Update app.py

app.py

@@ -10,9 +10,6 @@ import gradio as gr
 import pandas as pd
 from datetime import datetime
 
-# --- THE FINAL FIX IS HERE: Re-introducing the missing import ---
-import regex as re2
-
 # --- BACKEND IMPORTS ---
 from langchain_cohere import ChatCohere
 
@@ -37,11 +34,11 @@ def load_markdown_text(filepath: str) -> str:
 
 def _sanitize_text(s: str) -> str:
     if not isinstance(s, str): return s
-    # This now works because 're2' is defined from the import above
     return re2.sub(r'[\p{C}--[\n\t]]+', '', s)
 
 def _create_python_script(user_scenario: str, schema_context: str) -> str:
     """Uses an LLM to act as an "AI Coder", writing a complete Python script."""
+    # --- THE FINAL PROMPT FIX IS HERE ---
     prompt_for_coder = f"""
 You are an expert Python data scientist. Your sole job is to write a single, complete, and executable Python script to answer the user's request.
 You have access to a list of pandas dataframes loaded into a variable named `dfs`.
@@ -50,15 +47,12 @@ You have access to a list of pandas dataframes loaded into a variable named `dfs
 {schema_context}
 --- END SCHEMA ---
 
-CRITICAL RULE: You MUST use the exact column names provided in the DATA SCHEMA. Column names are case-sensitive. Pay close attention to capitalization (e.g., 'Zone' vs 'zone'). A KeyError will cause a failure.
-
-Based on the user's scenario below, write a single Python script that performs the entire analysis.
-
-RULES FOR YOUR SCRIPT:
-1.  **Use the DataFrames:** Your script MUST use the `dfs` list and the exact column names from the schema.
-2.  **Print Your Findings:** Use the `print()` function at each step to output the results as a formatted report.
-3.  **No Placeholders:** Do not use placeholder data.
-4.  **Self-Contained:** The script must be entirely self-contained, starting with `import pandas as pd`.
+CRITICAL RULES FOR YOUR SCRIPT:
+1.  **HANDLE DATA TYPES:** Before performing any mathematical operations (like addition or division), you MUST explicitly convert string values (e.g., '5.5%', '$100') to numeric types (`float` or `int`). Failure to do this will cause a fatal `TypeError`.
+2.  **CHECK COLUMN NAMES:** You MUST use the exact, case-sensitive column names provided in the DATA SCHEMA. A `KeyError` will cause a failure.
+3.  **USE THE DATAFRAMES:** Your script MUST use the `dfs` list to access the data.
+4.  **PRINT FINDINGS:** Use the `print()` function at each step to output your results as a formatted report.
+5.  **NO PLACEHOLDERS:** Do not use placeholder data.
 
 --- USER'S SCENARIO ---
 {user_scenario}