Use pandas dataframes with autosklearn>=0.15, instead of the encoded numpy arrays.
This is preferred because it is more "auto" and because it makes inference time measurements more comparable across frameworks.
note: this is on top of the measure_inference_time PR #532.
@eddiebergman @mfeurer are there any other changes that should be made to account for the switch?
Use pandas dataframes with
autosklearn>=0.15, instead of the encoded numpy arrays. This is preferred because it is more "auto" and because it makes inference time measurements more comparable across frameworks.note: this is on top of the
measure_inference_timePR #532.@eddiebergman @mfeurer are there any other changes that should be made to account for the switch?