dragon-ml-toolbox 12.3.0__tar.gz → 12.5.0__tar.gz

{dragon_ml_toolbox-12.3.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-12.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.3.0
+Version: 12.5.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-12.3.0 → dragon_ml_toolbox-12.5.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.3.0
+Version: 12.5.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-12.3.0 → dragon_ml_toolbox-12.5.0}/ml_tools/custom_logger.py

@@ -172,7 +172,7 @@ def load_list_strings(text_file: Union[str,Path], verbose: bool=True) -> list[st
         raise ValueError()
     
     if verbose:
-        _LOGGER.info(f"Text file loaded as list of strings.")
+        _LOGGER.info(f"Loaded '{target_path.name}' as list of strings.")
         
     return loaded_strings
 

{dragon_ml_toolbox-12.3.0 → dragon_ml_toolbox-12.5.0}/ml_tools/data_exploration.py

@@ -891,7 +891,8 @@ def standardize_percentages(
     df: pd.DataFrame,
     columns: list[str],
     treat_one_as_proportion: bool = True,
-    round_digits: int = 2
+    round_digits: int = 2,
+    verbose: bool=True
 ) -> pd.DataFrame:
     """
     Standardizes numeric columns containing mixed-format percentages.
@@ -932,6 +933,8 @@ def standardize_percentages(
 
         # Otherwise, the value is assumed to be a correctly formatted percentage
         return x
+    
+    fixed_columns: list[str] = list()
 
     for col in columns:
         # --- Robustness Checks ---
@@ -949,6 +952,13 @@ def standardize_percentages(
 
         # Round the result
         df_copy[col] = df_copy[col].round(round_digits)
+        
+        fixed_columns.append(col)
+        
+    if verbose:
+        _LOGGER.info(f"Columns standardized:")
+        for fixed_col in fixed_columns:
+            print(f"  '{fixed_col}'")
 
     return df_copy
 

{dragon_ml_toolbox-12.3.0 → dragon_ml_toolbox-12.5.0}/ml_tools/serde.py

@@ -9,12 +9,13 @@ from ._logger import _LOGGER
 
 
 __all__ = [
+    "serialize_object_filename",
     "serialize_object",
     "deserialize_object",
 ]
 
 
-def serialize_object(obj: Any, save_dir: Union[str,Path], filename: str, verbose: bool=True, raise_on_error: bool=False) -> None:
+def serialize_object_filename(obj: Any, save_dir: Union[str,Path], filename: str, verbose: bool=True, raise_on_error: bool=False) -> None:
     """
     Serializes a Python object using joblib; suitable for Python built-ins, numpy, and pandas.
 
@@ -40,6 +41,41 @@ def serialize_object(obj: Any, save_dir: Union[str,Path], filename: str, verbose
             _LOGGER.info(f"Object of type '{type(obj)}' saved to '{full_path}'")
         return None
 
+
+def serialize_object(obj: Any, file_path: Path, verbose: bool = True, raise_on_error: bool = False) -> None:
+    """
+    Serializes a Python object using joblib to a specific file path.
+
+    Suitable for Python built-ins, numpy, and pandas.
+
+    Parameters:
+        obj (Any) : The Python object to serialize.
+        file_path (Path) : The full file path to save the object to.
+                           '.joblib' extension will be appended if missing.
+        raise_on_error (bool) : If True, raises exceptions on failure.
+    """
+    try:
+        # Ensure the extension is correct
+        if file_path.suffix != '.joblib':
+            file_path = file_path.with_suffix(file_path.suffix + '.joblib')
+
+        # Ensure the parent directory exists
+        _save_dir = make_fullpath(file_path.parent, make=True, enforce="directory")
+
+        # Dump the object
+        joblib.dump(obj, file_path)
+
+    except (IOError, OSError, TypeError, TerminatedWorkerError) as e:
+        _LOGGER.error(f"Failed to serialize object of type '{type(obj)}' to '{file_path}'. Error: {e}")
+        if raise_on_error:
+            raise e
+        return None
+    else:
+        if verbose:
+            _LOGGER.info(f"Object of type '{type(obj)}' saved to '{file_path}'")
+        return None
+
+
 # Define a TypeVar to link the expected type to the return type of deserialization
 T = TypeVar('T')
     

{dragon_ml_toolbox-12.3.0 → dragon_ml_toolbox-12.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "12.3.0"
+version = "12.5.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl L. Loza Vidaurre", email = "luigiloza@gmail.com" }