openstef 3.4.72__tar.gz → 3.4.73__tar.gz

{openstef-3.4.72 → openstef-3.4.73}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.72
+Version: 3.4.73
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.72 → openstef-3.4.73}/openstef/data_classes/prediction_job.py

@@ -21,7 +21,7 @@ class PredictionJobDataClass(BaseModel):
     )
     model: str = Field(
         ...,
-        description="The model type that should be used. Options are: 'xgb', 'xgb_quantile', 'lgb', 'linear', 'linear_quantile', 'gblinear_quantile', 'xgb_multioutput_quantile', 'flatliner'.",
+        description="The model type that should be used. Options are: 'xgb', 'xgb_quantile', 'lgb', 'linear', 'linear_quantile', 'gblinear_quantile', 'xgb_multioutput_quantile', 'flatliner', 'median'.",
     )
 
     model_kwargs: Optional[dict] = Field(

{openstef-3.4.72 → openstef-3.4.73}/openstef/enums.py

@@ -125,6 +125,7 @@ class ModelType(Enum):
     GBLINEAR_QUANTILE = "gblinear_quantile"
     ARIMA = "arima"
     FLATLINER = "flatliner"
+    MEDIAN = "median"
 
 
 class ForecastType(Enum):

{openstef-3.4.72 → openstef-3.4.73}/openstef/model/model_creator.py

@@ -17,6 +17,7 @@ from openstef.model.regressors.xgb import XGBOpenstfRegressor
 from openstef.model.regressors.xgb_multioutput_quantile import (
     XGBMultiOutputQuantileOpenstfRegressor,
 )
+from openstef.model.regressors.median import MedianRegressor
 from openstef.model.regressors.xgb_quantile import XGBQuantileOpenstfRegressor
 
 logger = get_logger(__name__)
@@ -138,6 +139,9 @@ valid_model_kwargs = {
         "seasonal_order",
         "trend",
     ],
+    ModelType.MEDIAN: [
+        # This model does not have any parameters
+    ],
 }
 
 
@@ -155,6 +159,7 @@ class ModelCreator:
         ModelType.GBLINEAR_QUANTILE: GBLinearQuantileOpenstfRegressor,
         ModelType.ARIMA: ARIMAOpenstfRegressor,
         ModelType.FLATLINER: FlatlinerRegressor,
+        ModelType.MEDIAN: MedianRegressor,
     }
 
     @staticmethod

openstef-3.4.73/openstef/model/regressors/median.py

@@ -0,0 +1,78 @@
+"""This module contains the median regressor."""
+
+import numpy as np
+import pandas as pd
+
+from sklearn.base import RegressorMixin
+from sklearn.utils.validation import check_is_fitted
+
+from openstef.model.regressors.regressor import OpenstfRegressor
+
+
+class MedianRegressor(OpenstfRegressor, RegressorMixin):
+    """
+    Median regressor implementing the OpenSTEF regressor API.
+
+    This regressor is good for predicting two types of signals:
+    - Signals with very slow dynamics compared to the sampling rate, possibly
+      with a lot of noise.
+    - Signals that switch between two or more states, which random in nature or
+    depend on unknown features, but tend to be stable in each state. An example of
+    this may be waste heat delivered from an industrial process. Using a median
+    over the last few timesteps adds some hysterisis to avoid triggering on noise.
+    """
+
+    def __init__(self):
+        """Initialize MedianRegressor."""
+        super().__init__()
+
+    @property
+    def feature_names(self) -> list:
+        """Retrieve the model input feature names.
+
+        Returns:
+            The list of feature names
+
+        """
+        check_is_fitted(self, "feature_names_")
+        return self.feature_names_
+
+    @property
+    def can_predict_quantiles(self) -> bool:
+        return False
+
+    def predict(self, x: pd.DataFrame, **kwargs) -> np.array:
+        """
+        Predict the median of the lag features for each time step in the context window.
+
+        Args:
+            x (pd.DataFrame): The input data for prediction. This should be a pandas dataframe with lag features.
+
+        Returns:
+            np.array: The predicted median for each time step in the context window.
+            If any lag feature is NaN, this will be ignored.
+            If all lag features are NaN, the regressor will return NaN.
+        """
+
+        lag_df = x.loc[:, self.feature_names]
+        median = lag_df.median(axis=1, skipna=True)
+
+        return median
+
+    def fit(self, x: pd.DataFrame, y: pd.DataFrame, **kwargs) -> RegressorMixin:
+        """This model does not have any hyperparameters to fit,
+        but it does need to know the feature names of the lag features.
+
+        Which lag features are used is determined by the feature engineering step.
+        """
+        self.feature_names_ = list(x.columns[x.columns.str.startswith("T-")])
+        if len(self.feature_names_) == 0:
+            raise ValueError("No lag features found in the input data.")
+
+        self.feature_importances_ = np.ones(len(self.feature_names_)) / (
+            len(self.feature_names_) or 1.0
+        )
+        return self
+
+    def __sklearn_is_fitted__(self) -> bool:
+        return True

{openstef-3.4.72 → openstef-3.4.73}/openstef.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.72
+Version: 3.4.73
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.72 → openstef-3.4.73}/openstef.egg-info/SOURCES.txt

@@ -74,6 +74,7 @@ openstef/model/regressors/gblinear_quantile.py
 openstef/model/regressors/lgbm.py
 openstef/model/regressors/linear.py
 openstef/model/regressors/linear_quantile.py
+openstef/model/regressors/median.py
 openstef/model/regressors/regressor.py
 openstef/model/regressors/xgb.py
 openstef/model/regressors/xgb_multioutput_quantile.py

{openstef-3.4.72 → openstef-3.4.73}/setup.py

@@ -33,7 +33,7 @@ def read_long_description_from_readme():
 
 setup(
     name="openstef",
-    version="3.4.72",
+    version="3.4.73",
     packages=find_packages(include=["openstef", "openstef.*"]),
     description="Open short term energy forecaster",
     long_description=read_long_description_from_readme(),