openstef 3.4.46__py3-none-any.whl → 3.4.49__py3-none-any.whl

openstef/feature_engineering/apply_features.py

@@ -40,13 +40,14 @@ def apply_features(
     pj: PredictionJobDataClass = None,
     feature_names: list[str] = None,
     horizon: float = 24.0,
+    years: list[int] | None = None,
 ) -> pd.DataFrame:
     """Applies the feature functions defined in ``feature_functions.py`` and returns the complete dataframe.
 
     Features requiring more recent label-data are omitted.
 
     .. note::
-        For the time deriven features only the onces in the features list will be added. But for the weather features all will be added at present.
+        For the time derived features only the ones in the features list will be added. But for the weather features all will be added at present.
         These unrequested additional features have to be filtered out later.
 
     Args:
@@ -56,8 +57,9 @@ def apply_features(
                                         columns=[label, predictor_1,..., predictor_n]
                                     )
         pj (PredictionJobDataClass): Prediction job.
-        feature_names (list[str]): list of reuqested features
+        feature_names (list[str]): list of requested features
         horizon (float): Forecast horizon limit in hours.
+        years (list[int] | None): years for which to create holiday features.
 
     Returns:
         pd.DataFrame(index = datetime, columns = [label, predictor_1,..., predictor_n, feature_1, ..., feature_m])
@@ -100,7 +102,7 @@ def apply_features(
 
     # Get holiday feature functions
     feature_functions.update(
-        generate_holiday_feature_functions(country_code=country_code)
+        generate_holiday_feature_functions(country_code=country_code, years=years)
     )
 
     # Add the features to the dataframe using previously defined feature functions

openstef/feature_engineering/holiday_features.py

@@ -15,7 +15,7 @@ HOLIDAY_CSV_PATH: str = PROJECT_ROOT / "openstef" / "data" / "dutch_holidays.csv
 
 def generate_holiday_feature_functions(
     country_code: str = "NL",
-    years: list = None,
+    years: list[int] | None = None,
     path_to_school_holidays_csv: str = HOLIDAY_CSV_PATH,
 ) -> dict:
     """Generates functions for creating holiday feature.
@@ -48,9 +48,11 @@ def generate_holiday_feature_functions(
     The 'Brugdagen' are updated untill dec 2020. (Generated using agenda)
 
     Args:
-        country: Country for which to create holiday features.
-        years: years for which to create holiday features.
+        country_code: Country for which to create holiday features.
+        years: years for which to create holiday features. If None,
+            the last 4 years, the current and next year are used.
         path_to_school_holidays_csv: Filepath to csv with school holidays.
+
         NOTE: Dutch holidays csv file is only until January 2026.
 
     Returns:

openstef/model/metamodels/feature_clipper.py

@@ -0,0 +1,90 @@
+# SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com> # noqa E501>
+#
+# SPDX-License-Identifier: MPL-2.0
+from sklearn.base import BaseEstimator, TransformerMixin
+import pandas as pd
+from typing import List, Dict, Tuple, Optional
+
+
+class FeatureClipper(BaseEstimator, TransformerMixin):
+    """
+    A transformer that clips the values of specified columns to the minimum and
+    maximum values observed during training. This prevents the model from
+    extrapolating beyond these values during prediction.
+    """
+
+    def __init__(self, columns: List[str]):
+        """
+        Initialize the FeatureClipper.
+
+        Parameters:
+        ----------
+        columns : List[str]
+            List of column names to be clipped.
+        """
+        self.columns: List[str] = columns
+        self.feature_ranges: Dict[str, Tuple[float, float]] = {}
+
+    def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> "FeatureClipper":
+        """
+        Fits the transformer on the training data by calculating the min and max
+        values for the specified columns.
+
+        Parameters:
+        ----------
+        X : pd.DataFrame
+            The input DataFrame containing training data.
+
+        y : Optional[pd.Series]
+            Ignored. This parameter exists for compatibility with scikit-learn's pipeline.
+
+        Returns:
+        -------
+        self : FeatureClipper
+            Fitted transformer.
+
+        Raises:
+        ------
+        ValueError:
+            If the input is not a pandas DataFrame.
+        """
+        if not isinstance(X, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+
+        for col in self.columns:
+            if col in X.columns:
+                self.feature_ranges[col] = (X[col].min(), X[col].max())
+
+        return self
+
+    def transform(self, X: pd.DataFrame) -> pd.DataFrame:
+        """
+        Transforms new data by clipping the specified columns' values to be within
+        the min and max range observed during fitting.
+
+        Parameters:
+        ----------
+        X : pd.DataFrame
+            The input DataFrame containing new data to be transformed.
+
+        Returns:
+        -------
+        X_ : pd.DataFrame
+            A copy of the input DataFrame with clipped values in the specified columns.
+
+        Raises:
+        ------
+        ValueError:
+            If the input is not a pandas DataFrame.
+        """
+        if not isinstance(X, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+
+        X_copy = X.copy()
+
+        for col in self.columns:
+            if col in X_copy.columns and col in self.feature_ranges:
+                min_val, max_val = self.feature_ranges[col]
+                X_copy[col] = X_copy[col].clip(lower=min_val, upper=max_val)
+
+        return X_copy

openstef/model/regressors/linear_quantile.py

@@ -14,6 +14,7 @@ from sklearn.utils.validation import check_is_fitted
 from openstef.feature_engineering.missing_values_transformer import (
     MissingValuesTransformer,
 )
+from openstef.model.metamodels.feature_clipper import FeatureClipper
 from openstef.model.regressors.regressor import OpenstfRegressor
 
