openstef 3.4.79__py3-none-any.whl → 3.4.80__py3-none-any.whl

openstef/model/metamodels/feature_clipper.py

@@ -4,9 +4,15 @@
 from typing import Dict, List, Optional, Tuple
 
 import pandas as pd
+from pydantic import BaseModel
 from sklearn.base import BaseEstimator, TransformerMixin
 
 
+class FeatureStats(BaseModel):
+    mean: float
+    std: float
+
+
 class FeatureClipper(BaseEstimator, TransformerMixin):
     """
     A transformer that clips the values of specified columns to the minimum and
@@ -14,7 +20,7 @@ class FeatureClipper(BaseEstimator, TransformerMixin):
     extrapolating beyond these values during prediction.
     """
 
-    def __init__(self, columns: List[str]):
+    def __init__(self, columns: List[str], clip_number_of_std: float = 2.0):
         """
         Initialize the FeatureClipper.
 
@@ -24,7 +30,8 @@ class FeatureClipper(BaseEstimator, TransformerMixin):
             List of column names to be clipped.
         """
         self.columns: List[str] = columns
-        self.feature_ranges: Dict[str, Tuple[float, float]] = {}
+        self.feature_ranges: Dict[str, Tuple[float, float] | FeatureStats] = {}
+        self.clip_number_of_std = clip_number_of_std
 
     def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> "FeatureClipper":
         """
@@ -54,7 +61,9 @@ class FeatureClipper(BaseEstimator, TransformerMixin):
 
         for col in self.columns:
             if col in X.columns:
-                self.feature_ranges[col] = (X[col].min(), X[col].max())
+                self.feature_ranges[col] = FeatureStats(
+                    mean=X[col].mean(), std=X[col].std()
+                )
 
         return self
 
@@ -85,7 +94,15 @@ class FeatureClipper(BaseEstimator, TransformerMixin):
 
         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)
+                if isinstance(self.feature_ranges[col], FeatureStats):
+                    stats = self.feature_ranges[col]
+                    X_copy[col] = X_copy[col].clip(
+                        lower=stats.mean - self.clip_number_of_std * stats.std,
+                        upper=stats.mean + self.clip_number_of_std * stats.std,
+                    )
+                else:
+                    # Backward compatibility with previous minmax-based implementation
+                    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-3.4.79.dist-info → openstef-3.4.80.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openstef
-Version: 3.4.79
+Version: 3.4.80
 Summary: Open short term energy forecaster
 Home-page: https://github.com/OpenSTEF/openstef
 Author: Alliander N.V

{openstef-3.4.79.dist-info → openstef-3.4.80.dist-info}/RECORD

@@ -52,7 +52,7 @@ openstef/model/objective_creator.py,sha256=3jJgcmY1sm-Yoe3SfjKrJukrsqtYyloUFaPbB
 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
+openstef/model/metamodels/feature_clipper.py,sha256=moAZKC8fY3wB_k5x_imNXiS0VgwCdEj80oveVb6M1g8,3593
 openstef/model/metamodels/grouped_regressor.py,sha256=yMN_a6TnQSyFaqlB_6Nifq-ydpb5hs6w_b97IaBbHj4,8337
 openstef/model/metamodels/missing_values_handler.py,sha256=glgAlkeubLZFWbD8trTYBik7_qOJi4GCPGl1sSybSkQ,5257
 openstef/model/regressors/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
@@ -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-3.4.79.dist-info/licenses/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
-openstef-3.4.79.dist-info/METADATA,sha256=zfFVPR_RhCyKZ50LSCxuA46CI8L8d2tIJH02ryc9bUk,8834
-openstef-3.4.79.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-openstef-3.4.79.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
-openstef-3.4.79.dist-info/RECORD,,
+openstef-3.4.80.dist-info/licenses/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
+openstef-3.4.80.dist-info/METADATA,sha256=dOp_BpkALreNj6bd4oGsF7H-m-wlFMwf0PTWsqrG1oU,8834
+openstef-3.4.80.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+openstef-3.4.80.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
+openstef-3.4.80.dist-info/RECORD,,