Update app.py

app.py

@@ -109,23 +109,23 @@ def load_models():
         models['xgboost'] = create_dummy_model("xgboost")
     
     # Try to load Linear Regression model
-    #try:
-    #    linear_path = hf_hub_download(
-    #        repo_id="Lesterchia174/HDB_Price_Predictor",
-    #        filename="linear_regression.joblib",
-    #        repo_type="space"
-    #    )
-    #    models['linear_regression'] = safe_joblib_load(linear_path)
-    #    if models['linear_regression'] is None:
-    #        print("⚠️  Creating dummy model for Linear Regression")
-    #        models['linear_regression'] = create_dummy_model("linear_regression")
-    #    else:
-    #        print("✅ Linear Regression model loaded and validated")
+    try:
+        linear_path = hf_hub_download(
+            repo_id="Lesterchia174/HDB_Price_Predictor",
+            filename="linear_regression.joblib",
+            repo_type="space"
+        )
+        models['linear_regression'] = safe_joblib_load(linear_path)
+        if models['linear_regression'] is None:
+            print("⚠️  Creating dummy model for Linear Regression")
+            models['linear_regression'] = create_dummy_model("linear_regression")
+        else:
+            print("✅ Linear Regression model loaded and validated")
             
-    #except Exception as e:
-    #    print(f"❌ Error downloading Linear Regression model: {e}")
-    #    print("⚠️  Creating dummy model for Linear Regression")
-    #    models['linear_regression'] = create_dummy_model("linear_regression")
+    except Exception as e:
+        print(f"❌ Error downloading Linear Regression model: {e}")
+        print("⚠️  Creating dummy model for Linear Regression")
+        models['linear_regression'] = create_dummy_model("linear_regression")
     
     return models
 
@@ -237,11 +237,11 @@ def create_market_insights_chart(data, user_input, predicted_price_xgb, predicte
                                              line=dict(width=2, color='darkred')),
                                  name='XGBoost Prediction'))
 
-        #fig.add_trace(go.Scatter(x=[user_input['floor_area_sqm']], y=[predicted_price_lr],
-        #                         mode='markers',
-        #                         marker=dict(symbol='diamond', size=20, color='blue',
-        #                                     line=dict(width=2, color='darkblue')),
-        #                         name='Linear Regression Prediction'))
+        fig.add_trace(go.Scatter(x=[user_input['floor_area_sqm']], y=[predicted_price_lr],
+                                 mode='markers',
+                                 marker=dict(symbol='diamond', size=20, color='blue',
+                                             line=dict(width=2, color='darkblue')),
+                                 name='Linear Regression Prediction'))
 
         fig.update_layout(template="plotly_white", height=400, showlegend=True)
         return fig
@@ -268,11 +268,11 @@ def predict_hdb_price(town, flat_type, flat_model, floor_area_sqm, storey_level,
             print(f"❌ XGBoost prediction error: {e}")
             predicted_price_xgb = 400000  # Fallback value
         
-        #try:
-        #    predicted_price_lr = max(0, float(models['linear_regression'].predict(processed_input)[0]))
-        #except Exception as e:
-        #    print(f"❌ Linear Regression prediction error: {e}")
-        #    predicted_price_lr = 380000  # Fallback value
+        try:
+            predicted_price_lr = max(0, float(models['linear_regression'].predict(processed_input)[0]))
+        except Exception as e:
+            print(f"❌ Linear Regression prediction error: {e}")
+            predicted_price_lr = 380000  # Fallback value
         
         # Use selected model's prediction
         if model_choice == "XGBoost":
@@ -299,8 +299,8 @@ def predict_hdb_price(town, flat_type, flat_model, floor_area_sqm, storey_level,
 
         **Model Predictions:**
         - XGBoost: ${predicted_price_xgb:,.0f}
-        #- Linear Regression: ${predicted_price_lr:,.0f}
-        #- Difference: ${abs(predicted_price_xgb - predicted_price_lr):,.0f}
+        - Linear Regression: ${predicted_price_lr:,.0f}
+        - Difference: ${abs(predicted_price_xgb - predicted_price_lr):,.0f}
 
         **Selected Model: {model_choice}**