import pandas as pd all_year_data = pd.read_parquet("./cache/ballon_data_lin.parquet") def get_dataframe_between_year(start_year, end_year): res = all_year_data filtered_res = res[(res['file_name'].str.extract(r'LIN-(\d{4})')[0].astype(int) >= start_year) & (res['file_name'].str.extract(r'LIN-(\d{4})')[0].astype(int) <= end_year)] return filtered_res