dragon-ml-toolbox 9.0.0__py3-none-any.whl → 9.1.0__py3-none-any.whl

{dragon_ml_toolbox-9.0.0.dist-info → dragon_ml_toolbox-9.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 9.0.0
+Version: 9.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-9.0.0.dist-info → dragon_ml_toolbox-9.1.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-9.0.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-9.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
-ml_tools/ETL_engineering.py,sha256=SH8b9BSR79cib49YpIixjayaruD0qftnW7FV3xskoOs,44876
+dragon_ml_toolbox-9.1.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-9.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+ml_tools/ETL_engineering.py,sha256=c-YyhfuNglUhDBbTN71-iHozWL7Y9E8KqNNS5hK1nA4,44883
 ml_tools/GUI_tools.py,sha256=kEQWg-bog3pB5tI22gMGKWaCGHnz9TB2Lvvfhf5F2CI,45412
 ml_tools/MICE_imputation.py,sha256=kVSythWfxJFR4-2mtcYCWQaQ1Oz5yyx_SJu5gjnS7H8,11670
 ml_tools/ML_callbacks.py,sha256=JPvEw_cW5tYNJ2rMSgnNrKLuni_UrmuhDFaOw-u2SvA,13926
@@ -24,12 +24,12 @@ ml_tools/data_exploration.py,sha256=hKA_3U-piJ8TtDWhzX_T2Awkg-25e0DC5E8qloqPo6w,
 ml_tools/ensemble_evaluation.py,sha256=xMEMfXJ5MjTkTfr1LkFOeD7iUtnVDCW3S9lm3zT-6tY,24778
 ml_tools/ensemble_inference.py,sha256=EFHnbjbu31fcVp88NBx8lWAVdu2Gpg9MY9huVZJHFfM,9350
 ml_tools/ensemble_learning.py,sha256=3s0kH4i_naj0IVl_T4knst-Hwg4TScWjEdsXX5KAi7I,21929
-ml_tools/handle_excel.py,sha256=p5BpBS9vhBhz3lqkk_WQ9Ef7EGedf2dp2cl0yekeRy4,13065
+ml_tools/handle_excel.py,sha256=He4UT15sCGhaG-JKfs7uYVAubxWjrqgJ6U7OhMR2fuE,14005
 ml_tools/keys.py,sha256=HtPG8-MWh89C32A7eIlfuuA-DLwkxGkoDfwR2TGN9CQ,1074
 ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
 ml_tools/path_manager.py,sha256=TJgoqMAryc5F0dal8W_zvJgE1TpOzlskIyYJk614WW4,13809
 ml_tools/utilities.py,sha256=zzfYR7SUSb2rZILTNoCjl_pfLlPdHf4263atXuEb3iE,19341
-dragon_ml_toolbox-9.0.0.dist-info/METADATA,sha256=FWDN8U9RARbPxbCBVrv4ZHqJys-LVo7M3dlyVwKdh74,6941
-dragon_ml_toolbox-9.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-9.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-9.0.0.dist-info/RECORD,,
+dragon_ml_toolbox-9.1.0.dist-info/METADATA,sha256=NMMsbllyABDp8fVflbBWJ9aIQ0KemBI-3hBlj5JhE2E,6941
+dragon_ml_toolbox-9.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-9.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-9.1.0.dist-info/RECORD,,

ml_tools/ETL_engineering.py

@@ -62,7 +62,7 @@ def save_unique_values(csv_path: Union[str, Path], output_dir: Union[str, Path])
         
     # --- 3. Process Each Column ---
     for i, column_name in enumerate(df.columns):
-        _LOGGER.info(f"Processing column: '{column_name}'...")
+        # _LOGGER.info(f"Processing column: '{column_name}'...")
 
         # --- Get unique values AS IS ---
         try:
@@ -96,7 +96,7 @@ def save_unique_values(csv_path: Union[str, Path], output_dir: Union[str, Path])
         except IOError:
             _LOGGER.exception(f"Error writing to file {file_path}.")
         else:
-            _LOGGER.info(f"Successfully saved {len(sorted_uniques)} unique values to '{file_path}'")
+            _LOGGER.info(f"Successfully saved {len(sorted_uniques)} unique values from '{column_name}'.")
             
     _LOGGER.info("Process complete.")
 

ml_tools/handle_excel.py

@@ -167,49 +167,63 @@ def validate_excel_schema(
     strict: bool = False
 ) -> None:
     """
-    Validates that each Excel file in a directory conforms to the expected column schema.
+    Validates that each Excel file in a directory conforms to the expected column schema. Only the first worksheet of each file is analyzed.
     
     Parameters:
         target_dir (str | Path): Path to the directory containing Excel files.
         expected_columns (list[str]): List of expected column names.
         strict (bool): If True, columns must match exactly (names and order).
                       If False, columns must contain at least all expected names.
-
-    Returns:
-        List[str]: List of file paths that failed the schema validation.
     """
-    invalid_files: list[Path] = []
+    invalid_files: dict[str, str] = {}
     expected_set = set(expected_columns)
     
     target_path = make_fullpath(target_dir)
-    
     excel_paths = find_excel_files(target_path)
     
     for file in excel_paths:
         try:
+            # Using first worksheet
             wb = load_workbook(file, read_only=True)
-            ws = wb.active  # Only check the first worksheet
+            ws = wb.active
 
             header = [cell.value for cell in next(ws.iter_rows(max_row=1))] # type: ignore
 
+            # Change 2: Detailed reason-finding logic
             if strict:
                 if header != expected_columns:
-                    invalid_files.append(file)
+                    header_set = set(header)
+                    reason_parts = []
+                    missing = sorted(list(expected_set - header_set)) # type: ignore
+                    extra = sorted(list(header_set - expected_set)) # type: ignore
+                    
+                    if missing:
+                        reason_parts.append(f"Missing: {missing}")
+                    if extra:
+                        reason_parts.append(f"Extra: {extra}")
+                    if not missing and not extra:
+                        reason_parts.append("Incorrect column order")
+                    
+                    invalid_files[file.name] = ". ".join(reason_parts)
             else:
                 header_set = set(header)
                 if not expected_set.issubset(header_set):
-                    invalid_files.append(file)
+                    missing_cols = sorted(list(expected_set - header_set)) # type: ignore
+                    reason = f"Missing required columns: {missing_cols}"
+                    invalid_files[file.name] = reason
 
         except Exception as e:
             _LOGGER.error(f"Error processing '{file}': {e}")
-            invalid_files.append(file)
+            invalid_files[file.name] = f"File could not be read. Error: {e}"
     
     valid_excel_number = len(excel_paths) - len(invalid_files)
     _LOGGER.info(f"{valid_excel_number} out of {len(excel_paths)} excel files conform to the schema.")
+    
+    # Change 3: Updated print loop to show the reason
     if invalid_files:
         _LOGGER.warning(f"{len(invalid_files)} excel files are invalid:")
-        for in_file in invalid_files:
-            print(f"  - {in_file.name}")
+        for file_name, reason in invalid_files.items():
+            print(f"  - {file_name}: {reason}")
 
     return None