Update app.py

app.py

@@ -31,8 +31,10 @@ except Exception as e:
 
 # Define all_traits dictionary (needed for preprocessing)
 all_traits = {
-    'Interests': set(['Reading', 'Dancing', 'Physics', 'Research', 'Cooking', 'Art', 'Playing Football', 'Creativity', 'Writing']),
-    'Strengths': set(['Communication', 'Creativity', 'Logical Reasoning', 'Innovative Thinking', 'Teamwork', 'Hands-on Skills', 'Analytical Thinking'])
+    'Interests': set(['Reading', 'Dancing', 'Physics', 'Research', 'Cooking', 'Art', 'Playing Football', 'Creativity', 'Writing',
+                     'Technology', 'Public Speaking', 'Music', 'Mathematics', 'Leadership', 'Problem-Solving', 'Entrepreneurship']),
+    'Strengths': set(['Communication', 'Creativity', 'Logical Reasoning', 'Innovative Thinking', 'Teamwork', 'Hands-on Skills', 
+                     'Analytical Thinking', 'Leadership', 'Detail-Oriented'])
 }
 
 # Function to convert grades to numerical values
@@ -93,7 +95,9 @@ def prepare_model_data(processed_df):
     # Identify categorical and numerical features
     categorical_features = ["Desired_Career"]
     numerical_features = ["Aggregate", "English", "Core Maths", "Science", "Social Studies",
-                          "Physics", "Biology", "Elective Maths", "Chemistry"]
+                          "Physics", "Biology", "Elective Maths", "Chemistry",
+                          "Economics", "E-ICT", "Literature", "Geography", 
+                          "Business Management", "Visual Arts", "Government"]
 
     # Add the binary interest and strength columns
     interest_strength_cols = [col for col in processed_df.columns if col.startswith('interest_') or col.startswith('strength_')]
@@ -102,6 +106,9 @@ def prepare_model_data(processed_df):
     for col in numerical_features:
         if col in processed_df.columns:  # Check if column exists
             processed_df[col] = processed_df[col].apply(grade_to_numeric)
+        else:
+            # Add missing columns with NaN values
+            processed_df[col] = np.nan
 
     # Get features (using processed_df with numerical grades)
     X = processed_df[categorical_features + numerical_features + interest_strength_cols]
@@ -181,7 +188,7 @@ def predict_career(desired_career, aggregate, interests, strengths, english, cor
                   elective_maths, physics, biology, chemistry):
     
     try:
-        # Create student data dictionary
+        # Create student data dictionary with all required fields
         student_info = {
             "StudentID": "STU_TEMP",
             "Desired_Career": desired_career,
@@ -196,7 +203,15 @@ def predict_career(desired_career, aggregate, interests, strengths, english, cor
             "Elective Maths": elective_maths,
             "Physics": physics,
             "Biology": biology,
-            "Chemistry": chemistry
+            "Chemistry": chemistry,
+            # Add empty values for other subjects that were in the training data
+            "Economics": "",
+            "E-ICT": "",
+            "Literature": "",
+            "Geography": "",
+            "Business Management": "",
+            "Visual Arts": "",
+            "Government": ""
         }
         
         # Get recommendations
@@ -216,7 +231,9 @@ def predict_career(desired_career, aggregate, interests, strengths, english, cor
         
         return recommendations + "\n" + explanation
     except Exception as e:
-        return f"Error processing request: {str(e)}"
+        import traceback
+        error_details = traceback.format_exc()
+        return f"Error processing request: {str(e)}\n\nDetails:\n{error_details}"
 
 # Define grade options - fixing format to work with Gradio
 grade_options = [