dragon-ml-toolbox 10.4.2__py3-none-any.whl → 10.5.0__py3-none-any.whl

{dragon_ml_toolbox-10.4.2.dist-info → dragon_ml_toolbox-10.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.4.2
+Version: 10.5.0
 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-10.4.2.dist-info → dragon_ml_toolbox-10.5.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-10.4.2.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-10.4.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-10.5.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-10.5.0.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
@@ -21,7 +21,7 @@ ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=wcImAiXEZKPNcwM30qBh3t7HvoPURonJY0nrgMGF0sM,4719
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/custom_logger.py,sha256=ry43hk54K6xKo8jRAgq1sFxUpOA9T0LIJ7sw0so2BW0,5880
-ml_tools/data_exploration.py,sha256=hKA_3U-piJ8TtDWhzX_T2Awkg-25e0DC5E8qloqPo6w,27206
+ml_tools/data_exploration.py,sha256=4McT2BR9muK4JVVTKUfvRyThe0m_o2vpy9RJ1f_1FeY,28692
 ml_tools/ensemble_evaluation.py,sha256=xMEMfXJ5MjTkTfr1LkFOeD7iUtnVDCW3S9lm3zT-6tY,24778
 ml_tools/ensemble_inference.py,sha256=EFHnbjbu31fcVp88NBx8lWAVdu2Gpg9MY9huVZJHFfM,9350
 ml_tools/ensemble_learning.py,sha256=3s0kH4i_naj0IVl_T4knst-Hwg4TScWjEdsXX5KAi7I,21929
@@ -30,7 +30,7 @@ ml_tools/keys.py,sha256=HtPG8-MWh89C32A7eIlfuuA-DLwkxGkoDfwR2TGN9CQ,1074
 ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
 ml_tools/path_manager.py,sha256=7sRvAoNrboRY6ef9gH3_qdzoZ66iLs7Aii4P39K0kEk,13819
 ml_tools/utilities.py,sha256=SVMaSDigh6SUoAeig2_sXLLIj5w5mUs5KuVWpHvFDec,19816
-dragon_ml_toolbox-10.4.2.dist-info/METADATA,sha256=h1d0dElCW4RCyrk_awtDZs1wJM0-SA6kRgcDs4FlVAI,6968
-dragon_ml_toolbox-10.4.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-10.4.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-10.4.2.dist-info/RECORD,,
+dragon_ml_toolbox-10.5.0.dist-info/METADATA,sha256=K4ziPX-Xx9f4E2vk_OXm6G8CR8l07arIByU4yfGC5a8,6968
+dragon_ml_toolbox-10.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-10.5.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-10.5.0.dist-info/RECORD,,

ml_tools/data_exploration.py

@@ -21,6 +21,7 @@ __all__ = [
     "show_null_columns",
     "drop_columns_with_missing_data",
     "drop_macro",
+    "clean_column_names",
     "split_features_targets", 
     "split_continuous_binary", 
     "plot_correlation_heatmap", 
@@ -300,6 +301,42 @@ def drop_macro(df: pd.DataFrame,
     return df_clean
 
 
+def clean_column_names(df: pd.DataFrame, replacement_char: str = '-', replacement_pattern: str = r'[\[\]{}<>,:"]', verbose: bool = True) -> pd.DataFrame:
+    """
+    Cleans DataFrame column names by replacing special characters.
+
+    This function is useful for ensuring compatibility with libraries like LightGBM,
+    which do not support special JSON characters such as `[]{}<>,:"` in feature names.
+
+    Args:
+        df (pd.DataFrame): The input DataFrame.
+        replacement_char (str): The character to use for replacing characters.
+        replacement_pattern (str): Regex pattern to use for the replacement logic.
+        verbose (bool): If True, prints the renamed columns.
+
+    Returns:
+        pd.DataFrame: A new DataFrame with cleaned column names.
+    """
+    new_df = df.copy()
+    
+    original_columns = new_df.columns
+    new_columns = original_columns.str.replace(replacement_pattern, replacement_char, regex=True)
+    
+    # Create a map of changes for logging
+    rename_map = {old: new for old, new in zip(original_columns, new_columns) if old != new}
+    
+    if verbose:
+        if rename_map:
+            _LOGGER.info(f"Cleaned {len(rename_map)} column name(s) containing special characters:")
+            for old, new in rename_map.items():
+                print(f"    '{old}' -> '{new}'")
+        else:
+            _LOGGER.info("No column names required cleaning.")
+            
+    new_df.columns = new_columns
+    return new_df
+
+
 def split_features_targets(df: pd.DataFrame, targets: list[str]):
     """
     Splits a DataFrame's columns into features and targets.