update optimization

app.py

@@ -121,7 +121,7 @@ def _bar_for_models(results: dict):
 
 def run_predict(*vals):
     if STATE["df"] is None or STATE["models"] is None:
-        return "❌ Models not initialized. Reload the app.", None, "", pd.DataFrame()
+        return None, "❌ Models not initialized. Reload the app.", pd.DataFrame()
 
     input_dict = {col: vals[i] for i, col in enumerate(CLEVELAND_FEATURES_ORDER)}
     results = predict_all(STATE["models"], input_dict)
@@ -257,7 +257,7 @@ with gr.Blocks(theme="gstaff/sketch", css=vlai_template.custom_css, fill_width=T
       - k-NN: distance weighting, Manhattan metric, optimized neighbors
       - Random Forest: 200 trees, class balancing, feature sampling
       - Gradient Boosting: regularization, subsampling, lower learning rate
-      - AdaBoost: SAMME.R algorithm, increased estimators
+      - AdaBoost: SAMME algorithm, increased estimators
       - XGBoost: L1/L2 regularization, optimal depth and learning rate
     - **Feature descriptions**:
       - `age`: Patient age in years

src/heart_disease_core.py

@@ -189,7 +189,7 @@ def build_models() -> Dict[str, Pipeline]:
             random_state=42,
             n_estimators=150,      # More estimators
             learning_rate=0.8,     # Slower learning for stability
-            algorithm="SAMME.R"    # Probability-based boosting
+            algorithm="SAMME"      # Compatible algorithm for newer sklearn
         ))
     ])
 
@@ -241,7 +241,7 @@ def build_models() -> Dict[str, Pipeline]:
         ("rf", RandomForestClassifier(random_state=42, n_estimators=200, max_depth=10, 
                                     min_samples_split=5, min_samples_leaf=2, max_features="sqrt", 
                                     class_weight="balanced", n_jobs=-1)),
-        ("ada", AdaBoostClassifier(random_state=42, n_estimators=150, learning_rate=0.8, algorithm="SAMME.R")),
+        ("ada", AdaBoostClassifier(random_state=42, n_estimators=150, learning_rate=0.8, algorithm="SAMME")),
         ("gb", GradientBoostingClassifier(random_state=42, n_estimators=150, learning_rate=0.08, 
                                         max_depth=4, min_samples_split=10, min_samples_leaf=4, 
                                         subsample=0.8, max_features="sqrt")),