Update src/streamlit_app.py

src/streamlit_app.py

@@ -555,18 +555,39 @@ with tabs[4]:
                     max_depth=trial.suggest_int("max_depth", 4, 30),
                     random_state=42, n_jobs=-1)
             else:
+                # fallback
                 m = RandomForestRegressor(random_state=42)
+    
             try:
                 return np.mean(cross_val_score(m, X_local, y_local, cv=3, scoring="r2"))
             except Exception:
                 return -999.0
-
+    
+        # --- Run Optuna optimization ---
         study = optuna.create_study(direction="maximize")
-        study.optimize(obj, n_trials=n_trials, show_progress_bar=False)
-        params = study.best_trial.params if study.trials else {}
+        try:
+            study.optimize(obj, n_trials=n_trials, show_progress_bar=False)
+            params = study.best_trial.params if study.trials else {}
+            best_score = study.best_value if study.trials else -999.0
+        except Exception as e:
+            st.warning(f"Optuna failed for {fam}: {e}")
+            params, best_score = {}, -999.0
+    
+        # --- Always safely initialize a model, even if trials failed ---
         if fam == "RandomForest":
-            model = RandomForestRegressor(**study.best_trial.params, random_state=42)
-        return {"family": fam, "model_obj": model, "best_params": params, "cv_score": study.best_value}
+            model = RandomForestRegressor(**params, random_state=42, n_jobs=-1)
+        elif fam == "ExtraTrees":
+            model = ExtraTreesRegressor(**params, random_state=42, n_jobs=-1)
+        else:
+            model = RandomForestRegressor(random_state=42, n_jobs=-1)
+    
+        return {
+            "family": fam,
+            "model_obj": model,
+            "best_params": params,
+            "cv_score": best_score
+        }
+
 
     # --- Run button ---
     if st.button("Run AutoML + SHAP"):