Update app.py

app.py

@@ -24,26 +24,25 @@ class HybridExcelQuerySystem:
         self.sheet_names = []
 
     def _pivot_numerical_data(self, df: pd.DataFrame) -> pd.DataFrame:
-        """Pivots the special 'Numerical Data' sheet into a clean, usable format."""
-        # Find the row with month names, which will become our header
         header_row_index = 0
-        df = df.T # Transpose the dataframe
-        df.columns = df.iloc[header_row_index] # Set the first row as header
-        df = df.drop(header_row_index) # Drop the header row from data
-        df = df.reset_index().rename(columns={'index': 'Month'}) # Make months a column
+        df = df.T
+        df.columns = df.iloc[header_row_index]
         
-        # Clean up column names (e.g., "Profit & Loss Account" -> "Profit_Loss_Account")
-        df.columns = df.columns.str.strip().str.replace(r'[^a-zA-Z0-9_]', '_', regex=True)
+        # --- THIS IS THE FIXED LINE ---
+        df = df.iloc[1:] # Keep all rows from the second row onwards
+        
+        df = df.reset_index().rename(columns={'index': 'Month'})
+        df.columns = df.columns.str.strip().str.replace(r'[^a-zA-Z0-9_%]', '_', regex=True).str.replace('__', '_')
         
-        # Convert numeric columns to numbers, coercing errors
+        # Identify and convert numeric columns
         for col in df.columns:
             if col != 'Month':
+                # Remove '%' and convert to numeric, coercing errors
+                df[col] = df[col].astype(str).str.replace('%', '', regex=False)
                 df[col] = pd.to_numeric(df[col], errors='coerce')
         
-        # Drop columns that are entirely empty after conversion
         df = df.dropna(axis=1, how='all')
-        df = df.rename(columns={'Period': 'Month'}) # A final cleanup
-        # Filter out any non-month rows that might have slipped through
+        df = df.rename(columns={'Period': 'Month'})
         months = ['Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec', 'Jan', 'Feb', 'Mar']
         df = df[df['Month'].isin(months)]
         return df
@@ -58,14 +57,12 @@ class HybridExcelQuerySystem:
             for sheet_name in self.sheet_names:
                 df = pd.read_excel(file_path, sheet_name=sheet_name)
                 
-                # --- Prepare for Agent ---
                 if sheet_name == "Numerical Data":
                     agent_df = self._pivot_numerical_data(df.copy())
                 else:
                     agent_df = self._clean_dataframe_for_agent(df.copy())
                 self.dataframes[sheet_name] = agent_df
 
-                # --- Prepare for RAG ---
                 rag_df = self._clean_dataframe_for_rag(df.copy())
                 markdown_text = rag_df.to_markdown(index=False)
                 doc = Document(text=markdown_text, metadata={"source": sheet_name})
@@ -127,7 +124,7 @@ class HybridExcelQuerySystem:
                 verbose=True,
                 allow_dangerous_code=True,
                 max_iterations=15,
-                handle_parsing_errors=True # The direct fix for the error
+                handle_parsing_errors=True
             )
             response = agent.invoke(query)
             return {"answer": response['output'], "tool_used": "Calculation (Pandas Agent)"}