dragon-ml-toolbox 13.1.0__py3-none-any.whl → 13.2.0__py3-none-any.whl

{dragon_ml_toolbox-13.1.0.dist-info → dragon_ml_toolbox-13.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.1.0
+Version: 13.2.0
 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-13.1.0.dist-info → dragon_ml_toolbox-13.2.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-13.1.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-13.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+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
 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
@@ -18,9 +18,9 @@ ml_tools/PSO_optimization.py,sha256=T-HWHMRJUnPvPwixdU5jif3_rnnI36TzcL8u3oSCwuA,
 ml_tools/RNN_forecast.py,sha256=Qa2KoZfdAvSjZ4yE78N4BFXtr3tTr0Gx7tQJZPotsh0,1967
 ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
 ml_tools/VIF_factor.py,sha256=at5IVqPvicja2-DNSTSIIy3SkzDWCmLzo3qTG_qr5n8,10422
-ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
+ml_tools/__init__.py,sha256=kJiankjz9_qXu7gU92mYqYg_anLvt-B6RtW0mMH8uGo,76
 ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
-ml_tools/_schema.py,sha256=MYYAO8CYygIvwv9TkGBAxzZpG7xQ2IV8_yB5zzFin0c,710
+ml_tools/_schema.py,sha256=MloQLJvuYzWHbmHfp0rUx5vgTPdfusfQ1b83KY277bY,2767
 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
@@ -29,13 +29,13 @@ ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNV
 ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
 ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
 ml_tools/handle_excel.py,sha256=pfdAPb9ywegFkM9T54bRssDOsX-K7rSeV0RaMz7lEAo,14006
-ml_tools/keys.py,sha256=eJ4St5fl8uHstEGO1XVdP8G-ddwjOxV9zqG0D6W8pCI,2124
+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=Wjf8N1thSfJ4r6Vm_pWxP2UTPcP2f3s2FiGz0z6kqKI,4925
+ml_tools/serde.py,sha256=IHXHS2XwpEe5Y8mdWvR2SAykOriB8CysDuD70SvtikQ,6223
 ml_tools/utilities.py,sha256=OcAyV1tEcYAfOWlGjRgopsjDLxU3DcI5EynzvWV4q3A,15754
-dragon_ml_toolbox-13.1.0.dist-info/METADATA,sha256=8n0bhl_rSVdg6MDh51r7tl5JflbqIOdqZx5gjaBWk0o,6166
-dragon_ml_toolbox-13.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-13.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-13.1.0.dist-info/RECORD,,
+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,,

ml_tools/__init__.py

@@ -1 +1,2 @@
 from .custom_logger import custom_logger
+from ._schema import FeatureSchema

ml_tools/_schema.py

@@ -1,4 +1,9 @@
-from typing import NamedTuple, Tuple, Optional, Dict
+from typing import NamedTuple, Tuple, Optional, Dict, Union
+from pathlib import Path
+
+from .custom_logger import save_list_strings
+from .keys import DatasetKeys
+
 
 class FeatureSchema(NamedTuple):
     """Holds the final, definitive schema for the model pipeline."""
@@ -15,5 +20,51 @@ class FeatureSchema(NamedTuple):
     # Map of {column_index: cardinality} for categorical features
     categorical_index_map: Optional[Dict[int, int]]
     
-    # The original string-to-int mappings (e.g., {'color': {'red': 0, 'blue': 1}})
+    # Map string-to-int category values (e.g., {'color': {'red': 0, 'blue': 1}})
     categorical_mappings: Optional[Dict[str, Dict[str, int]]]
+
+    def _save_helper(self, artifact: Tuple[str, ...], directory: Union[str,Path], filename: str, verbose: bool):
+        to_save = list(artifact)
+        save_list_strings(list_strings=to_save,
+                          directory=directory,
+                          filename=filename,
+                          verbose=verbose)
+
+    def save_all_features(self, directory: Union[str,Path], verbose: bool=True):
+        """
+        Saves all feature names to a text file.
+
+        Args:
+            directory: The directory where the file will be saved.
+            verbose: If True, prints a confirmation message upon saving.
+        """
+        self._save_helper(artifact=self.feature_names,
+                          directory=directory,
+                          filename=DatasetKeys.FEATURE_NAMES,
+                          verbose=verbose)
+        
+    def save_continuous_features(self, directory: Union[str,Path], verbose: bool=True):
+        """
+        Saves continuous feature names to a text file.
+
+        Args:
+            directory: The directory where the file will be saved.
+            verbose: If True, prints a confirmation message upon saving.
+        """
+        self._save_helper(artifact=self.continuous_feature_names,
+                          directory=directory,
+                          filename=DatasetKeys.CONTINUOUS_NAMES,
+                          verbose=verbose)
+    
+    def save_categorical_features(self, directory: Union[str,Path], verbose: bool=True):
+        """
+        Saves categorical feature names to a text file.
+
+        Args:
+            directory: The directory where the file will be saved.
+            verbose: If True, prints a confirmation message upon saving.
+        """
+        self._save_helper(artifact=self.categorical_feature_names,
+                          directory=directory,
+                          filename=DatasetKeys.CATEGORICAL_NAMES,
+                          verbose=verbose)

