lecrapaud 0.9.0__py3-none-any.whl → 0.9.1__py3-none-any.whl

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/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.dist-info → lecrapaud-0.9.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.9.0
+Version: 0.9.1
 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.dist-info → lecrapaud-0.9.1.dist-info}/RECORD

@@ -11,7 +11,7 @@ lecrapaud/db/alembic/versions/2025_06_24_1711-86457e2f333f_.py,sha256=dl6tfvcqEr
 lecrapaud/db/alembic.ini,sha256=zgvur-5jnLsT66_98FaTOTNgjwObGZCE0HqMwRAeJrs,3587
 lecrapaud/db/models/__init__.py,sha256=Lhyw9fVLdom0Fc6yIP-ip8FjkU1EwVwjae5q2VM815Q,740
 lecrapaud/db/models/base.py,sha256=CYtof_UjFwX3C7XUifequh_UtLHJ25bU7LCwT501uGE,7508
-lecrapaud/db/models/experiment.py,sha256=KwFbPTDAEXU0I9_33xMg6Ujx8QR_ffcjKA2YBOUuys4,3997
+lecrapaud/db/models/experiment.py,sha256=IeS-TWPT-4l9xCMIdR2S2O-foXNt3Ru6WmtPMWToK7c,4035
 lecrapaud/db/models/feature.py,sha256=5o77O2FyRObnLOCGNj8kaPSGM3pLv1Ov6mXXHYkmnYY,1136
 lecrapaud/db/models/feature_selection.py,sha256=nXy_Lg3uDxid71vYll_qzdo8ajYsJEXskI7vLQ3uyW0,3315
 lecrapaud/db/models/feature_selection_rank.py,sha256=PvEpdv-JJt2wZMtX5TO0wyZ3IONlPkeDaC49i0VA-qU,2074
@@ -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=_kuRARuw1pXe13K3MHz22KOJSiRmvhPb7Q2Mkli32t8,2519
-lecrapaud/feature_engineering.py,sha256=U3YOftZBB3PEqGbu2aFY_3B3Ks9Hiu04UxixOkBz0UU,31168
+lecrapaud/feature_engineering.py,sha256=MnBp0oVYuzL61yn3gCSxFpYRGMe3A0Cb8GAX66alODA,32006
 lecrapaud/feature_selection.py,sha256=_Je2817Ah1v-6Rls4EiYC-fn3EbpBj6Uaq81KWBpQG4,43430
 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-0.9.0.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
-lecrapaud-0.9.0.dist-info/METADATA,sha256=GZItqrsRZu_QUCY0hFsdN03454boqWlYIaZh4fIEaHY,11623
-lecrapaud-0.9.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-lecrapaud-0.9.0.dist-info/RECORD,,
+lecrapaud-0.9.1.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
+lecrapaud-0.9.1.dist-info/METADATA,sha256=Rjz-7FASML-yASCCeKHf4eagzuP970B2f75ttC9E7aY,11623
+lecrapaud-0.9.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+lecrapaud-0.9.1.dist-info/RECORD,,