dragon-ml-toolbox 20.11.0__py3-none-any.whl → 20.13.0__py3-none-any.whl

{dragon_ml_toolbox-20.11.0.dist-info → dragon_ml_toolbox-20.13.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.11.0
+Version: 20.13.0
 Summary: Complete pipelines and helper tools for data science and machine learning projects.
 Author-email: Karl Luigi Loza Vidaurre <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-20.11.0.dist-info → dragon_ml_toolbox-20.13.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-20.11.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-20.11.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-20.13.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-20.13.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/ETL_cleaning/__init__.py,sha256=gLRHF-qzwpqKTvbbn9chIQELeUDh_XGpBRX28j-5IqI,545
@@ -46,7 +46,7 @@ ml_tools/ML_evaluation/_loss.py,sha256=1a4O25i3Ya_3naNZNL7ELLUL46BY86g1scA7d7q2U
 ml_tools/ML_evaluation/_regression.py,sha256=UZA7_fg85ZKJQWszioWDtmkplSiXeHJk2fBYR5bRXHY,11225
 ml_tools/ML_evaluation/_sequence.py,sha256=gUk9Uvmy7MrXkfrriMnfypkgJU5XERHdqekTa2gBaOM,8004
 ml_tools/ML_evaluation/_vision.py,sha256=abBHQ6Z2GunHNusL3wcLgfI1FVNA6hBUBTq1eOA8FSA,11489
-ml_tools/ML_evaluation_captum/_ML_evaluation_captum.py,sha256=RMWkSmqHbb0Lj7W_uQJInEexOjXYmhMkcVHZT77wUrc,18847
+ml_tools/ML_evaluation_captum/_ML_evaluation_captum.py,sha256=eCP19o4sxfG0XlAVKiuuIxdtxO5lqCc0SuhWXx6eObY,20079
 ml_tools/ML_evaluation_captum/__init__.py,sha256=DZDoZXexCI49JNl_tTmFfYW4hTUYK5QQLex01wMfhnk,333
 ml_tools/ML_finalize_handler/_ML_finalize_handler.py,sha256=g-vkHJDTGXZsKOUA-Yfg7EuA1SmaHjzesCPiAyRMg2k,7054
 ml_tools/ML_finalize_handler/__init__.py,sha256=VQyLbCQUcliAAFiOAsnPhyJ7UVYgbSqAbAnpqeOnRSg,198
@@ -86,7 +86,7 @@ ml_tools/ML_trainer/__init__.py,sha256=42kueHa7Z0b_yLbywNCgIxlW6WmgLBqkTFwKH7vFL
 ml_tools/ML_trainer/_base_trainer.py,sha256=0ATm672NRsjJ6nv_NEl6-OEd9Bst1-s5OPxfG4qe8Lg,18075
 ml_tools/ML_trainer/_dragon_detection_trainer.py,sha256=B5F93PPnp2fYQmj1SYFRnAPVA39JwZUtJRMCdpSQF7k,16235
 ml_tools/ML_trainer/_dragon_sequence_trainer.py,sha256=Tj4YGgMrCkLnnNUlT_8wcdJFFcFhsdux308QPiqj-tw,23509
-ml_tools/ML_trainer/_dragon_trainer.py,sha256=bvSen_liut6B7gbg53MxOXKpJUkRaHtXDXW2SXBWPYQ,58553
+ml_tools/ML_trainer/_dragon_trainer.py,sha256=KLDLoUcCLIteoGtrLQDTbnD9Cf73V7TUiGT7CGSdeks,58574
 ml_tools/ML_utilities/__init__.py,sha256=71T3RDKDgHVvFrEr0G7tjuwbDVk_4JZGzwZtejC3PuE,739
 ml_tools/ML_utilities/_artifact_finder.py,sha256=X4xz_rmi0jVan8Sun_6431TcQiNM-GDHm-DHLA1zYms,15816
 ml_tools/ML_utilities/_inspection.py,sha256=mXTnjGmdDpBfY99xfekyrGbSvrWHBcVndivMbqPD4PI,13186
@@ -119,7 +119,7 @@ ml_tools/ensemble_learning/_ensemble_learning.py,sha256=MHDZBR20_nStlSSeThFI3bSu
 ml_tools/excel_handler/__init__.py,sha256=AaWM3n_dqBhJLTs3OEA57ex5YykKXNOwVCyHlVsdnqI,530
 ml_tools/excel_handler/_excel_handler.py,sha256=TODudmeQgDSdxUKzLfAzizs--VL-g8WxDOfQ4sgxxLs,13965
 ml_tools/keys/__init__.py,sha256=-0c2pmrhyfROc-oQpEjJGLBMhSagA3CyFijQaaqZRqU,399
-ml_tools/keys/_keys.py,sha256=Kr73o9SaH5Y3DT0z0H-1eLwlBplJmjisjoO_EoUNkAg,9388
+ml_tools/keys/_keys.py,sha256=YE_Ux2FYObfWurcQvfCvA3ZehwOvKvtCvIViUuYAYNM,9447
 ml_tools/math_utilities/__init__.py,sha256=K7Obkkc4rPKj4EbRZf1BsXHfiCg7FXYv_aN9Yc2Z_Vg,400
 ml_tools/math_utilities/_math_utilities.py,sha256=BYHIVcM9tuKIhVrkgLLiM5QalJ39zx7dXYy_M9aGgiM,9012
 ml_tools/optimization_tools/__init__.py,sha256=KD8JXpfGuPndO4AHnjJGu6uV1GRwhOfboD0KZV45kzw,658
@@ -143,7 +143,7 @@ ml_tools/utilities/__init__.py,sha256=h4lE3SQstg-opcQj6QSKhu-HkqSbmHExsWoM9vC5D9
 ml_tools/utilities/_translate.py,sha256=U8hRPa3PmTpIf9n9yR3gBGmp_hkcsjQLwjAHSHc0WHs,10325
 ml_tools/utilities/_utility_save_load.py,sha256=EFvFaTaHahDQWdJWZr-j7cHqRbG_Xrpc96228JhV-bs,16773
 ml_tools/utilities/_utility_tools.py,sha256=bN0J9d1S0W5wNzNntBWqDsJcEAK7-1OgQg3X2fwXns0,6918
-dragon_ml_toolbox-20.11.0.dist-info/METADATA,sha256=KiKepG9k7M1RbCXxEutcr7EkvDPaWIRiKoSvrTR1HSw,7889
-dragon_ml_toolbox-20.11.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-20.11.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-20.11.0.dist-info/RECORD,,
+dragon_ml_toolbox-20.13.0.dist-info/METADATA,sha256=bTnTpMlvOFu2IlYpmc0QphbYeqbslxzptluUbEWaO-s,7889
+dragon_ml_toolbox-20.13.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+dragon_ml_toolbox-20.13.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-20.13.0.dist-info/RECORD,,

{dragon_ml_toolbox-20.11.0.dist-info → dragon_ml_toolbox-20.13.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

ml_tools/ML_evaluation_captum/_ML_evaluation_captum.py

@@ -30,7 +30,8 @@ def captum_feature_importance(model: nn.Module,
                               save_dir: Union[str, Path],
                               target_names: Optional[list[str]] = None,
                               n_steps: int = 50,
-                              device: Union[str, torch.device] = 'cpu'):
+                              device: Union[str, torch.device] = 'cpu',
+                              verbose: int = 0):
     """
     Calculates feature importance using Captum's Integrated Gradients.
 
@@ -49,7 +50,7 @@ def captum_feature_importance(model: nn.Module,
             - If `None`, generic names (e.g., "Output_0") will be generated based on model output shape.
         n_steps (int): Number of steps for the integral approximation. Higher means more accurate but slower.
         device (str | torch.device): Torch device.
-        
+        verbose (int): Verbosity level.
     <br>
         
     ### NOTE: 
@@ -127,7 +128,8 @@ def captum_feature_importance(model: nn.Module,
             save_dir=save_dir_path,
             n_steps=n_steps,
             file_suffix=f"_{clean_name}",
-            target_name=name  # Pass original name for plotting
+            target_name=name,  # Pass original name for plotting
+            verbose=verbose
         )
 
 
@@ -139,7 +141,8 @@ def _process_single_target(ig: 'IntegratedGradients', # type: ignore
                            save_dir: Path,
                            n_steps: int,
                            file_suffix: str,
-                           target_name: str = ""):
+                           target_name: str = "",
+                           verbose: int = 0):
     """
     Private helper to run the attribution, aggregation, and saving for a single context.
     """
@@ -153,8 +156,8 @@ def _process_single_target(ig: 'IntegratedGradients', # type: ignore
                                            return_convergence_delta=True)
         # Check convergence quality
         mean_delta = torch.mean(torch.abs(delta)).item()
-        if mean_delta > 0.1:
-            _LOGGER.warning(f"Captum Convergence Delta is high ({mean_delta:.4f}). The attribution approximation may be inaccurate. Consider increasing 'n_steps'.")
+        if mean_delta > 0.1 and verbose > 0:
+            _LOGGER.warning(f"Captum Convergence Delta is high ({mean_delta:.4f}). Consider increasing 'n_steps'.")
         
     except Exception as e:
         _LOGGER.error(f"Captum attribution failed for target '{target_index}': {e}")
@@ -198,11 +201,36 @@ def _process_single_target(ig: 'IntegratedGradients', # type: ignore
         min_len = min(len(mean_abs_attr), len(feature_names))
         mean_abs_attr = mean_abs_attr[:min_len]
         feature_names = feature_names[:min_len]
+    
+    # Calculate percentages (Before Min-Max scaling to preserve relative importance)
+    total_attr_sum = np.sum(mean_abs_attr)
+    if total_attr_sum > 0:
+        attr_percentages = (mean_abs_attr / total_attr_sum) * 100.0
+    else:
+        attr_percentages = np.zeros_like(mean_abs_attr)
+    
+    # Min-Max Scaling
+    target_min = 0.01
+    target_max = 1.0
+    
+    _min = np.min(mean_abs_attr)
+    _max = np.max(mean_abs_attr)
+    
+    if _max > _min:
+        # 1. Normalize to [0, 1]
+        mean_abs_attr = (mean_abs_attr - _min) / (_max - _min)
+        # 2. Scale to [target_min, target_max]
+        mean_abs_attr = mean_abs_attr * (target_max - target_min) + target_min
+    else:
+        # Fallback: if all values are identical (e.g. all 0.0), set to target_min
+        fill_val = target_min if _max == 0 else target_max
+        mean_abs_attr = np.full_like(mean_abs_attr, fill_val)
 
     # --- Save Data to CSV ---
     summary_df = pd.DataFrame({
         CaptumKeys.FEATURE_COLUMN: feature_names,
-        CaptumKeys.IMPORTANCE_COLUMN: mean_abs_attr
+        CaptumKeys.IMPORTANCE_COLUMN: mean_abs_attr,
+        CaptumKeys.PERCENT_COLUMN: attr_percentages
     }).sort_values(CaptumKeys.IMPORTANCE_COLUMN, ascending=False)
     
     csv_name = f"{CaptumKeys.SAVENAME}{file_suffix}.csv"
@@ -210,10 +238,13 @@ def _process_single_target(ig: 'IntegratedGradients', # type: ignore
     summary_df.to_csv(csv_path, index=False)
 
     # --- Generate Plot ---
-    plot_df = summary_df.head(20).sort_values(CaptumKeys.IMPORTANCE_COLUMN, ascending=True)
-    plt.figure(figsize=(10, 8), dpi=200)
-    plt.barh(plot_df[CaptumKeys.FEATURE_COLUMN], plot_df[CaptumKeys.IMPORTANCE_COLUMN], color='mediumpurple')
-    plt.xlabel("Mean Absolute Attribution")
+    plot_df = summary_df.head(20).sort_values(CaptumKeys.PERCENT_COLUMN, ascending=True)
+    plt.figure(figsize=(10, 8), dpi=300)
+    plt.barh(plot_df[CaptumKeys.FEATURE_COLUMN], plot_df[CaptumKeys.PERCENT_COLUMN], color='mediumpurple')
+    # plt.xlim(0, 1.05) # standardized scale # Removed to reflect actual percentages
+    plt.xlim(left=0) # start at 0
+    # plt.xlabel("Scaled Mean Absolute Attribution")
+    plt.xlabel("Relative Importance (%)")
     
     title = "Feature Importance"
     

ml_tools/ML_trainer/_dragon_trainer.py

@@ -33,8 +33,7 @@ from ..ML_configuration import (FormatRegressionMetrics,
                             FinalizeMultiTargetRegression,
                             FinalizeRegression)
 
-from ..path_manager import make_fullpath
-from ..keys._keys import PyTorchLogKeys, PyTorchCheckpointKeys, DatasetKeys, MLTaskKeys, MagicWords, DragonTrainerKeys, ScalerKeys
+from ..keys._keys import PyTorchLogKeys, PyTorchCheckpointKeys, DatasetKeys, MLTaskKeys, DragonTrainerKeys, ScalerKeys
 from .._core import get_logger
 
 from ._base_trainer import _BaseDragonTrainer
@@ -824,7 +823,8 @@ class DragonTrainer(_BaseDragonTrainer):
                        n_samples: int = 100,
                        feature_names: Optional[list[str]] = None,
                        target_names: Optional[list[str]] = None,
-                       n_steps: int = 50):
+                       n_steps: int = 50,
+                       verbose: int = 0):
         """
         Explains model predictions using Captum's Integrated Gradients.
         
@@ -927,7 +927,8 @@ class DragonTrainer(_BaseDragonTrainer):
                 save_dir=save_dir,
                 target_names=target_names,
                 n_steps=n_steps,
-                device=self.device
+                device=self.device,
+                verbose=verbose
             )
 
     def _attention_helper(self, dataloader: DataLoader):

ml_tools/keys/_keys.py

@@ -99,8 +99,9 @@ class SHAPKeys:
 
 class CaptumKeys:
     """Keys for Captum functions"""
-    FEATURE_COLUMN = "feature"
-    IMPORTANCE_COLUMN = "importance"
+    FEATURE_COLUMN = "Feature"
+    IMPORTANCE_COLUMN = "Scaled Mean Attribution"
+    PERCENT_COLUMN = "Relative Importance(%)"
     SAVENAME = "captum_summary"
     PLOT_NAME = "captum_importance_plot"