It would be convenient, if one could, instead of having to create a full CVS specifying the splits, just pass a custom number of CV folds to use AutoFolio more easily with different dataset sizes.
Let me know if you'd like me to provide a pull request.
Hi Marius,
when using the CSV-facade, one can specify the CV-folds with an extra CSV file: https://github.com/automl/AutoFolio/blob/f296f528b1b684d36837075b0e8160e3fa4124f7/autofolio/facade/af_csv_facade.py#L27 However, when not doing that, it will call the ASLibScenario without specifying the number of CV folds: https://github.com/mlindauer/ASlibScenario/blob/9ce38dd43dc6e2834cb8ef44cd837514e950a9c5/aslib_scenario/aslib_scenario.py#L168 In that case, the default of 10 folds will be used: https://github.com/mlindauer/ASlibScenario/blob/9ce38dd43dc6e2834cb8ef44cd837514e950a9c5/aslib_scenario/aslib_scenario.py#L827
It would be convenient, if one could, instead of having to create a full CVS specifying the splits, just pass a custom number of CV folds to use AutoFolio more easily with different dataset sizes.
Let me know if you'd like me to provide a pull request.
Best, Jan