There is a newer version of the record available.

Published August 4, 2023 | Version v1.2.0
Software Open

PyRACER - Unofficial Python implementation of the RACER classification algorithm.

Creators

Description

  • RACERPreprocessor now uses Scikit-learn's OneHotEncoder and LabelBinarizer by default. You may use fit_transform_pandas to use the pandas version of the encoding. However, be advised that the newly added fit and transform methods still use OneHotEncoder (for features) and LabelBinarizer (for targets).
  • Fixed several issues with the automatic classification task inference.
  • Marginally improved overall performance courtesy of Scikit-learn's optimized categorical encoders.

Full Changelog: https://github.com/Adversarian/RACER/compare/v1.1.3...v1.2.0

Notes

If you use this software, please cite it as below.

Files

Adversarian/RACER-v1.2.0.zip

Files (21.5 kB)

Name Size Download all
md5:c3eb73a3d687d3085c6c3184c31a9e6e
21.5 kB Preview Download

Additional details

Related works

Is supplement to
https://github.com/Adversarian/RACER/tree/v1.2.0 (URL)