CACP: Classification Algorithms Comparison Pipeline

Abstract

This paper presents a Classification Algorithms Comparison Pipeline (CACP) for comparing newly developed classification algorithms in Python with other commonly used classifiers to evaluate classification performance, reproducibility, and statistical reliability. CACP simplifies the entire classifier evaluation process. Code examples and output results are explained and detailed to provide the basics of the module and give an overview of its capabilities. The code is available on GitHub under the MIT license.

Keywords

• Supervised classification
• Computational reproducibility
• Classifier performance evaluation
• Wilcoxon signed-rank test