dragon-ml-toolbox 12.7.0__py3-none-any.whl → 12.8.0__py3-none-any.whl

{dragon_ml_toolbox-12.7.0.dist-info → dragon_ml_toolbox-12.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.7.0
+Version: 12.8.0
 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-12.7.0.dist-info → dragon_ml_toolbox-12.8.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-12.7.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.7.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-12.8.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-12.8.0.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
@@ -14,7 +14,7 @@ ml_tools/ML_optimization.py,sha256=es3TlQbY7RYgJMZnznkjYGbUxFnAqzZxE_g3_qLK9Q8,2
 ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
 ml_tools/ML_simple_optimization.py,sha256=W2mce1XFCuiOHTOjOsCNbETISHn5MwYlYsTIXH5hMMo,18177
 ml_tools/ML_trainer.py,sha256=_g48w5Ak-wQr5fGHdJqlcpnzv3gWyL1ghkOhy9VOZbo,23930
-ml_tools/ML_utilities.py,sha256=35DfZzAwfDwVwfRECD8X_2ynsU2NCpTdNJSmza6oAzQ,8712
+ml_tools/ML_utilities.py,sha256=EnKpPTnJ2qjZmz7kvows4Uu5CfSA7ByRmI1v2-KarKw,9337
 ml_tools/PSO_optimization.py,sha256=fVHeemqilBS0zrGV25E5yKwDlGdd2ZKa18d8CZ6Q6Fk,22961
 ml_tools/RNN_forecast.py,sha256=Qa2KoZfdAvSjZ4yE78N4BFXtr3tTr0Gx7tQJZPotsh0,1967
 ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
@@ -24,18 +24,18 @@ 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=xot-VeZFigKjcVxADgzvI54vZO_MqMMejo7JmDED8Xo,5892
-ml_tools/data_exploration.py,sha256=xvuWHrxk5HOtY7_WmtXEUNf1d_TUxuNPFPFyN7QJxCY,46836
+ml_tools/data_exploration.py,sha256=joaJPgXeweYMAn-xnMOzUIE8VvKvbEPenVjVHM21U4c,46914
 ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 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=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
 ml_tools/math_utilities.py,sha256=PxoOrnuj6Ntp7_TJqyDWi0JX03WpAO5iaFNK2Oeq5I4,8800
-ml_tools/optimization_tools.py,sha256=ewYMAdSGlFxYALAGFXn-MsHpvW_Sbx6I-sKg9Kp6rB8,13533
+ml_tools/optimization_tools.py,sha256=P074YCuZzkqkONnAsM-Zb9DTX_i8cRkkJLpwAWz6CRw,13521
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
 ml_tools/serde.py,sha256=UIshIesHRFmxr8F6B3LxGG8bYc1HHK-nlE3kENSZL18,5288
 ml_tools/utilities.py,sha256=OcAyV1tEcYAfOWlGjRgopsjDLxU3DcI5EynzvWV4q3A,15754
-dragon_ml_toolbox-12.7.0.dist-info/METADATA,sha256=Ek5m6-ExduWUlSvDJ26AYySjU5aILoyiUVlP5dDYWyY,6166
-dragon_ml_toolbox-12.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.7.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.7.0.dist-info/RECORD,,
+dragon_ml_toolbox-12.8.0.dist-info/METADATA,sha256=zbA_0bdkX_96eSpkx7QGZelCTKrckDXUdvmHE4oCNMI,6166
+dragon_ml_toolbox-12.8.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-12.8.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-12.8.0.dist-info/RECORD,,

ml_tools/ML_utilities.py

@@ -1,12 +1,13 @@
 import pandas as pd
 from pathlib import Path
-from typing import Union, Any
+from typing import Union, Any, Optional
 
 from .path_manager import make_fullpath, list_subdirectories, list_files_by_extension
 from ._script_info import _script_info
 from ._logger import _LOGGER
 from .keys import DatasetKeys, PytorchModelArchitectureKeys, PytorchArtifactPathKeys, SHAPKeys
 from .utilities import load_dataframe
+from .custom_logger import save_list_strings
 
 
 __all__ = [
@@ -139,6 +140,7 @@ def find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool, v
 def select_features_by_shap(
     root_directory: Union[str, Path],
     shap_threshold: float,
+    log_feature_names_directory: Optional[Union[str, Path]],
     verbose: bool = True) -> list[str]:
     """
     Scans subdirectories to find SHAP summary CSVs, then extracts feature
@@ -148,11 +150,13 @@ def select_features_by_shap(
     importance scores aggregated from multiple models.
 
     Args:
-        root_directory (Union[str, Path]):
+        root_directory (str | Path):
             The path to the root directory that contains model subdirectories.
         shap_threshold (float):
             The minimum mean absolute SHAP value for a feature to be included
             in the final list.
+        log_feature_names_directory (str | Path | None):
+            If given, saves the chosen feature names as a .txt file in this directory.
 
     Returns:
         list[str]:
@@ -211,6 +215,13 @@ def select_features_by_shap(
     final_features = sorted(list(master_feature_set))
     if verbose:
         _LOGGER.info(f"Selected {len(final_features)} unique features across all files.")
+        
+    if log_feature_names_directory is not None:
+        save_names_path = make_fullpath(log_feature_names_directory, make=True, enforce="directory")
+        save_list_strings(list_strings=final_features,
+                          directory=save_names_path,
+                          filename=DatasetKeys.FEATURE_NAMES,
+                          verbose=verbose)
     
     return final_features
 

ml_tools/data_exploration.py

@@ -362,6 +362,7 @@ def encode_categorical_features(
         encode_nulls (bool): If True, encodes Null values as a distinct category
             "Other" with a value of 0. Other categories start from 1. 
             If False, Nulls are ignored and categories start from 0.
+            Note: Use False when encoding binary values with missing entries.
         split_resulting_dataset (bool): If True, returns two separate DataFrames:
             one with non-categorical columns and one with the encoded columns.
             If False, returns a single DataFrame with all columns.

ml_tools/optimization_tools.py

@@ -98,7 +98,7 @@ def create_optimization_bounds(
 
     # 3. Populate categorical bounds (Index-based)
     # The indices in categorical_map (e.g., {2: 4}) directly correspond
-    # to the indices in our new `feature_names` list.
+    # to the indices in the `feature_names` list.
     for index, cardinality in categorical_map.items():
         if not (0 <= index < total_features):
             _LOGGER.error(f"Categorical index {index} is out of range for the {total_features} features.")
@@ -125,8 +125,8 @@ def create_optimization_bounds(
             # Map name to its index in the *feature-only* list
             index = feature_names.index(name)
         except ValueError:
-            _LOGGER.error(f"Feature name '{name}' from 'continuous_bounds_map' not found in the CSV's feature columns.")
-            raise ValueError()
+            _LOGGER.warning(f"Feature name '{name}' from 'continuous_bounds_map' not found in the CSV's feature columns.")
+            continue
             
         if lower_bounds[index] is not None:
             # This index was already set by the categorical map