On Supervised Feature Selection from High Dimensional Feature Spaces

Created by Yijing Yang, Wei Wang, Hongyu Fu and C.-C. Jay Kuo from University of Southern California.

Introduction

This is an official implementation of our work DFT/RFT feature selection. A faster implementation of the DFT/RFT loss can be found in the cpp version.

Contents

• feat_utils.py: The function feature_selection is the main function for DFT-based feature selection.