 DEFAULT_QUANTILES: tuple[float, ...] = (0.9, 0.5, 0.1)
@@ -28,6 +29,7 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
     x_scaler_: StandardScaler
     y_scaler_: StandardScaler
     models_: Dict[float, QuantileRegressor]
+    feature_clipper_: FeatureClipper
 
     is_fitted_: bool = False
 
@@ -51,6 +53,7 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
         weight_exponent: float = 1,
         weight_floor: float = 0.1,
         no_fill_future_values_features: List[str] = None,
+        clipped_features: List[str] = None,
     ):
         """Initialize LinearQuantileOpenstfRegressor.
 
@@ -89,6 +92,9 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
                 "Cannot train quantile model as 0.5 is not in requested quantiles!"
             )
 
+        if clipped_features is None:
+            clipped_features = ["APX"]
+
         self.quantiles = quantiles
         self.alpha = alpha
         self.solver = solver
@@ -103,6 +109,7 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
         )
         self.x_scaler_ = StandardScaler()
         self.y_scaler_ = StandardScaler()
+        self.feature_clipper_ = FeatureClipper(columns=clipped_features)
         self.models_ = {
             quantile: QuantileRegressor(alpha=alpha, quantile=quantile, solver=solver)
             for quantile in quantiles
@@ -177,6 +184,7 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
             y = pd.Series(np.asarray(y), name="load")
 
         x = self._remove_ignored_features(x)
+        self.feature_clipper_.fit(x)
 
         # Fix nan columns
         x, y = self.imputer_.fit_transform(x, y)
@@ -252,6 +260,7 @@ class LinearQuantileOpenstfRegressor(OpenstfRegressor, RegressorMixin):
 
         # Preprocess input data
         x = self._remove_ignored_features(x)
+        x = self.feature_clipper_.transform(x)
         x = self.imputer_.transform(x)
         x_scaled = self.x_scaler_.transform(x)
 

{openstef-3.4.46.dist-info → openstef-3.4.49.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: openstef
-Version: 3.4.46
+Version: 3.4.49
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -29,11 +29,22 @@ Requires-Dist: pvlib==0.10.5
 Requires-Dist: pydantic~=2.4
 Requires-Dist: pydantic-settings~=2.3
 Requires-Dist: pymsteams~=0.2.2
-Requires-Dist: scikit-learn~=1.3
+Requires-Dist: scikit-learn<1.6,>=1.3
 Requires-Dist: scipy~=1.10
 Requires-Dist: statsmodels<1.0.0,>=0.13.5
 Requires-Dist: structlog<25,>=23.1
 Requires-Dist: xgboost~=2.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 <!--
 SPDX-FileCopyrightText: 2017-2023 Contributors to the OpenSTEF project <korte.termijn.prognoses@alliander.com>