ml_tools/keys.py

@@ -55,10 +55,13 @@ class PytorchArtifactPathKeys:
 
 
 class DatasetKeys:
-    """Keys for saving dataset artifacts"""
+    """Keys for saving dataset artifacts. Also used by FeatureSchema"""
     FEATURE_NAMES = "feature_names"
     TARGET_NAMES = "target_names"
     SCALER_PREFIX = "scaler_"
+    # Feature Schema
+    CONTINUOUS_NAMES = "continuous_feature_names"
+    CATEGORICAL_NAMES = "categorical_feature_names"
 
 
 class SHAPKeys:

ml_tools/serde.py

@@ -6,12 +6,15 @@ from pathlib import Path
 from .path_manager import make_fullpath, sanitize_filename
 from ._script_info import _script_info
 from ._logger import _LOGGER
+from ._schema import FeatureSchema
 
 
 __all__ = [
     "serialize_object_filename",
     "serialize_object",
     "deserialize_object",
+    "serialize_schema",
+    "deserialize_schema"
 ]
 
 
@@ -25,21 +28,20 @@ def serialize_object_filename(obj: Any, save_dir: Union[str,Path], filename: str
         filename (str) : Name for the output file, extension will be appended if needed.
     """
     try:
-        save_path = make_fullpath(save_dir, make=True)
+        save_path = make_fullpath(save_dir, make=True, enforce="directory")
         sanitized_name = sanitize_filename(filename)
-        if not sanitized_name.endswith('.joblib'):
-            sanitized_name = sanitized_name + ".joblib"
         full_path = save_path / sanitized_name
-        joblib.dump(obj, full_path)
-    except (IOError, OSError, TypeError, TerminatedWorkerError) as e:
-        _LOGGER.error(f"Failed to serialize object of type '{type(obj)}'.")
+    except (IOError, OSError, TypeError) as e:
+        _LOGGER.error(f"Failed to construct save path from dir='{save_dir}' and filename='{filename}'. Error: {e}")
         if raise_on_error:
             raise e
         return None
-    else:
-        if verbose:
-            _LOGGER.info(f"Object of type '{type(obj)}' saved to '{full_path}'")
-        return None
+    
+    # call serialize_object with the fully constructed path.
+    serialize_object(obj=obj,
+                     file_path=full_path,
+                     verbose=verbose,
+                     raise_on_error=raise_on_error)
 
 
 def serialize_object(obj: Any, file_path: Path, verbose: bool = True, raise_on_error: bool = False) -> None:
@@ -56,8 +58,7 @@ def serialize_object(obj: Any, file_path: Path, verbose: bool = True, raise_on_e
     """
     try:
         # Ensure the extension is correct
-        if file_path.suffix != '.joblib':
-            file_path = file_path.with_suffix(file_path.suffix + '.joblib')
+        file_path = file_path.with_suffix('.joblib')
 
         # Ensure the parent directory exists
         _save_dir = make_fullpath(file_path.parent, make=True, enforce="directory")
@@ -126,5 +127,46 @@ def deserialize_object(
         
         return obj
 
+
+def serialize_schema(schema: FeatureSchema, file_path: Path):
+    """
+    Serializes a FeatureSchema object to a .joblib file.
+
+    This is a high-level wrapper around `serialize_object` that
+    specifically handles `FeatureSchema` instances and ensures
+    errors are raised on failure.
+
+    Args:
+        schema (FeatureSchema): The schema object to serialize.
+        file_path (Path): The full file path to save the schema to.
+    """
+    serialize_object(obj=schema,
+                     file_path=file_path,
+                     verbose=True,
+                     raise_on_error=True)
+    
+    
+def deserialize_schema(file_path: Path):
+    """
+    Deserializes a FeatureSchema object from a .joblib file.
+
+    This is a high-level wrapper around `deserialize_object` that
+    validates the loaded object is an instance of `FeatureSchema`.
+
+    Args:
+        file_path (Path): The full file path of the serialized schema.
+
+    Returns:
+        FeatureSchema: The deserialized schema object.
+    
+    Raises:
+        TypeError: If the deserialized object is not an instance of `FeatureSchema`.
+    """
+    schema = deserialize_object(filepath=file_path,
+                                expected_type=FeatureSchema,
+                                verbose=True)
+    return schema
+
+
 def info():
     _script_info(__all__)