gitlabds 2.1.6__tar.gz → 2.1.7__tar.gz

{gitlabds-2.1.6 → gitlabds-2.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gitlabds
-Version: 2.1.6
+Version: 2.1.7
 Summary: Gitlab Data Science and Modeling Tools
 Home-page: https://gitlab.com/gitlab-data/gitlabds
 Author: Kevin Dietz

{gitlabds-2.1.6 → gitlabds-2.1.7}/gitlabds/model_evaluator.py

@@ -1938,7 +1938,6 @@ class ModelEvaluator:
                     ax.set_yticks([])
                     ax.set_title(f"Class {class_idx}")
 
-
     def plot_shap_beeswarm(
         self,
         n_features: int = 20,
@@ -1954,6 +1953,13 @@ class ModelEvaluator:
     ) -> None:
         """
         Create a SHAP beeswarm plot for feature importance.
+        
+        Parameters
+        ----------
+        class_index : int, optional
+            For multi-class classification, specify which class to plot.
+            If None, plots global importance (averaged across classes).
+            Only applicable for multi-class models.
         """
         # Set defaults if not provided
         save_plot = self.save_plots if save_plot is None else save_plot
@@ -1986,33 +1992,62 @@ class ModelEvaluator:
             # Get SHAP values
             shap_values = explainer(X)
             
-            # For multi-class classification - create a global view
+            # For multi-class classification
             if self.classification and self.n_classes > 2:
-                # For multi-class, we need to create a 2D representation for beeswarm
                 if hasattr(shap_values, 'values') and len(shap_values.values.shape) == 3:
-                    # Create global explanation by taking the mean across the class dimension
-                    global_values = shap_values.values.mean(axis=2)
-                    global_exp = shap.Explanation(
-                        values=global_values,
-                        data=X.values,
-                        feature_names=X.columns.tolist()
-                    )
-                    
-                    # Create a figure first
-                    plt.figure(figsize=(12, 8))
-                    
-                    # Use the global explanation for plotting
-                    if plot_type == "beeswarm":
-                        shap.plots.beeswarm(global_exp, max_display=n_features, show=False)
+                    # Validate class_index if provided
+                    if class_index is not None:
+                        if not isinstance(class_index, int) or class_index < 0 or class_index >= self.n_classes:
+                            logger.warning(f"Invalid class_index {class_index}. Must be integer between 0 and {self.n_classes-1}. Using global view.")
+                            class_index = None
+                    
+                    if class_index is not None:
+                        # Plot for specific class
+                        class_values = shap_values.values[:, :, class_index]
+                        class_exp = shap.Explanation(
+                            values=class_values,
+                            data=X.values,
+                            feature_names=X.columns.tolist()
+                        )
+                        
+                        # Create a figure first
+                        plt.figure(figsize=(12, 8))
+                        
+                        # Use the class-specific explanation for plotting
+                        if plot_type == "beeswarm":
+                            shap.plots.beeswarm(class_exp, max_display=n_features, show=False)
+                        else:
+                            shap.plots.bar(class_exp, max_display=n_features, show=False)
+                        
+                        plt.title(f"SHAP Values for Class {class_index} ({dataset.title()} Data)")
+                        
                     else:
-                        shap.plots.bar(global_exp, max_display=n_features, show=False)
-                    
-                    plt.title(f"SHAP Values ({dataset.title()} Data)")
+                        # Create global explanation by taking the mean across the class dimension
+                        global_values = shap_values.values.mean(axis=2)
+                        global_exp = shap.Explanation(
+                            values=global_values,
+                            data=X.values,
+                            feature_names=X.columns.tolist()
+                        )
+                        
+                        # Create a figure first
+                        plt.figure(figsize=(12, 8))
+                        
+                        # Use the global explanation for plotting
+                        if plot_type == "beeswarm":
+                            shap.plots.beeswarm(global_exp, max_display=n_features, show=False)
+                        else:
+                            shap.plots.bar(global_exp, max_display=n_features, show=False)
+                        
+                        plt.title(f"SHAP Values - Global View ({dataset.title()} Data)")
                     
-                    # Handle saving
+                    # Handle saving and showing
                     if save_plot:
                         os.makedirs(plot_dir, exist_ok=True)
-                        save_path = os.path.join(plot_dir, f"{plot_name}.{plot_save_format}")
+                        if class_index is not None:
+                            save_path = os.path.join(plot_dir, f"{plot_name}_class_{class_index}.{plot_save_format}")
+                        else:
+                            save_path = os.path.join(plot_dir, f"{plot_name}.{plot_save_format}")
                         plt.savefig(save_path, format=plot_save_format, dpi=plot_save_dpi, bbox_inches="tight")
                     
                     # Show or close
@@ -2024,10 +2059,15 @@ class ModelEvaluator:
                     return
                 else:
                     # If the SHAP values don't have the expected format
+                    if class_index is not None:
+                        logger.warning("Multi-class SHAP values don't have expected format for class-specific plotting. Using global view.")
                     logger.warning("Multi-class SHAP values don't have expected format. Unable to create beeswarm plot.")
                     return
             
             # Binary classification or regression - use the original behavior
+            if class_index is not None:
+                logger.warning(f"class_index parameter ignored for {('binary classification' if self.classification else 'regression')} model.")
+            
             # Create a figure first
             plt.figure(figsize=(12, 8))
             
@@ -2056,6 +2096,8 @@ class ModelEvaluator:
             print(f"Error: {str(e)}")
 
 
+
+
     def plot_score_distribution(
         self,
         bins=None,

{gitlabds-2.1.6 → gitlabds-2.1.7}/gitlabds.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gitlabds
-Version: 2.1.6
+Version: 2.1.7
 Summary: Gitlab Data Science and Modeling Tools
 Home-page: https://gitlab.com/gitlab-data/gitlabds
 Author: Kevin Dietz