openstef 3.4.76__py3-none-any.whl → 3.4.78__py3-none-any.whl

openstef/data_classes/prediction_job.py

@@ -10,7 +10,12 @@ from pydantic import BaseModel, Field
 from openstef.data_classes.data_prep import DataPrepDataClass
 from openstef.data_classes.model_specifications import ModelSpecificationDataClass
 from openstef.data_classes.split_function import SplitFuncDataClass
-from openstef.enums import AggregateFunction, BiddingZone, PipelineType
+from openstef.enums import (
+    AggregateFunction,
+    BiddingZone,
+    PipelineType,
+    FallbackStrategy,
+)
 
 
 class PredictionJobDataClass(BaseModel):
@@ -135,6 +140,15 @@ 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,
+        description="The fallback strategy to use when not enough input data is available.",
+    )
 
     def __getitem__(self, item: str) -> Any:
         """Allows us to use subscription to get the items from the object."""

openstef/enums.py

@@ -139,3 +139,8 @@ class PipelineType(Enum):
     FORECAST = "forecast"
     TRAIN = "train"
     HYPER_PARMATERS = "hyper_parameters"
+
+
+class FallbackStrategy(Enum):
+    EXTREME_DAY = "extreme_day"
+    RAISE_ERROR = "raise_error"

openstef/model/fallback.py

@@ -5,11 +5,13 @@ from datetime import UTC, datetime
 
 import pandas as pd
 
+from openstef.enums import FallbackStrategy
+
 
 def generate_fallback(
     forecast_input: pd.DataFrame,
     load: pd.DataFrame,
-    fallback_strategy: str = "extreme_day",
+    fallback_strategy: FallbackStrategy = FallbackStrategy.EXTREME_DAY,
 ) -> pd.DataFrame:
     """Make a fall back forecast, Set the value of the forecast 'quality' column to 'substituted'.
 
@@ -20,6 +22,7 @@ def generate_fallback(
         load: index=datetime, columns=['load']
         fallback_strategy: strategy to determine fallback. options:
             - extreme_day: use daily profile of most extreme day
+            - raise_error: raise error if not enough data is available
     Returns:
         Fallback forecast DataFrame with columns; 'forecast', 'quality'
 
@@ -32,12 +35,17 @@ def generate_fallback(
     if len(load.dropna()) == 0:
         raise ValueError("No historic load data available")
 
-    if fallback_strategy != "extreme_day":
-        raise NotImplementedError(
-            f'fallback_strategy should be "extreme_day", received:{fallback_strategy}'
-        )
+    if fallback_strategy not in [
+        FallbackStrategy.RAISE_ERROR,
+        FallbackStrategy.EXTREME_DAY,
+    ]:
+        raise NotImplementedError("Fallback strategy not implemented")
+
+    if fallback_strategy == FallbackStrategy.RAISE_ERROR:
+        # Raise error if not enough data is available
+        raise ValueError("Not enough load data available to generate forecast")
 
-    if fallback_strategy == "extreme_day":
+    if fallback_strategy == FallbackStrategy.EXTREME_DAY:
         # Execute this fallback strategy
         # Find most extreme historic day and merge it by time-of-day to the requested moments
 

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/pipeline/create_forecast.py

@@ -20,6 +20,7 @@ from openstef.postprocessing.postprocessing import (
     sort_quantiles,
 )
 from openstef.validation import validation
+from openstef.enums import FallbackStrategy
 
 
 def create_forecast_pipeline(
@@ -51,11 +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)
 
 
@@ -88,7 +88,7 @@ def create_forecast_pipeline_core(
     """
     logger = get_logger(__name__)
 
-    fallback_strategy = "extreme_day"  # this can later be expanded
+    fallback_strategy = pj.get("fallback_strategy", FallbackStrategy.EXTREME_DAY)
 
