Update app.py

app.py

@@ -190,76 +190,4 @@ st.success(f"""
 
 
 
-                
-
-                # Display raw result for debugging purposes
-                st.markdown("<p style='font-family:sans-serif;font-size: 0.9rem;'> Raw Result: </p>", unsafe_allow_html=True)
-                st.success(raw_answer)
-
-                # Processing the raw_answer
-                processed_answer = raw_answer['answer'].replace(';', ' ')  # Clean the answer text
-                row_idx = raw_answer['coordinates'][0][0]  # Row index from TAPAS
-                col_idx = raw_answer['coordinates'][0][1]  # Column index from TAPAS
-                column_name = df.columns[col_idx]  # Column name from the DataFrame
-                row_data = df.iloc[row_idx].to_dict()  # Row data corresponding to the row index
-
-                # Handle different types of answers (e.g., 'SUM', 'MAX', 'MIN', 'AVG', etc.)
-                if 'SUM' in processed_answer:
-                    summary_type = 'sum'
-                    numeric_value = df_numeric[column_name].sum()
-                elif 'MAX' in processed_answer:
-                    summary_type = 'maximum'
-                    numeric_value = df_numeric[column_name].max()
-                elif 'MIN' in processed_answer:
-                    summary_type = 'minimum'
-                    numeric_value = df_numeric[column_name].min()
-                elif 'AVG' in processed_answer or 'AVERAGE' in processed_answer:
-                    summary_type = 'average'
-                    numeric_value = df_numeric[column_name].mean()
-                elif 'COUNT' in processed_answer:
-                    summary_type = 'count'
-                    numeric_value = df_numeric[column_name].count()
-                elif 'MEDIAN' in processed_answer:
-                    summary_type = 'median'
-                    numeric_value = df_numeric[column_name].median()
-                elif 'STD' in processed_answer or 'STANDARD DEVIATION' in processed_answer:
-                    summary_type = 'std_dev'
-                    numeric_value = df_numeric[column_name].std()
-                else:
-                    summary_type = 'value'
-                    numeric_value = processed_answer  # In case of a general answer
-
-                # Build a natural language response based on the aggregation type
-                if summary_type == 'sum':
-                    natural_language_answer = f"The total {column_name} is {numeric_value}."
-                elif summary_type == 'maximum':
-                    natural_language_answer = f"The highest {column_name} is {numeric_value}, recorded for '{row_data.get('Name', 'Unknown')}'."
-                elif summary_type == 'minimum':
-                    natural_language_answer = f"The lowest {column_name} is {numeric_value}, recorded for '{row_data.get('Name', 'Unknown')}'."
-                elif summary_type == 'average':
-                    natural_language_answer = f"The average {column_name} is {numeric_value}."
-                elif summary_type == 'count':
-                    natural_language_answer = f"The number of entries in {column_name} is {numeric_value}."
-                elif summary_type == 'median':
-                    natural_language_answer = f"The median {column_name} is {numeric_value}."
-                elif summary_type == 'std_dev':
-                    natural_language_answer = f"The standard deviation of {column_name} is {numeric_value}."
-                else:
-                    natural_language_answer = f"The {column_name} value is {numeric_value} for '{row_data.get('Name', 'Unknown')}'."
-
-                # Display the final natural language answer
-                st.markdown("<p style='font-family:sans-serif;font-size: 0.9rem;'> Analysis Results: </p>", unsafe_allow_html=True)
-                st.success(f"""
-                    • Answer: {natural_language_answer}
-
-                    Data Location:
-                    • Row: {row_idx + 1}
-                    • Column: {column_name}
-
-                    Additional Context:
-                    • Full Row Data: {row_data}
-                    • Query Asked: "{question}"
-                """)
-
-            except Exception as e:
-                st.warning("Please retype your question and make sure to use the column name and cell value correctly.")
+