lecrapaud 0.7.1__py3-none-any.whl → 0.8.0__py3-none-any.whl

lecrapaud/feature_engineering.py

@@ -122,8 +122,41 @@ class FeatureEngineeringEngine:
         # Cyclic encode dates
         self.data = self.cyclic_encode_date()
 
+        # Remove constant columns if training (feature selection methods need independent features)
+        if self.for_training:
+            self.data = self.remove_constant_columns()
+
         return self.data
 
+    def remove_constant_columns(
+        self,
+        threshold: float = 0.99,
+    ) -> pd.DataFrame:
+        """
+            Removes constant or almost constant columns from a DataFrame.
+
+        Parameters:
+            threshold (float): Max proportion for a single value (default 0.99 = 99%).
+
+        Returns:
+            pd.DataFrame: Cleaned DataFrame.
+        """
+
+        to_drop = []
+
+        for col in self.data.columns:
+            value_counts = self.data[col].value_counts(dropna=False, normalize=True)
+            if value_counts.empty:
+                to_drop.append(col)
+            elif value_counts.iloc[0] >= threshold:
+                to_drop.append(col)
+
+        if to_drop:
+            logger.info(f"🔍 Removed {len(to_drop)} constant/almost constant columns:")
+            logger.info(to_drop)
+
+        return self.data.drop(columns=to_drop, errors="ignore")
+
     def cyclic_encode_date(self) -> pd.DataFrame:
         """
         Adds cyclic (sine and cosine) encoding for common date parts: day of week, day of month, and month.

{lecrapaud-0.7.1.dist-info → lecrapaud-0.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.7.1
+Version: 0.8.0
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 Author: Pierre H. Gallet

{lecrapaud-0.7.1.dist-info → lecrapaud-0.8.0.dist-info}/RECORD

@@ -23,7 +23,7 @@ lecrapaud/db/models/target.py,sha256=DKnfeaLU8eT8J_oh_vuFo5-o1CaoXR13xBbswme6Bgk
 lecrapaud/db/session.py,sha256=K9dTyXmO-aF_2r9RRHsDsbW9_zLNDaOcchXlpiv7cSo,2719
 lecrapaud/directories.py,sha256=t4PrnJR48MpDfBOTYTyGlDVMUr39mcaj7uCPTaocBRw,725
 lecrapaud/experiment.py,sha256=NwwGDZqUyvvRu5EDK3_Oh0_kF29bNIPDawVFFpzFvZM,2350
-lecrapaud/feature_engineering.py,sha256=U3YOftZBB3PEqGbu2aFY_3B3Ks9Hiu04UxixOkBz0UU,31168
+lecrapaud/feature_engineering.py,sha256=_KohdWnM5W4z6bDzrNrHuRb_0aY1Fc0DUpssNPi7wy0,32241
 lecrapaud/feature_selection.py,sha256=vgA7E4zUJpv3wNC3GA8_l-RjFdwoiIXcgoc6SKQH22o,42746
 lecrapaud/integrations/openai_integration.py,sha256=hHLF3fk5Bps8KNbNrEL3NUFa945jwClE6LrLpuMZOd4,7459
 lecrapaud/jobs/__init__.py,sha256=ZkrsyTOR21c_wN7RY8jPhm8jCrL1oCEtTsf3VFIlQiE,292
@@ -37,7 +37,7 @@ lecrapaud/speed_tests/test-gpu-resnet.ipynb,sha256=27Vu7nYwujYeh3fOxBNCnKJn3MXNP
 lecrapaud/speed_tests/test-gpu-transformers.ipynb,sha256=k6MBSs_Um1h4PykvE-LTBcdpbWLbIFST_xl_AFW2jgI,8444
 lecrapaud/speed_tests/tests.ipynb,sha256=RjI7LDHSsbadUkea_hT14sD7ivljtIQk4NB5McXJ1bE,3835
 lecrapaud/utils.py,sha256=Dy2uhK9cslzoqRHiIE6MdkxjNJWjmKmzGr6i7EYM28A,8106
-lecrapaud-0.7.1.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
-lecrapaud-0.7.1.dist-info/METADATA,sha256=K-iLKVIYfNQynIBxbUX91OAWyNlajm6pvdOl-b0HgX0,11623
-lecrapaud-0.7.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-lecrapaud-0.7.1.dist-info/RECORD,,
+lecrapaud-0.8.0.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
+lecrapaud-0.8.0.dist-info/METADATA,sha256=_qAznpxq2p5QHxb7FEKJoPbQQKDb0SfsTkyj6DA0diA,11623
+lecrapaud-0.8.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+lecrapaud-0.8.0.dist-info/RECORD,,