     # Validate and clean data
     validated_data = validation.validate(

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-3.4.76.dist-info → openstef-3.4.78.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.76
+Version: 3.4.78
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.76.dist-info → openstef-3.4.78.dist-info}/RECORD

@@ -1,7 +1,7 @@
 openstef/__init__.py,sha256=93UM6m0LLQhO69-mSqLuUy73jgs4W7Iuxfo3Lm8c98g,419
 openstef/__main__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/app_settings.py,sha256=4SiEoPfPmM_Vc9gwWleT_IRxHIk36bZaYRCdNf3ewoo,762
-openstef/enums.py,sha256=kwAbEoMI_a--Ikk6RxeJmvR2JKYKDNHynhMUbbiczZs,2851
+openstef/enums.py,sha256=_nhwTY5-bV14ydv4nA06KEZ1xsI53oNqMX963P10jgg,2947
 openstef/exceptions.py,sha256=dgnvZe5WWuJWCZm_GES6suEATbusPlwbiEUfNQKeExY,1993
 openstef/settings.py,sha256=nSgkBqFxuqB3w7Rwo60i8j37c5ngDbt6vpjHS6QtJXQ,354
 openstef/data/NL_terrestrial_radiation.csv,sha256=A4kbW56GDzWi4tWUwY2C-4PiOvcKJCwkWQQtdg4ekPE,820246
@@ -17,7 +17,7 @@ openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_model_card.md.license,sha25
 openstef/data_classes/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/data_classes/data_prep.py,sha256=sANgFjfwmSWhLCfmLjfqXQnczuvVZfk2765jZd7LwuE,3691
 openstef/data_classes/model_specifications.py,sha256=PZeBLfH_MrP9-QorL1r0Hklp0befE8Nw05vNhTX9Y20,1338
-openstef/data_classes/prediction_job.py,sha256=omVzowGYUp5YD_7k3i3pKlDh1I7i_jU3-za7FJ3fK1s,6731
+openstef/data_classes/prediction_job.py,sha256=794joix2ynvCYvm-MbiA5eagT46CArr_n_K5UrVoFBs,7166
 openstef/data_classes/split_function.py,sha256=K8y1dsQC5exeIDh37f7UwJ11tV71_uVSNbnKmwXpnOM,3435
 openstef/feature_engineering/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/feature_engineering/apply_features.py,sha256=pro4eUmOFexX_9g9kJtDcbrQ1hWKzXjVpiJBmmBi89o,5326
@@ -45,11 +45,11 @@ openstef/metrics/reporter.py,sha256=2F1uRmh2MC-JH8Lsr1xGLxUFYDGfQ0Q85Pcjcc31TP0,
 openstef/model/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/model/basecase.py,sha256=caI6Q-8y0ymlxGK9Js_H3Vh0q6ruNHlGD5RG0_kE5M0,2878
 openstef/model/confidence_interval_applicator.py,sha256=VOdHsDJhfeyaq_cnk9QMUaZ2IumbiBBoW1zo8AuqDg0,9559
-openstef/model/fallback.py,sha256=g6TEuEhV4w07SCGkR_AvPf2up9f0ixGKQojYC-Ewl6Y,2812
+openstef/model/fallback.py,sha256=x60GVyl1c5DpebzkjJEMToZpMTD1c4FrhM-tBN9uizk,3177
 openstef/model/model_creator.py,sha256=fnhcVGUHskbuAys5kjlJ4GXKxbi9Eq5eAA19ex11Vv0,6658
 openstef/model/objective.py,sha256=0PZUbPzuyaYlpWEH_qPavO6ll7zwqTTUTfIrUzzFMbs,15585
 openstef/model/objective_creator.py,sha256=3jJgcmY1sm-Yoe3SfjKrJukrsqtYyloUFaPbBWqswhQ,2208
-openstef/model/serializer.py,sha256=k5GY8eRJdlii8mEY7Qheu4yb5USyIyxw77EYkSQJGYk,17034
+openstef/model/serializer.py,sha256=8vESYq2TmtEzEViBR7qbJ3rjm68LZkbiET2cUPGvFMs,17925
