import dask.dataframe as dd df = dd.read_csv('large_dataset.csv') result = df[df['column1'] > 10].groupby('column2').sum() result.to_csv('result.csv', index=False) import modin.pandas as md df = md.read_csv('large_dataset.csv') result = df[df['column1'] > 10].groupby('column2').sum() result.to_csv('result.csv', index=False)