dragon-ml-toolbox 10.11.0__py3-none-any.whl → 10.11.2__py3-none-any.whl

{dragon_ml_toolbox-10.11.0.dist-info → dragon_ml_toolbox-10.11.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.11.0
+Version: 10.11.2
 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-10.11.0.dist-info → dragon_ml_toolbox-10.11.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-10.11.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-10.11.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-10.11.2.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-10.11.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_cleaning.py,sha256=lSP5q6-ukGhJBPV8dlsqJvPXAzj4du_0J-SbtEd0Pjg,19292
 ml_tools/ETL_engineering.py,sha256=a6KCWH6kRatZtjaFEF_o917ApPMK5_vRD-BjfCDAl-E,49400
 ml_tools/GUI_tools.py,sha256=kEQWg-bog3pB5tI22gMGKWaCGHnz9TB2Lvvfhf5F2CI,45412
@@ -28,9 +28,9 @@ ml_tools/ensemble_learning.py,sha256=3s0kH4i_naj0IVl_T4knst-Hwg4TScWjEdsXX5KAi7I
 ml_tools/handle_excel.py,sha256=He4UT15sCGhaG-JKfs7uYVAubxWjrqgJ6U7OhMR2fuE,14005
 ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
 ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
-ml_tools/path_manager.py,sha256=CCZSlHpUiuaHsMAYcmMGZ9GvbHNbbrTqYFicgWz6pRs,17883
-ml_tools/utilities.py,sha256=30z0x1aDLyBGzF98_tgSaxwFafYwQS-GTFzXHopBSGc,29105
-dragon_ml_toolbox-10.11.0.dist-info/METADATA,sha256=dUnqRVopM0cM7AjWbhS2ife0tKObinp6J0vwUt-rJ-A,6969
-dragon_ml_toolbox-10.11.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-10.11.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-10.11.0.dist-info/RECORD,,
+ml_tools/path_manager.py,sha256=ke0MYOhYheRPX599GUbrvRsYHn2JKUmMDldS5LP6LQA,18431
+ml_tools/utilities.py,sha256=uheMUjQJ1zI69gASsE-mCq4KlRPVGgrgqson02rGNYM,30755
+dragon_ml_toolbox-10.11.2.dist-info/METADATA,sha256=bBK3PyfNJ-e6nvmGlyHg3HvDLSnmDsKHbo7KwovMWck,6969
+dragon_ml_toolbox-10.11.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-10.11.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-10.11.2.dist-info/RECORD,,

ml_tools/path_manager.py

@@ -248,26 +248,33 @@ class PathManager:
             _LOGGER.error(f"'{type(self).__name__}' object has no attribute or path key '{sanitized_name}'")
             raise AttributeError()
     
-    def __setattr__(self, name: str, value: Union[str, Path]):
+    def __setattr__(self, name: str, value: Union[str, Path, bool, dict, str, int, tuple]):
         """Allows attribute-style setting of paths, e.g., PM.data = 'path/to/data'."""
-        # Check for internal attributes 
+        # Check for internal attributes, which are set directly on the object.
         if name.startswith('_'):
-            if hasattr(self, '_initialized') and self._initialized:
-                self._check_underscore_key(name)
-                return
-            else:
-                # During initialization, allow private attributes to be set.
-                super().__setattr__(name, value)
+            # This check prevents setting new private attributes after __init__ is done.
+            is_initialized = self.__dict__.get('_initialized', False)
+            if is_initialized:
+                _LOGGER.error(f"Cannot set private attribute '{name}' after initialization.")
+                raise AttributeError()
+            super().__setattr__(name, value)
             return
 
-        # Block overwriting of existing methods/attributes
+        # Sanitize the key for the public path.
         sanitized_name = self._sanitize_key(name)
         self._check_underscore_key(sanitized_name)
-        if hasattr(self, sanitized_name):
+
+        # Prevent overwriting existing methods (e.g., PM.status = 'foo').
+        # This check looks at the class, not the instance therefore won't trigger __getattr__.
+        if hasattr(self.__class__, sanitized_name):
             _LOGGER.error(f"Cannot overwrite existing attribute or method '{sanitized_name}' ({name}).")
             raise AttributeError()
+        
+        if not isinstance(value, (str, Path)):
+            _LOGGER.error(f"Cannot assign type '{type(value).__name__}' to a path. Must be str or Path.")
+            raise TypeError
 
-        # If all checks pass, treat it as a public path.
+        # If all checks pass, treat it as a public path and store it in the _paths dictionary.
         self._paths[sanitized_name] = Path(value)
 
 

ml_tools/utilities.py

@@ -3,7 +3,7 @@ import numpy as np
 import pandas as pd
 import polars as pl
 from pathlib import Path
-from typing import Literal, Union, Sequence, Optional, Any, Iterator, Tuple, overload
+from typing import Literal, Union, Sequence, Optional, Any, Iterator, Tuple, overload, TypeVar, get_origin, Type
 import joblib
 from joblib.externals.loky.process_executor import TerminatedWorkerError
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths, list_files_by_extension, list_subdirectories
@@ -444,16 +444,32 @@ 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 deserialize_object(filepath: Union[str,Path], verbose: bool=True, raise_on_error: bool=True) -> Optional[Any]:
+# Define a TypeVar to link the expected type to the return type of deserialization
+T = TypeVar('T')
+    
+def deserialize_object(
+    filepath: Union[str, Path],
+    expected_type: Optional[Type[T]] = None,
+    verbose: bool = True,
+    raise_on_error: bool = True
+    ) -> Optional[T]:
     """
     Loads a serialized object from a .joblib file.
 
     Parameters:
         filepath (str | Path): Full path to the serialized .joblib file.
+        expected_type (Type[T] | None): The expected type of the object.
+            If provided, the function raises a TypeError if the loaded object
+            is not an instance of this type. It correctly handles generics
+            like `list[str]` by checking the base type (e.g., `list`).
+            Defaults to None, which skips the type check.
+        verbose (bool): If True, logs success messages.
+        raise_on_error (bool): If True, raises exceptions on errors. If False, returns None instead.
 
     Returns:
-        (Any | None): The deserialized Python object, or None if loading fails.
+        (Any | None): The deserialized Python object, which will match the
+            `expected_type` if provided. Returns None if an error
+            occurs and `raise_on_error` is False.
     """
     true_filepath = make_fullpath(filepath)
     
@@ -465,8 +481,26 @@ def deserialize_object(filepath: Union[str,Path], verbose: bool=True, raise_on_e
             raise e
         return None
     else:
+        # --- Type Validation Step ---
+        if expected_type:
+            # get_origin handles generics (e.g., list[str] -> list)
+            # If it's not a generic, get_origin returns None, so we use the type itself.
+            type_to_check = get_origin(expected_type) or expected_type
+            
+            # Can't do an isinstance check on 'Any', skip it.
+            if type_to_check is not Any and not isinstance(obj, type_to_check):
+                error_msg = (
+                    f"Type mismatch: Expected an instance of '{expected_type}', "
+                    f"but found '{type(obj)}' in '{true_filepath}'."
+                )
+                _LOGGER.error(error_msg)
+                if raise_on_error:
+                    raise TypeError()
+                return None
+        
         if verbose:
-            _LOGGER.info(f"Loaded object of type '{type(obj)}'.")
+            _LOGGER.info(f"Loaded object of type '{type(obj)}' from '{true_filepath}'.")
+        
         return obj