dragon-ml-toolbox 13.2.0__py3-none-any.whl → 13.3.0__py3-none-any.whl

{dragon_ml_toolbox-13.2.0.dist-info → dragon_ml_toolbox-13.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.2.0
+Version: 13.3.0
 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-13.2.0.dist-info → dragon_ml_toolbox-13.3.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-13.2.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-13.2.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-13.3.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-13.3.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
 ml_tools/ETL_cleaning.py,sha256=2VBRllV8F-ZiPylPp8Az2gwn5ztgazN0BH5OKnRUhV0,20402
 ml_tools/ETL_engineering.py,sha256=KfYqgsxupAx6e_TxwO1LZXeu5mFkIhVXJrNjP3CzIZc,54927
 ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
@@ -20,11 +20,11 @@ ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
 ml_tools/VIF_factor.py,sha256=at5IVqPvicja2-DNSTSIIy3SkzDWCmLzo3qTG_qr5n8,10422
 ml_tools/__init__.py,sha256=kJiankjz9_qXu7gU92mYqYg_anLvt-B6RtW0mMH8uGo,76
 ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
-ml_tools/_schema.py,sha256=MloQLJvuYzWHbmHfp0rUx5vgTPdfusfQ1b83KY277bY,2767
+ml_tools/_schema.py,sha256=yu6aWmn_2Z4_AxAtJGDDCIa96y6JcUp-vgnCS013Qmw,3908
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/custom_logger.py,sha256=7tSAgRL7e-Ekm7rS1FLDocaPLCnaoKc7VSrtfwCtCEg,10067
-ml_tools/data_exploration.py,sha256=aVcxjoXVqrmFBpwBSbLvrG8quzJfr92On48Sy3K58Vs,51900
+ml_tools/data_exploration.py,sha256=-BbWO7BBFapPi_7ZuWo65VqguJXaBfgFSptrXyoWrDk,51902
 ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
 ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
@@ -33,9 +33,9 @@ ml_tools/keys.py,sha256=oykUVLB4Wos3AZomowjtI8AFFC5xnMUH-icNHydRpOk,2275
 ml_tools/math_utilities.py,sha256=PxoOrnuj6Ntp7_TJqyDWi0JX03WpAO5iaFNK2Oeq5I4,8800
 ml_tools/optimization_tools.py,sha256=TYFQ2nSnp7xxs-VyoZISWgnGJghFbsWasHjruegyJRs,12763
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
-ml_tools/serde.py,sha256=IHXHS2XwpEe5Y8mdWvR2SAykOriB8CysDuD70SvtikQ,6223
+ml_tools/serde.py,sha256=CmdJmQCPdrm2RQA1hWLsGxU_B3aClQoQ9B4vcQtIrEs,6951
 ml_tools/utilities.py,sha256=OcAyV1tEcYAfOWlGjRgopsjDLxU3DcI5EynzvWV4q3A,15754
-dragon_ml_toolbox-13.2.0.dist-info/METADATA,sha256=NzCUzaOdHUWqWZ7B96xs-rywNbalnz5MAlduLaowvX8,6166
-dragon_ml_toolbox-13.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-13.2.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-13.2.0.dist-info/RECORD,,
+dragon_ml_toolbox-13.3.0.dist-info/METADATA,sha256=m2RVQa8YeN6e4hnsg6TwAMjymhTrburFXbmw-yB8JeQ,6166
+dragon_ml_toolbox-13.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-13.3.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-13.3.0.dist-info/RECORD,,

ml_tools/_schema.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 from .custom_logger import save_list_strings
 from .keys import DatasetKeys
+from ._logger import _LOGGER
 
 
 class FeatureSchema(NamedTuple):
@@ -25,6 +26,12 @@ class FeatureSchema(NamedTuple):
 
