dragon-ml-toolbox 12.3.0__py3-none-any.whl → 12.4.0__py3-none-any.whl

{dragon_ml_toolbox-12.3.0.dist-info → dragon_ml_toolbox-12.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.3.0
+Version: 12.4.0
 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-12.3.0.dist-info → dragon_ml_toolbox-12.4.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-12.3.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.3.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-12.4.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-12.4.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
 ml_tools/ETL_cleaning.py,sha256=PLRSR-VYnt1nNT9XrcWq40SE0VzHCw7DQ8v9czfSQsU,20366
 ml_tools/ETL_engineering.py,sha256=l0I6Og9o4s6EODdk0kZXjbbC-a3vVPYy1FopP2BkQSQ,54909
 ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
@@ -23,8 +23,8 @@ ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
-ml_tools/custom_logger.py,sha256=OZqG7FR_UE6byzY3RDmlj08a336ZU-4DzNBMPLr_d5c,5881
-ml_tools/data_exploration.py,sha256=H-cHp6jL4u4Kl2L_fktcCdQWRdAzTC6kwFCrOHnzLNA,46549
+ml_tools/custom_logger.py,sha256=xot-VeZFigKjcVxADgzvI54vZO_MqMMejo7JmDED8Xo,5892
+ml_tools/data_exploration.py,sha256=OwPJHAM6MpkUD-S76XF4v-NRXjw5-pizKNHpyKj5OwE,46809
 ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
 ml_tools/ensemble_learning.py,sha256=aTPeKthO4zRWBEaQJOUj8jEqVHiHjjOMXuiEWjI9NxM,21946
@@ -35,7 +35,7 @@ ml_tools/optimization_tools.py,sha256=ewYMAdSGlFxYALAGFXn-MsHpvW_Sbx6I-sKg9Kp6rB
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
 ml_tools/serde.py,sha256=k0qAwfMf13lVBQSgq5u9MSXEoo31iOA2-Ncm8XgMCMI,3974
 ml_tools/utilities.py,sha256=gef62GLK7ev5BWkkQekeJoVZqwf2mIuOlOfyCw6WdtE,13882
-dragon_ml_toolbox-12.3.0.dist-info/METADATA,sha256=999BzvvR1VfwwEETUJhMLJk6a3EtcPuITG_QXE2NP_c,6166
-dragon_ml_toolbox-12.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.3.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.3.0.dist-info/RECORD,,
+dragon_ml_toolbox-12.4.0.dist-info/METADATA,sha256=KylxsFKgAXRHl6A_0w3PXcevzLc_GnAtmR1SLRC4x8g,6166
+dragon_ml_toolbox-12.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-12.4.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-12.4.0.dist-info/RECORD,,

ml_tools/custom_logger.py

@@ -172,7 +172,7 @@ def load_list_strings(text_file: Union[str,Path], verbose: bool=True) -> list[st
         raise ValueError()
     
     if verbose:
-        _LOGGER.info(f"Text file loaded as list of strings.")
+        _LOGGER.info(f"Loaded '{target_path.name}' as list of strings.")
         
     return loaded_strings
 

ml_tools/data_exploration.py

@@ -891,7 +891,8 @@ def standardize_percentages(
     df: pd.DataFrame,
     columns: list[str],
     treat_one_as_proportion: bool = True,
-    round_digits: int = 2
+    round_digits: int = 2,
+    verbose: bool=True
 ) -> pd.DataFrame:
     """
     Standardizes numeric columns containing mixed-format percentages.
@@ -932,6 +933,8 @@ def standardize_percentages(
 
         # Otherwise, the value is assumed to be a correctly formatted percentage
         return x
+    
+    fixed_columns: list[str] = list()
 
     for col in columns:
         # --- Robustness Checks ---
@@ -949,6 +952,13 @@ def standardize_percentages(
 
         # Round the result
         df_copy[col] = df_copy[col].round(round_digits)
+        
+        fixed_columns.append(col)
+        
+    if verbose:
+        _LOGGER.info(f"Columns standardized:")
+        for fixed_col in fixed_columns:
+            print(f"  '{fixed_col}'")
 
     return df_copy