William La Cava

write evaluation routine for features in c++ with eigen and interface with main codebase via Cython. Include distutils changes to support package distribution.

the timing in multiple cores is multiplied by the number of cores.

I believe the plots in the README are mislabelled in the markdown text.

Hi! thanks for this very cool method. It would be great to include it in our [symbolic regression benchmarks](https://github.com/EpistasisLab/regression-benchmark/) project. We are just asking each method to have a scikit-learn...

fetch metafeatures option in fetch_data

5

It would be nice to add an option to fetch feature types from fetch_data.

would be good to show the metadata for each dataset on its pandas profiling page, using this argument during profiling: https://pandas-profiling.github.io/pandas-profiling/docs/master/rtd/pages/metadata.html

the [horse-colic](https://github.com/EpistasisLab/penn-ml-benchmarks/tree/PMLB2.0/datasets/horse_colic) dataset has no 0 labels, but it does have class labels [1,2]. Also, is it different from [colic?](https://github.com/EpistasisLab/penn-ml-benchmarks/tree/PMLB2.0/datasets/colic)

change sklearn to scikit-learn

1

pypi doesn't accept `sklearn` as a dependency anymore; has to be `scikit-learn` https://github.com/natekupp/ffx/blob/ced56d9423aa62d0a1b539832ed9537b6b7fefac/setup.py#L18