Update app.py

app.py

@@ -726,6 +726,7 @@ CRITICAL RULES:
 9.  **SAFE ITERATION:** When iterating over mixed data structures, always check types before accessing attributes. Not all list items are dicts (some may be strings), not all values have `.items()`.
 10. **KEY-VALUE DATA PATTERN:** Many healthcare datasets use key-value format (e.g., columns: 'Indicator'/'Value' or 'Metric'/'Amount'). To extract a specific value, filter rows by the key column, then access the value column: `df.loc[df['Indicator'] == 'Cost per client', 'Value'].iloc[0]`
 11. **CONVERT STRINGS BEFORE MATH:** Always clean and convert strings to float/int BEFORE performing arithmetic. Use `re.sub(r'[^\\d.]', '', value)` to strip currency symbols ($), percentage signs (%), commas, and other non-numeric characters. For ranges like "8–10", split first, clean each part, convert to float, then calculate: `parts = text.split('–'); avg = (float(re.sub(r'[^\\d.]', '', parts[0])) + float(re.sub(r'[^\\d.]', '', parts[1]))) / 2`
+12. **SCALAR VS VECTORIZED:** When applying a cleaning function to DataFrame columns, use `.apply()` for element-wise operations: `df['col'].apply(clean_func)`. Do NOT pass a Series to a function expecting a single value. For a single extracted value, use `.iloc[0]` to get the scalar before processing.
 
 --- USER'S SCENARIO ---
 {user_scenario}