dragon-ml-toolbox 8.1.0__tar.gz → 8.2.0__tar.gz

{dragon_ml_toolbox-8.1.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-8.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 8.1.0
+Version: 8.2.0
 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-8.1.0 → dragon_ml_toolbox-8.2.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 8.1.0
+Version: 8.2.0
 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-8.1.0 → dragon_ml_toolbox-8.2.0}/ml_tools/ETL_engineering.py

@@ -3,7 +3,6 @@ import re
 from typing import Literal, Union, Optional, Any, Callable, List, Dict, Tuple
 from ._script_info import _script_info
 from ._logger import _LOGGER
-import warnings
 
 
 __all__ = [
@@ -13,6 +12,7 @@ __all__ = [
     "DataProcessor",
     "BinaryTransformer",
     "MultiBinaryDummifier",
+    "AutoDummifier",
     "KeywordDummifier",
     "NumberExtractor",
     "MultiNumberExtractor",
@@ -277,16 +277,32 @@ class DataProcessor:
                     processed_columns.append(result.alias(output_col_spec))
                 
                 elif isinstance(result, pl.DataFrame):
-                    if not isinstance(output_col_spec, list):
-                        raise TypeError(f"Function for '{input_col_name}' returned a DataFrame but 'output_col' is not a list.")
-                    if len(result.columns) != len(output_col_spec):
-                        raise ValueError(
-                            f"Mismatch in '{input_col_name}': function produced {len(result.columns)} columns, "
-                            f"but recipe specifies {len(output_col_spec)} output names."
-                        )
+                    # 1. Handle list-based renaming
+                    if isinstance(output_col_spec, list):
+                        if len(result.columns) != len(output_col_spec):
+                            raise ValueError(
+                                f"Mismatch in '{input_col_name}': function produced {len(result.columns)} columns, "
+                                f"but recipe specifies {len(output_col_spec)} output names."
+                            )
+                        
+                        renamed_df = result.rename(dict(zip(result.columns, output_col_spec)))
+                        processed_columns.extend(renamed_df.get_columns())
+
+                    # 2. Handle a string prefix for AutoDummifier
+                    elif isinstance(output_col_spec, str):
+                        prefix = output_col_spec
+                        # Replace the original name part with the desired prefix.
+                        new_names = {
+                            col: f"{prefix}{col[len(input_col_name):]}" for col in result.columns
+                        }
+                        renamed_df = result.rename(new_names)
+                        processed_columns.extend(renamed_df.get_columns())
                     
-                    renamed_df = result.rename(dict(zip(result.columns, output_col_spec)))
-                    processed_columns.extend(renamed_df.get_columns())
+                    else:
+                        raise TypeError(
+                            f"Function for '{input_col_name}' returned a DataFrame, "
+                            f"so 'output_col' must be a list of names or a string prefix."
+                        )
                 
                 else:
                     raise TypeError(f"Function for '{input_col_name}' returned an unexpected type: {type(result)}.")
@@ -413,6 +429,27 @@ class BinaryTransformer:
             return (~contains_keyword).cast(pl.UInt8)
 
 
+class AutoDummifier:
+    """
+    A transformer that performs one-hot encoding on a categorical column,
+    automatically detecting the unique categories from the data.
+    """
+    def __call__(self, column: pl.Series) -> pl.DataFrame:
+        """
+        Executes the one-hot encoding logic.
+
+        Args:
+            column (pl.Series): The input Polars Series of categories.
+
+        Returns:
+            pl.DataFrame: A DataFrame with one-hot encoded columns.
+                          Column names are auto-generated by Polars as
+                          '{original_col_name}_{category_value}'.
+        """
+        # Ensure the column is treated as a string before creating dummies
+        return column.cast(pl.Utf8).to_dummies()
+
+
 class MultiBinaryDummifier:
     """
     A one-to-many transformer that creates multiple binary columns from a single

{dragon_ml_toolbox-8.1.0 → dragon_ml_toolbox-8.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "8.1.0"
+version = "8.2.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }