dragon-ml-toolbox 20.12.0__tar.gz → 20.13.0__tar.gz

{dragon_ml_toolbox-20.12.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-20.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.12.0
+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-20.12.0 → dragon_ml_toolbox-20.13.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.12.0
+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-20.12.0 → dragon_ml_toolbox-20.13.0}/ml_tools/ML_evaluation_captum/_ML_evaluation_captum.py

@@ -202,6 +202,13 @@ def _process_single_target(ig: 'IntegratedGradients', # type: ignore
         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
@@ -222,7 +229,8 @@ def _process_single_target(ig: 'IntegratedGradients', # type: ignore
     # --- 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"
@@ -230,11 +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)
+    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.IMPORTANCE_COLUMN], color='mediumpurple')
-    plt.xlim(0, 1.05) # standardized scale
-    plt.xlabel("Mean Absolute Attribution")
+    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"
     

{dragon_ml_toolbox-20.12.0 → dragon_ml_toolbox-20.13.0}/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"
 

{dragon_ml_toolbox-20.12.0 → dragon_ml_toolbox-20.13.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "20.12.0"
+version = "20.13.0"
 description = "Complete pipelines and helper tools for data science and machine learning projects."
 authors = [
     { name = "Karl Luigi Loza Vidaurre", email = "luigiloza@gmail.com" }