Update app.py

app.py

@@ -1175,6 +1175,10 @@ def handle_large_dataset(df, create_document,isDataFrame):
         # 1. Drop the original first column
         if len(df.columns) > 1:
                 # Skipping the original first column
+                # List of required columns
+                required_columns = ['Broker Name', 'Account Number', 'Employee name', 'Account Owner', 'Account ID']
+                # Filter the DataFrame to include only the required columns
+                df = df[required_columns]
                 limited_data = df.head(3)
                 limited_data_without_first_column = limited_data.iloc[:, 1:] 
         else:
@@ -1195,6 +1199,7 @@ def handle_large_dataset(df, create_document,isDataFrame):
 
         file_path = "output_data.xlsx"
         #file_path = os.path.join(current_folder, 'output_data.xlsx')
+        #Broker Name, Account Number, Employee name,Account Owner,Account ID
         df.to_excel(file_path, index=False)