Update app.py

app.py

@@ -93,35 +93,36 @@ outputs = [gr.Dataframe(
     #})
 
 def infer(inputs):
+    # Create DataFrame from inputs
     data = pd.DataFrame(inputs, columns=headers)
     
-    # Store the Name column first, before any processing
-    names = data['Name'].copy()
+    # Create a copy of the input DataFrame to preserve original data
+    prediction_data = data.copy()
     
-    # Replace empty strings with NaN
-    data = data.replace('', np.nan)
+    # Replace empty strings with NaN for numeric columns only
+    numeric_columns = [col for col in all_headers if col != 'Name']
+    prediction_data[numeric_columns] = prediction_data[numeric_columns].replace('', np.nan)
     
     # Add missing columns with default values
     for col in all_headers:
-        if col not in data.columns:
-            data[col] = 0
+        if col not in prediction_data.columns:
+            prediction_data[col] = 0
     
     # Ensure the order of columns matches the training data
-    data = data[all_headers]
+    prediction_data = prediction_data[all_headers]
     
-    # Fill NaN values
-    data = data.fillna(0)
+    # Fill NaN values in numeric columns only
+    prediction_data[numeric_columns] = prediction_data[numeric_columns].fillna(0)
     
-    # Convert numeric columns to float, excluding 'Name'
-    numeric_columns = [col for col in all_headers if col != 'Name']
-    data[numeric_columns] = data[numeric_columns].astype(float)
+    # Convert numeric columns to float
+    prediction_data[numeric_columns] = prediction_data[numeric_columns].astype(float)
     
     # Make predictions
-    predictions = pipe.predict(data)
+    predictions = pipe.predict(prediction_data)
     
-    # Create output DataFrame with stored names and predictions
+    # Create output DataFrame using original names
     return pd.DataFrame({
-        'Name': names,
+        'Name': data['Name'],
         'Depression': predictions
     })