     def _save_helper(self, artifact: Tuple[str, ...], directory: Union[str,Path], filename: str, verbose: bool):
         to_save = list(artifact)
+        
+        # empty check
+        if not to_save:
+            _LOGGER.warning(f"Skipping save for '{filename}': The feature list is empty.")
+            return
+        
         save_list_strings(list_strings=to_save,
                           directory=directory,
                           filename=filename,
@@ -68,3 +75,22 @@ class FeatureSchema(NamedTuple):
                           directory=directory,
                           filename=DatasetKeys.CATEGORICAL_NAMES,
                           verbose=verbose)
+        
+    def save_artifacts(self, directory: Union[str,Path]):
+        """
+        Saves feature names, categorical feature names, continuous feature names to separate text files.
+        """
+        self.save_all_features(directory=directory, verbose=True)
+        self.save_continuous_features(directory=directory, verbose=True)
+        self.save_categorical_features(directory=directory, verbose=True)
+        
+    def __repr__(self) -> str:
+        """Returns a concise representation of the schema's contents."""
+        total = len(self.feature_names)
+        cont = len(self.continuous_feature_names)
+        cat = len(self.categorical_feature_names)
+        index_map = self.categorical_index_map is not None
+        cat_map = self.categorical_mappings is not None
+        return (
+            f"<FeatureSchema(total={total}, continuous={cont}, categorical={cat}, index_map={index_map}, categorical_map={cat_map})>"
+        )

ml_tools/data_exploration.py

@@ -1262,7 +1262,7 @@ def finalize_feature_schema(
     categorical_feature_names_list: List[str] = []
     categorical_index_map_dict: Dict[int, int] = {}
 
-    _LOGGER.info("Finalizing feature schema...")
+    # _LOGGER.info("Finalizing feature schema...")
 
     if categorical_mappings:
         # --- Categorical features are present ---

ml_tools/serde.py

@@ -18,6 +18,10 @@ __all__ = [
 ]
 
 
+# Base types that have a generic `type()` log.
+_SIMPLE_TYPES = (list, dict, tuple, set, str, int, float, bool)
+
+
 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.
@@ -27,6 +31,10 @@ def serialize_object_filename(obj: Any, save_dir: Union[str,Path], filename: str
         save_dir (str | Path) : Directory path where the serialized object will be saved.
         filename (str) : Name for the output file, extension will be appended if needed.
     """
+    if obj is None:
+        _LOGGER.warning(f"Attempted to serialize a None object. Skipping save for '{filename}'.")
+        return
+    
     try:
         save_path = make_fullpath(save_dir, make=True, enforce="directory")
         sanitized_name = sanitize_filename(filename)
@@ -56,6 +64,10 @@ def serialize_object(obj: Any, file_path: Path, verbose: bool = True, raise_on_e
                            '.joblib' extension will be appended if missing.
         raise_on_error (bool) : If True, raises exceptions on failure.
     """
+    if obj is None:
+        _LOGGER.warning(f"Attempted to serialize a None object. Skipping save for '{file_path}'.")
+        return
+    
     try:
         # Ensure the extension is correct
         file_path = file_path.with_suffix('.joblib')
@@ -73,7 +85,11 @@ def serialize_object(obj: Any, file_path: Path, verbose: bool = True, raise_on_e
         return None
     else:
         if verbose:
-            _LOGGER.info(f"Object of type '{type(obj)}' saved to '{file_path}'")
+            if isinstance(obj, _SIMPLE_TYPES):
+                _LOGGER.info(f"Object of type '{type(obj)}' saved to '{file_path}'")
+            else:
+                _LOGGER.info(f"Object '{obj}' saved to '{file_path}'")
+
         return None
 
 
@@ -123,9 +139,13 @@ def deserialize_object(
                 raise TypeError()
         
         if verbose:
-            _LOGGER.info(f"Loaded object of type '{type(obj)}' from '{true_filepath}'.")
+            # log special objects
+            if isinstance(obj, _SIMPLE_TYPES):
+                _LOGGER.info(f"Loaded object of type '{type(obj)}' from '{true_filepath}'.")
+            else:
+                _LOGGER.info(f"Loaded object '{obj}' from '{true_filepath}'.")
         
-        return obj
+        return obj # type: ignore
 
 
 def serialize_schema(schema: FeatureSchema, file_path: Path):