openstef 3.4.31__tar.gz → 3.4.33__tar.gz

{openstef-3.4.31 → openstef-3.4.33}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.31
+Version: 3.4.33
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

openstef-3.4.33/openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_model_card.md

@@ -0,0 +1,18 @@
+
+ # Model details : dazls\_model\_baseline\_model
+ 
+ ## Description
+ **Model Name**: dazls\_model\_baseline\_model   
+
+**Author**: KTP, Alliander   
+
+**Model type**: Energy splitting model   
+
+**Model Architecture**: LinearRegression   
+
+**Date**: 2024-04-26 
+ 
+ ## Intended use
+ This is a DAZLs model aimed at determining the energy splits for substations. 
+ Each of these splits are determined based on a set of features that are available in production,
+ and in this case have their origin in the Dutch energy grid.******************** 

openstef-3.4.33/openstef/data/dutch_holidays_2020-2022.csv.license

@@ -0,0 +1,3 @@
+SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com>
+
+SPDX-License-Identifier: MPL-2.0

openstef-3.4.33/openstef/data/pv_single_coefs.csv.license

@@ -0,0 +1,3 @@
+SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com>
+
+SPDX-License-Identifier: MPL-2.0

{openstef-3.4.31 → openstef-3.4.33}/openstef/feature_engineering/missing_values_transformer.py

@@ -7,7 +7,7 @@ import numpy as np
 import pandas as pd
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import FunctionTransformer
-from sklearn.utils.validation import check_array
+from sklearn.utils.validation import check_array, check_is_fitted
 
 
 class MissingValuesTransformer:
@@ -42,6 +42,20 @@ class MissingValuesTransformer:
         self.missing_values = missing_values
         self.imputation_strategy = imputation_strategy
         self.fill_value = fill_value
+        self.is_fitted_ = False
+
+        # Build the proper imputation transformer
+        # - Identity function if strategy is None
+        # - SimpleImputer with the dedicated strategy
+        if self.imputation_strategy is None:
+            self.imputer_ = FunctionTransformer(func=self._identity)
+        else:
+            self.imputer_ = SimpleImputer(
+                missing_values=self.missing_values,
+                strategy=self.imputation_strategy,
+                fill_value=self.fill_value,
+            ).set_output(transform="pandas")
+            self.imputer_._validate_params()
 
     def fit(self, x, y=None):
         """Fit the imputer on the input data."""
@@ -56,23 +70,13 @@ class MissingValuesTransformer:
         is_column_null = x.isnull().all(axis="index")
         self.non_null_feature_names = list(x.columns[~is_column_null])
 
-        # Build the proper imputation transformer
-        # - Identity function if strategy is None
-        # - SimpleImputer with the dedicated strategy
-        if self.imputation_strategy is None:
-            self.imputer_ = FunctionTransformer(func=self._identity)
-        else:
-            self.imputer_ = SimpleImputer(
-                missing_values=self.missing_values,
-                strategy=self.imputation_strategy,
-                fill_value=self.fill_value,
-            ).set_output(transform="pandas")
-
         # Imputers do not support labels
-        self.imputer_.fit(X=x, y=None)
+        self.imputer_.fit(X=x[self.non_null_feature_names], y=None)
+        self.is_fitted_ = True
 
     def transform(self, x) -> pd.DataFrame:
         """Transform the input data by imputing missing values."""
+        check_is_fitted(self)
         _ = check_array(x, force_all_finite="allow-nan")
         if not isinstance(x, pd.DataFrame):
             x = pd.DataFrame(np.asarray(x))

{openstef-3.4.31 → openstef-3.4.33}/openstef/model/regressors/linear_quantile.py

@@ -231,7 +231,7 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
         return np.array(
             [
                 reg_feature_importances_dict.get(c, 0)
-                for c in self.imputer_.in_feature_names
+                for c in self.imputer_.non_null_feature_names
             ]
         )
 

{openstef-3.4.31 → openstef-3.4.33}/openstef/model/regressors/xgb.py

@@ -1,6 +1,10 @@
 # SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
 #
 # SPDX-License-Identifier: MPL-2.0
+from typing import Optional
+
+import numpy as np
+from sklearn.base import RegressorMixin
 
 from xgboost import XGBRegressor
 
@@ -27,3 +31,22 @@ class XGBOpenstfRegressor(XGBRegressor, OpenstfRegressor):
             "gain_importance_name": "total_gain",
             "weight_importance_name": "weight",
         }
+
+    def fit(
+        self,
+        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:
+            self.set_params(eval_metric=eval_metric)
+
+        super().fit(x, y, **kwargs)