{openstef-3.4.46.dist-info → openstef-3.4.49.dist-info}/RECORD

@@ -20,14 +20,14 @@ openstef/data_classes/model_specifications.py,sha256=Uod1W3QzhRqVLb6zvXwxh9wRL3E
 openstef/data_classes/prediction_job.py,sha256=_o5_9HYv6ERTIWlcMpUE-mWwe7dRpaiP83dgNpqpa5Y,5657
 openstef/data_classes/split_function.py,sha256=ljQIQQu1t1Y_CVWGAy25jrM6wG9odIVVQVimrT1n-1s,3358
 openstef/feature_engineering/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
-openstef/feature_engineering/apply_features.py,sha256=S9HSsooDPcSSyEw9kixEhjjk3MAkAfyK1VhZKg5R0gA,4995
+openstef/feature_engineering/apply_features.py,sha256=EIxP9fvmnAjFRehQpVGBhZHt35GACL-HhDm65_ktHc0,5121
 openstef/feature_engineering/bidding_zone_to_country_mapping.py,sha256=u9aabjFDImydkO6_cXiaQxBT4gb5zy0gGTg2EoIUO_Y,2106
 openstef/feature_engineering/cyclic_features.py,sha256=0Z3wZeF_qrkmEcOq91gtdSMZucAq99kUoBuFDV0SHqk,5962
 openstef/feature_engineering/data_preparation.py,sha256=htca9LBO3ZN1D-iX4vXf0UN1fw_rRO7y6N3AuYVMpfk,5628
 openstef/feature_engineering/feature_adder.py,sha256=aSqDl_gUrB3H2TD3cNvU5JniY_KOb4u4a2A6J7zB2BQ,6835
 openstef/feature_engineering/feature_applicator.py,sha256=DR7jayrEMlra4BFL1Ps5WV2fxbkQ6VaOTa5RIKM-YNk,7447
 openstef/feature_engineering/general.py,sha256=tgU4_1stag9jJmaQAfWCMhfBscznVuQvW5hPK_z9_9g,4438
-openstef/feature_engineering/holiday_features.py,sha256=q_wJvKaVUd54GjPo3qEt1No_XsQ9d1oNmNNJD3AIHtE,8181
+openstef/feature_engineering/holiday_features.py,sha256=CbolIP5bfiQkqDct-9TbD828-lhC48bfeNQ2-VFnsJA,8274
 openstef/feature_engineering/lag_features.py,sha256=Dr6qS8UhdgEHPZZSe-w6ibtjl_lcbcQohhqdZN9fqEU,5652
 openstef/feature_engineering/missing_values_transformer.py,sha256=o_zCVEOCPn2tWzvlY44XZuDysV0TuxqeVYhilYU54YY,5010
 openstef/feature_engineering/weather_features.py,sha256=Lr9DItyHvJ2CpWQ1r6A83tJKtR2k_Wwn32FdFTGblO0,15750
@@ -45,6 +45,7 @@ openstef/model/objective_creator.py,sha256=cIO-uiCEYHjqYrgZizeFEjjgLHLLwab8le9O8
 openstef/model/serializer.py,sha256=IUiiAWvoGVoWzmS-akI6LC7jHRY5Ln_vOCBZy1LnESY,17238
 openstef/model/standard_deviation_generator.py,sha256=Od9bzXi2TLb1v8Nz-VhBMZHSopWH6ssaDe8gYLlqO1I,2911
 openstef/model/metamodels/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
+openstef/model/metamodels/feature_clipper.py,sha256=wDsf4k_2YuC6rrFlwE12LpgOdOwHHWuET2ZrJ_gr4yo,2861
 openstef/model/metamodels/grouped_regressor.py,sha256=yMN_a6TnQSyFaqlB_6Nifq-ydpb5hs6w_b97IaBbHj4,8337
 openstef/model/metamodels/missing_values_handler.py,sha256=veyvYZHhKvlYZxaUpxRQ7XoE033_3Lcg9LrbuKchlOk,5241
 openstef/model/regressors/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
@@ -54,7 +55,7 @@ openstef/model/regressors/dazls.py,sha256=Xt89yFHjkwpIUTkkhPmPZ74F8_tht_XV88INuP
 openstef/model/regressors/flatliner.py,sha256=T9u-ukhqFcatQmlgUtBL_G-1b_wQzgdVRq0ac64GnjQ,2789
 openstef/model/regressors/lgbm.py,sha256=zCdn1euEdSFxYJzH8XqQFFnb6R4JVUnmineKjX_Gy-g,800
 openstef/model/regressors/linear.py,sha256=uOvZMLGZH_9nXfmS5honCMfyVeyGXP1Cza9A_BdXlVw,3665
-openstef/model/regressors/linear_quantile.py,sha256=uj8Hd-Po14YymC_dUNSzxDayGqK9MjZ2dp_aLnpiv0s,10126
+openstef/model/regressors/linear_quantile.py,sha256=VAyIhp7GPayqbk8Vj_ONqPLNYuaOvxkFKDrRxx6yGY0,10510
 openstef/model/regressors/regressor.py,sha256=uJcx59AyCPE9f_yPcAQ59h2ZS7eNsDpIHJrladKvHIw,3461
 openstef/model/regressors/xgb.py,sha256=SH-UiYJtMbfmRBK6738dU0ZRfYfzNynnikwbxINCE7Q,1467
 openstef/model/regressors/xgb_multioutput_quantile.py,sha256=xWzA7tymC_o-F1OS3I7vUKf9zP6RR1ZglEeY4NAgjU0,9146
@@ -92,8 +93,8 @@ openstef/tasks/utils/predictionjobloop.py,sha256=Ysy3zF5lzPMz_asYDKeF5m0qgVT3tCt
 openstef/tasks/utils/taskcontext.py,sha256=L9K14ycwgVxbIVUjH2DIn_QWbnu-OfxcGtQ1K9T6sus,5630
 openstef/validation/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
 openstef/validation/validation.py,sha256=HVgreHvcZvPazfwC3NNE8_3lsMsZEd_42osCAg1_6W4,11128
-openstef-3.4.46.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
-openstef-3.4.46.dist-info/METADATA,sha256=UJAm_jF1JSm4lcXL2tPkwR7XBaEleozpBF6iJnI8D4U,8068
-openstef-3.4.46.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-openstef-3.4.46.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
-openstef-3.4.46.dist-info/RECORD,,
+openstef-3.4.49.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
+openstef-3.4.49.dist-info/METADATA,sha256=kQ4x33ZVT37sVcGoODmV3hnT3rpKMmM9JAyG88q63go,8305
+openstef-3.4.49.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+openstef-3.4.49.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
+openstef-3.4.49.dist-info/RECORD,,

{openstef-3.4.46.dist-info → openstef-3.4.49.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any