
+        if model_run_id is not None:
+            filter_string += f" AND attributes.run_id = '{model_run_id}'"
+
         models_df = mlflow.search_runs(
             experiment_names=[experiment_name],
             max_results=max_results,

{openstef-3.4.77 → openstef-3.4.78}/openstef/pipeline/create_forecast.py

@@ -52,11 +52,10 @@ def create_forecast_pipeline(
     # Use the alternative forecast model if it's specify in the pj
     if pj.alternative_forecast_model_pid:
         prediction_model_pid = pj.alternative_forecast_model_pid
-
     # Load most recent model for the given pid
     model, model_specs = MLflowSerializer(
         mlflow_tracking_uri=mlflow_tracking_uri
-    ).load_model(experiment_name=str(prediction_model_pid))
+    ).load_model(experiment_name=str(prediction_model_pid), model_run_id=pj.get("model_run_id"))
     return create_forecast_pipeline_core(pj, input_data, model, model_specs)
 
 

{openstef-3.4.77 → openstef-3.4.78}/openstef/pipeline/train_model.py

@@ -52,6 +52,7 @@ def train_model_pipeline(
         check_old_model_age: Check if training should be skipped because the model is too young
         mlflow_tracking_uri: Tracking URI for MLFlow
         artifact_folder: Path where artifacts, such as trained models, are stored
+        ignore_existing_models: If True, a new model is trained as if no old model exists.
 
     Returns:
         If pj.save_train_forecasts is False, None is returned
@@ -168,6 +169,7 @@ def train_model_pipeline_core(
         input_data: Input data
         old_model: Old model to compare to. Defaults to None.
         horizons: Horizons to train on in hours, relevant for feature engineering.
+        ignore_existing_models: If True, all existing models, including, hyperparameters are ignored and defsault values are used. 
 
     Raises:
         InputDataInsufficientError: when input data is insufficient.
@@ -319,8 +321,9 @@ def train_pipeline_step_load_model(
     old_model: Optional[OpenstfRegressor]
 
     if not ignore_existing_models:
+        model_run_id = pj.get("model_run_id", None)
         try:
-            old_model, model_specs = serializer.load_model(experiment_name=str(pj.id))
+            old_model, model_specs = serializer.load_model(str(pj.id), model_run_id=model_run_id)
             old_model_age = old_model.age  # Age attribute is openstef specific
             return old_model, model_specs, old_model_age
         except (AttributeError, FileNotFoundError, LookupError):

{openstef-3.4.77 → openstef-3.4.78}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.77
+Version: 3.4.78
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.77 → openstef-3.4.78}/setup.py

@@ -33,7 +33,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.77",
+    version="3.4.78",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),