Update app.py

app.py

@@ -89,22 +89,21 @@ def calculate_shap_values(model, x_tensor):
     model.eval()
     device = next(model.parameters()).device
     
-    # Create a background dataset (baseline) with a sufficient number of samples
-    background = np.zeros((300, x_tensor.shape[1]))
-    
     try:
-        # Try using DeepExplainer (efficient for neural networks)
+        # Create background as a torch tensor instead of a numpy array
+        background = torch.zeros((300, x_tensor.shape[1]), device=device)
+        
+        # Use DeepExplainer with the torch tensor background
         explainer = shap.DeepExplainer(model, background)
-        # Calculate SHAP values using DeepExplainer
         shap_values_all = explainer.shap_values(x_tensor)
+        
         # Get SHAP values for human class (index 1)
         shap_values = shap_values_all[1][0]
     except Exception as e:
         print(f"DeepExplainer failed, falling back to KernelExplainer: {str(e)}")
         
-        # Define a wrapper function to ensure proper input shape
+        # Define a wrapper that converts inputs to proper shape and tensor
         def model_predict(x):
-            # Ensure x is a numpy array and has at least 2 dimensions
             if not isinstance(x, np.ndarray):
                 x = np.array(x)
             if x.ndim == 1:
@@ -115,10 +114,9 @@ def calculate_shap_values(model, x_tensor):
                 probs = torch.softmax(output, dim=1)[:, 1]  # Human probability
                 return probs.cpu().numpy()
         
-        # Re-create a larger background for KernelExplainer if needed
+        # Use a numpy background for KernelExplainer
         background = np.zeros((300, x_tensor.shape[1]))
         
-        # Use KernelExplainer as fallback
         explainer = shap.KernelExplainer(model_predict, background)
         x_numpy = x_tensor.cpu().numpy()
         shap_values = explainer.shap_values(x_numpy, nsamples=100)