lecrapaud 0.9.0__tar.gz → 0.9.2__tar.gz

{lecrapaud-0.9.0 → lecrapaud-0.9.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.9.0
+Version: 0.9.2
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 Author: Pierre H. Gallet

{lecrapaud-0.9.0 → lecrapaud-0.9.2}/lecrapaud/db/models/experiment.py

@@ -121,6 +121,7 @@ class Experiment(Base):
             for fs in self.feature_selections
             if fs.target_id in target_idx
         )
+        _all_features = list(_all_features)
 
         # fallback to path if no features found
         if len(_all_features) == 0:
@@ -131,7 +132,7 @@ class Experiment(Base):
             all_features.append(date_column)
         if group_column:
             all_features.append(group_column)
-        all_features += list(_all_features)
+        all_features += _all_features
         all_features = list(dict.fromkeys(all_features))
 
         return all_features

{lecrapaud-0.9.0 → lecrapaud-0.9.2}/lecrapaud/feature_engineering.py

@@ -811,14 +811,34 @@ def traditional_descriptive_analysis(df: pd.DataFrame, group_column: str | None
         # Shape
         results["Shape"] = f"{df.shape[0]} rows × {df.shape[1]} columns"
 
+        # Create a copy of the DataFrame to avoid modifying the original
+        df_check = df.copy()
+        
+        # Convert numpy arrays to tuples for hashing
+        for col in df_check.columns:
+            if df_check[col].apply(lambda x: isinstance(x, np.ndarray)).any():
+                df_check[col] = df_check[col].apply(
+                    lambda x: tuple(x) if isinstance(x, np.ndarray) else x
+                )
+
         # Duplicated rows
-        results["Duplicated rows"] = int(df.duplicated().sum())
+        results["Duplicated rows"] = int(df_check.duplicated().sum())
 
-        # Duplicated columns
-        duplicated_cols = df.T[df.T.duplicated()].index.tolist()
-        results["Duplicated columns"] = (
-            ", ".join(duplicated_cols) if len(duplicated_cols) > 0 else "None"
-        )
+        # Check for duplicated columns
+        try:
+            # Try to find duplicated columns
+            duplicated_cols = []
+            cols = df_check.columns
+            for i, col1 in enumerate(cols):
+                for col2 in cols[i+1:]:
+                    if df_check[col1].equals(df_check[col2]):
+                        duplicated_cols.append(f"{col1} = {col2}")
+            
+            results["Duplicated columns"] = (
+                ", ".join(duplicated_cols) if duplicated_cols else "None"
+            )
+        except Exception as e:
+            results["Duplicated columns"] = f"Could not check: {str(e)}"
 
         # Missing values
         missing = df.isnull().sum()

{lecrapaud-0.9.0 → lecrapaud-0.9.2}/lecrapaud/feature_selection.py

@@ -899,10 +899,14 @@ class PreprocessModel:
         self.train = self.train[columns_to_keep]
 
         scaler_x = joblib.load(f"{self.preprocessing_dir}/scaler_x.pkl")
-        scaled_data = scaler_x.transform(self.train)
-        scaled_data = pd.DataFrame(
-            scaled_data, columns=self.train.columns, index=self.train.index
-        )
+
+        if scaler_x:
+            scaled_data = scaler_x.transform(self.train)
+            scaled_data = pd.DataFrame(
+                scaled_data, columns=self.train.columns, index=self.train.index
+            )
+        else:
+            scaled_data = self.train
 
         reshaped_data = None
         if (

{lecrapaud-0.9.0 → lecrapaud-0.9.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lecrapaud"
-version = "0.9.0"
+version = "0.9.2"
 description = "Framework for machine and deep learning, with regression, classification and time series analysis"
 authors = [
     {name = "Pierre H. Gallet"}