{openstef-3.4.31 → openstef-3.4.33}/openstef/tasks/create_basecase_forecast.py

@@ -97,7 +97,7 @@ def create_basecase_forecast_task(
     context.database.write_forecast(basecase_forecast, t_ahead_series=True)
 
 
-def main(config: object = None, database: object = None):
+def main(config: object = None, database: object = None, **kwargs):
     taskname = Path(__file__).name.replace(".py", "")
 
     if database is None or config is None:
@@ -110,7 +110,7 @@ def main(config: object = None, database: object = None):
         model_type = ["xgb", "xgb_quantile", "lgb"]
 
         PredictionJobLoop(context, model_type=model_type).map(
-            create_basecase_forecast_task, context
+            create_basecase_forecast_task, context, **kwargs
         )
 
 

{openstef-3.4.31 → openstef-3.4.33}/openstef/tasks/create_components_forecast.py

@@ -140,7 +140,7 @@ def create_components_forecast_task(
         )
 
 
-def main(config: object = None, database: object = None):
+def main(config: object = None, database: object = None, **kwargs):
     taskname = Path(__file__).name.replace(".py", "")
 
     if database is None or config is None:
@@ -155,7 +155,7 @@ def main(config: object = None, database: object = None):
         PredictionJobLoop(
             context,
             model_type=model_type,
-        ).map(create_components_forecast_task, context)
+        ).map(create_components_forecast_task, context, **kwargs)
 
 
 if __name__ == "__main__":

{openstef-3.4.31 → openstef-3.4.33}/openstef/tasks/create_forecast.py

@@ -118,7 +118,7 @@ def create_forecast_task(
     context.database.write_forecast(forecast, t_ahead_series=True)
 
 
-def main(model_type=None, config=None, database=None):
+def main(model_type=None, config=None, database=None, **kwargs):
     taskname = Path(__file__).name.replace(".py", "")
 
     if database is None or config is None:
@@ -132,7 +132,7 @@ def main(model_type=None, config=None, database=None):
             model_type = [ml.value for ml in MLModelType]
 
         PredictionJobLoop(context, model_type=model_type).map(
-            create_forecast_task, context
+            create_forecast_task, context, **kwargs
         )
 
 

{openstef-3.4.31 → openstef-3.4.33}/openstef/tasks/create_solar_forecast.py

@@ -216,7 +216,7 @@ def fides(data: pd.DataFrame, all_forecasts: bool = False):
     return forecast
 
 
-def main(config=None, database=None):
+def main(config=None, database=None, **kwargs):
     taskname = Path(__file__).name.replace(".py", "")
 
     if database is None or config is None:
@@ -245,7 +245,7 @@ def main(config=None, database=None):
             )
 
         PredictionJobLoop(context, prediction_jobs=prediction_jobs).map(
-            make_solar_prediction_pj, context
+            make_solar_prediction_pj, context, kwargs=kwargs
         )
 
 

{openstef-3.4.31 → openstef-3.4.33}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.31
+Version: 3.4.33
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.31 → openstef-3.4.33}/openstef.egg-info/SOURCES.txt

@@ -18,6 +18,10 @@ openstef/data/dutch_holidays_2020-2022.csv
 openstef/data/dutch_holidays_2020-2022.csv.license
 openstef/data/pv_single_coefs.csv
 openstef/data/pv_single_coefs.csv.license
+openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_baseline_model.z
+openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_baseline_model.z.license
+openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_model_card.md
+openstef/data/dazls_model_3.4.24/dazls_stored_3.4.24_model_card.md.license
 openstef/data_classes/__init__.py
 openstef/data_classes/data_prep.py
 openstef/data_classes/model_specifications.py

{openstef-3.4.31 → openstef-3.4.33}/setup.py

@@ -29,7 +29,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.31",
+    version="3.4.33",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),
@@ -43,7 +43,7 @@ setup(
     # for more information
     package_data={
         # Include anything in the data directory
-        "openstef": ["data/*", "data/dazls_model_3.4.7/*", "*.license"]
+        "openstef": ["data/*", "data/**/*", "*.license"]
     },
     python_requires=">=3.9.0",
     install_requires=read_requirements_from_file(),