 openstef/model/standard_deviation_generator.py,sha256=OorRvX2wRScU7f4SIBoiT24yJeeM50sETP3xC6m5IG4,2865
 openstef/model/metamodels/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/model/metamodels/feature_clipper.py,sha256=DNsyYdjUT7ZNimJJIyTvv1nmwTwDUk5fX9EDgV9FbUQ,2862
@@ -77,10 +77,10 @@ openstef/monitoring/teams.py,sha256=klN7Ge-0VktJbZ_I-K8MJIc3LWgdNy0MGL8b2TdoUR8,
 openstef/pipeline/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/pipeline/create_basecase_forecast.py,sha256=7IShIjEmjkzpNzWzQVKmYQvy0q_uwCGO-E0mSRmGdhw,4397
 openstef/pipeline/create_component_forecast.py,sha256=40fYKajdj4F9K7fzmL3euyvwTr0v-oO_5cXpya87A0c,5839
-openstef/pipeline/create_forecast.py,sha256=mVbbu7jM31NEwfaDeQPqF3Okps9H1oLfjhPPiJRL4zg,5582
+openstef/pipeline/create_forecast.py,sha256=z18MrnMW6f85mLjH9XKLniuCQ9oziWCqfgA5YdEgROM,5676
 openstef/pipeline/optimize_hyperparameters.py,sha256=w5LpZhW3KVklCJzaogNzyHfpMJfNqeRAnvyV4vi35wg,10953
 openstef/pipeline/train_create_forecast_backtest.py,sha256=hBJPxfDkbrmFSSGZrRH1vTiIVqJP-SWe0ibVpHT_8Qg,6048
-openstef/pipeline/train_model.py,sha256=O1pyATMQUkNZQ01FlOwG8r3gtKwRcx7YD73f-91umuo,19948
+openstef/pipeline/train_model.py,sha256=4mtNXosLxxLNDtyIBd58youAHx5zWIW7PoSeZdtDoXY,20234
 openstef/pipeline/utils.py,sha256=23mB31p19FoGWelLJzxNmqlzGwEr3fCDBEA37V2kpYY,2167
 openstef/plotting/__init__.py,sha256=KQjXzyafCt1bE7XDrSeV4TDUIO7MkwN_Br4ASOcNI2g,163
 openstef/plotting/load_forecast_plotter.py,sha256=GWHVmUB2YosNj7TnSrMnxYAfM2Z1mNg5oRV9A_lJmQY,8129
@@ -104,8 +104,8 @@ openstef/tasks/utils/predictionjobloop.py,sha256=Ysy3zF5lzPMz_asYDKeF5m0qgVT3tCt
 openstef/tasks/utils/taskcontext.py,sha256=O-LZ_wHEl5vbT8oB7EYtOeMkvk6EqCnI1-KiyER7Eu4,5407
 openstef/validation/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/validation/validation.py,sha256=r6UqkdH5TMjsGfn8Ta07K1jkqmrVmwcPGfyQvMmZyO4,11459
-openstef-3.4.76.dist-info/licenses/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
-openstef-3.4.76.dist-info/METADATA,sha256=OEFP-Jw1hquEQh71h5_uLi89nRCQKoHYOfJvJMWjFDo,8834
-openstef-3.4.76.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
-openstef-3.4.76.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
-openstef-3.4.76.dist-info/RECORD,,
+openstef-3.4.78.dist-info/licenses/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
+openstef-3.4.78.dist-info/METADATA,sha256=81sI3OOBkDqIOnQOVq9HCvFzCGnTEpAhg70_4j_2DxM,8834
+openstef-3.4.78.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+openstef-3.4.78.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
+openstef-3.4.78.dist-info/RECORD,,

{openstef-3.4.76.dist-info → openstef-3.4.78.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.4.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any