PR curves working as expected. Need to analyze efficiency of doing cv twice

model_selection/cv_metric_gen.py

@@ -236,9 +236,9 @@ if __name__ == "__main__":
                     mean_precision = np.mean(precisions, axis=0)
                     mean_pr_auc = np.mean(pr_aucs)
                     axes[model_idx][1].plot(mean_recall, mean_precision, color='b', lw=4, label=r'Mean PR (AUC = %0.2f)' % mean_pr_auc, alpha=.8)
-                    # # Plot baseline precision (proportion of positive samples)
-                    # baseline = np.sum(y_train) / len(y_train)
-                    # axes[model_idx][1].plot([0, 1], [baseline, baseline], linestyle='--', lw=2, color='r', alpha=.8, label='Baseline')
+                    # Plot baseline precision (proportion of positive samples)
+                    baseline = np.sum(y_train) / len(y_train)
+                    axes[model_idx][1].plot([0, 1], [baseline, baseline], linestyle='--', lw=2, color='r', alpha=.8, label='Baseline')
                     # Set Precision-Recall plot limits and title
                     axes[model_idx][1].set(xlim=[-0.05, 1.05], ylim=[-0.05, 1.05], title=f"Precision-Recall Curve - {model_name} ({group}-{method_names[j]})")
                     axes[model_idx][1].legend(loc="lower right")