GPR: A Python implementation of an extremely simple classifier based on fuzzy logic and gene expression programming

Abstract

In this work, we present a Python-based implementation of an extremely simple classifier (GPR), which combines gene expression programming (GEP) features and the algebraic representation of the ’if-then’ fuzzy rules theory of the Takagi–Sugeno fuzzy inference system. Generated fuzzy metarules are highly interpretable and suitable for many applications. We provide an open-source Python implementation of the GPR algorithm to enable the use of the algorithm without any commercial software tools and open access to the research community. We also added enhancements to improve the readability and interpretability of the rules.

Keywords

• Fuzzy rule-based classifier
• Gene expression programming
• Interpretability