dragon-ml-toolbox 13.1.0__tar.gz → 13.2.1__tar.gz

{dragon_ml_toolbox-13.1.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-13.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.1.0
+Version: 13.2.1
 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 → dragon_ml_toolbox-13.2.1/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 13.1.0
+Version: 13.2.1
 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 → dragon_ml_toolbox-13.2.1}/ml_tools/__init__.py

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

dragon_ml_toolbox-13.2.1/ml_tools/_schema.py

@@ -0,0 +1,85 @@
+from typing import NamedTuple, Tuple, Optional, Dict, Union
+from pathlib import Path
+
+from .custom_logger import save_list_strings
+from .keys import DatasetKeys
+from ._logger import _LOGGER
+
+
+class FeatureSchema(NamedTuple):
+    """Holds the final, definitive schema for the model pipeline."""
+    
+    # The final, ordered list of all feature names
+    feature_names: Tuple[str, ...]
+    
+    # List of all continuous feature names
+    continuous_feature_names: Tuple[str, ...]
+    
+    # List of all categorical feature names
+    categorical_feature_names: Tuple[str, ...]
+    
+    # Map of {column_index: cardinality} for categorical features
+    categorical_index_map: Optional[Dict[int, int]]
+    
+    # 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)
+        
+        # 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,
+                          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)
+        
+    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)

{dragon_ml_toolbox-13.1.0 → dragon_ml_toolbox-13.2.1}/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:

{dragon_ml_toolbox-13.1.0 → dragon_ml_toolbox-13.2.1}/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__)

{dragon_ml_toolbox-13.1.0 → dragon_ml_toolbox-13.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "13.1.0"
+version = "13.2.1"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl L. Loza Vidaurre", email = "luigiloza@gmail.com" }

dragon_ml_toolbox-13.1.0/ml_tools/_schema.py

@@ -1,19 +0,0 @@
-from typing import NamedTuple, Tuple, Optional, Dict
-
-class FeatureSchema(NamedTuple):
-    """Holds the final, definitive schema for the model pipeline."""
-    
-    # The final, ordered list of all feature names
-    feature_names: Tuple[str, ...]
-    
-    # List of all continuous feature names
-    continuous_feature_names: Tuple[str, ...]
-    
-    # List of all categorical feature names
-    categorical_feature_names: Tuple[str, ...]
-    
-    # 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}})
-    categorical_mappings: Optional[Dict[str, Dict[str, int]]]