XyGen: Synthetic data generator for feature selection
Firuz Kamalov, Said Elnaffar, Hana Sulieman, Aswani Kumar Cherukuri · Software Impacts · 2023
Given the large number of feature selection algorithms, it has become imperative to have a uniform procedure for evaluating the performance of the algorithms. We propose a library of synthetic datasets designed specifically to test the effectiveness of feature selection algorithms. The datasets are inspired by applications in the field of electronics and have a range of characteristics to provide a variety of test scenarios. The software comes in the form of a Python library with standard interface for loading and generating datasets. Each dataset is implemented as a function that allows control of various parameters of the data.