Update app.py

app.py

@@ -8,12 +8,13 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
 # 1) Load your synthetic profitability dataset
 df = pd.read_csv('synthetic_profit.csv')
 
-# 2) Ensure numeric columns for true aggregation (optional, but helps you verify sums)
+# 2) Ensure numeric columns for true aggregation
 for col in ["Revenue", "Profit", "ProfitMargin"]:
     df[col] = pd.to_numeric(df[col], errors='coerce')
 
 # 3) Build the schema description text
-schema_lines = [f"- {col}: {dtype.name}" for col, dtype in df.dtypes.iteritems()]
+#    ← replaced .iteritems() with .items() here
+schema_lines = [f"- {col}: {dtype.name}" for col, dtype in df.dtypes.items()]
 schema_text = "Table schema:\n" + "\n".join(schema_lines)
 
 # 4) Few-shot examples teaching SUM and AVERAGE patterns
@@ -44,10 +45,10 @@ table_qa = pipeline(
 
 # 6) QA function with schema-aware prompting
 def answer_profitability(question: str) -> str:
-    # 6a) cast all cells to string for safety
+    # cast all cells to string for safety
     table = df.astype(str).to_dict(orient="records")
 
-    # 6b) assemble the full prompt
+    # assemble the full prompt
     prompt = f"""{schema_text}
 
 {example_block}
@@ -55,7 +56,6 @@ def answer_profitability(question: str) -> str:
 Q: {question}
 A:"""
 
-    # 6c) call TAPEX
     try:
         out = table_qa(table=table, query=prompt)
         return out.get("answer", "No answer found.")
@@ -74,5 +74,6 @@ iface = gr.Interface(
     )
 )
 
+# 8) Launch the app
 if __name__ == "__main__":
     iface.launch(server_name="0.0.0.0", server_port=7860)