openstef 3.4.46__tar.gz → 3.4.48__tar.gz

{openstef-3.4.46 → openstef-3.4.48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.46
+Version: 3.4.48
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -29,7 +29,7 @@ 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

openstef-3.4.48/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-3.4.46 → openstef-3.4.48}/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 → openstef-3.4.48}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openstef
-Version: 3.4.46
+Version: 3.4.48
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V
@@ -29,7 +29,7 @@ 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

{openstef-3.4.46 → openstef-3.4.48}/openstef.egg-info/SOURCES.txt

@@ -55,6 +55,7 @@ openstef/model/objective_creator.py
 openstef/model/serializer.py
 openstef/model/standard_deviation_generator.py
 openstef/model/metamodels/__init__.py
+openstef/model/metamodels/feature_clipper.py
 openstef/model/metamodels/grouped_regressor.py
 openstef/model/metamodels/missing_values_handler.py
 openstef/model/regressors/__init__.py

{openstef-3.4.46 → openstef-3.4.48}/openstef.egg-info/requires.txt

@@ -13,7 +13,7 @@ pvlib==0.10.5
 pydantic~=2.4
 pydantic-settings~=2.3
 pymsteams~=0.2.2
-scikit-learn~=1.3
+scikit-learn<1.6,>=1.3
 scipy~=1.10
 statsmodels<1.0.0,>=0.13.5
 structlog<25,>=23.1

{openstef-3.4.46 → openstef-3.4.48}/setup.py

@@ -29,7 +29,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.46",
+    version="3.4.48",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),