lecrapaud 0.7.0__tar.gz → 0.8.0__tar.gz

{lecrapaud-0.7.0 → lecrapaud-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.7.0
+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-0.7.0 → lecrapaud-0.8.0}/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-0.7.0 → lecrapaud-0.8.0}/lecrapaud/feature_selection.py

@@ -1140,6 +1140,7 @@ def get_features_by_types(df: pd.DataFrame, sample_categorical_threshold: int =
         for col in df.columns
         if df[col].nunique() <= sample_categorical_threshold
         and df[col].dtype in ["int64", "Int64"]
+        and (df[col] >= 0).all()
     ]
     df_categorical = df[categorical_features]
     logger.info(f"Number of categorical features: {len(categorical_features)}")

{lecrapaud-0.7.0 → lecrapaud-0.8.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lecrapaud"
-version = "0.7.0"
+version = "0.8.0"
 description = "Framework for machine and deep learning, with regression, classification and time series analysis"
 authors = [
     {name = "Pierre H. Gallet"}