Update app.py

app.py

@@ -15,12 +15,11 @@ logger = logging.getLogger(__name__)
 # Initialize model components
 model = None
 scaler = None
-metadata = {}
 feature_names = []
 model_loaded = False
 
 def load_model():
-    global model, scaler, metadata, feature_names, model_loaded
+    global model, scaler, feature_names, model_loaded
     
     try:
         # Verify all required files exist
@@ -44,7 +43,7 @@ def load_model():
         logger.info("Loading metadata...")
         with open('metadata.json', 'r') as f:
             metadata = json.load(f)
-            feature_names = metadata.get('feature_names', [])
+            feature_names = metadata.get('feature_names', ['Score 1', 'Score 2'])  # Default names
             
         model_loaded = True
         logger.info("✅ Model loaded successfully!")
@@ -52,6 +51,7 @@ def load_model():
         
     except Exception as e:
         logger.error(f"❌ Model loading failed: {str(e)}")
+        feature_names = ['Score 1', 'Score 2']  # Default names if loading fails
         model_loaded = False
 
 # Load model at startup
@@ -84,15 +84,11 @@ def predict(*args):
         prediction = "Eligible" if probability > 0.5 else "Not Eligible"
         confidence = abs(probability - 0.5) * 2
         
-        return {
-            "Prediction": prediction,
-            "Probability": f"{probability:.4f}",
-            "Confidence": f"{confidence:.4f}"
-        }
+        return prediction, f"{probability:.4f}", f"{confidence:.4f}"
         
     except Exception as e:
         logger.error(f"Prediction error: {str(e)}")
-        return {"Error": str(e)}
+        return f"Error: {str(e)}", "N/A", "N/A"
 
 # Create Gradio interface
 with gr.Blocks(title="Student Eligibility Predictor") as demo:
@@ -101,34 +97,36 @@ with gr.Blocks(title="Student Eligibility Predictor") as demo:
     
     with gr.Row():
         with gr.Column():
-            input_components = [gr.Number(label=name) for name in feature_names]
+            # Create input components based on actual features
+            inputs = []
+            for feature in feature_names:
+                inputs.append(gr.Number(label=feature, value=75))
+            
             predict_btn = gr.Button("Predict", variant="primary")
+            
         with gr.Column():
             prediction_output = gr.Textbox(label="Prediction")
             probability_output = gr.Textbox(label="Probability")
             confidence_output = gr.Textbox(label="Confidence")
     
-    # Add examples if features exist
-    if len(feature_names) > 0:
-        examples = []
-        if len(feature_names) >= 3:
-            examples.append([75, 80, 85] + [0]*(len(feature_names)-3))
-        elif len(feature_names) == 2:
-            examples.append([75, 80])
-        else:
-            examples.append([75])
-        
-        gr.Examples(
-            examples=examples,
-            inputs=input_components,
-            outputs=[prediction_output, probability_output, confidence_output],
-            fn=predict,
-            cache_examples=False
-        )
+    # Setup examples
+    examples = []
+    if len(feature_names) >= 2:
+        examples = [[75, 80]]  # Basic example with two features
+    else:
+        examples = [[75]]  # Fallback example
+    
+    gr.Examples(
+        examples=examples,
+        inputs=inputs,
+        outputs=[prediction_output, probability_output, confidence_output],
+        fn=predict,
+        cache_examples=False
+    )
     
     predict_btn.click(
         fn=predict,
-        inputs=input_components,
+        inputs=inputs,
         outputs=[prediction_output, probability_output, confidence_output]
     )