The Python code in this repository performs feature ranking and selection via Simultanenous Perturbation Stochastic Approximation (SPSA). The benchmark dataset used is the Ionosphere dataset with the Gaussian Naive Bayes classifier. For more information, please refer to the manuscript: "SPSA-FSR: Simultaneous Perturbation Stochastic Approximation for Feature Selection and Ranking", https://arxiv.org/abs/1804.05589.
Published at https://www.sciencedirect.com/science/article/abs/pii/S0305054821001180#!
Website: featureranking.com
go to directory of the package
conda create -n spsa-fsr python=3.6 conda activate spsa-fsr pip install -r requirements.txt
Run spfsr_example.py for