tests.py [323:337]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if test_Spark:
            job_data_access_df, workload_print_info = prepare_df(datetime.strptime("2024-10-22", "%Y-%m-%d"),
                                                                 datetime.strptime("2024-10-28", "%Y-%m-%d"),
                                                                 Presto=True, Spark=True)
        else:
            job_data_access_df, workload_print_info = prepare_df(datetime.strptime("2023-09-08", "%Y-%m-%d"),
                                                                 datetime.strptime("2023-09-14", "%Y-%m-%d"),
                                                                    Presto=True, Spark=False)

        if not view_mode:
            graph = Query_on_DB_Table(
                job_data_access_df,
                workload_print_info,
                'report-table-size-0907.csv' if not test_Spark else 'report-table-size-20241021.csv',
                rep_threshold=rep_budget_rate, # optimizer will figure out the actual budget based on the data
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tests.py [538:551]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if test_Spark:
            job_data_access_df, workload_print_info = prepare_df(datetime.strptime("2024-10-22", "%Y-%m-%d"),
                                                                 datetime.strptime("2024-10-28", "%Y-%m-%d"),
                                                                 Presto=True, Spark=True)
        else:
            job_data_access_df, workload_print_info = prepare_df(datetime.strptime("2023-09-08", "%Y-%m-%d"),
                                                                 datetime.strptime("2023-09-14", "%Y-%m-%d"),
                                                                    Presto=True, Spark=False)
        if not view_mode:
            graph = Query_on_DB_Table(
                job_data_access_df,
                workload_print_info,
                'report-table-size-0907.csv' if not test_Spark else 'report-table-size-20241021.csv',
                rep_threshold=rep_budget_rate,  # optimizer will figure out the actual budget based on the data
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



