Python code smells detection using conventional machine learning models

• Published in: PeerJ. Computer science Vol. 9; p. e1370
• Main Authors: Sandouka, Rana, Aljamaan, Hamoud
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 29.05.2023; PeerJ Inc
• Subjects: Algorithms; Analysis; Artificial Intelligence; Code smell; Data mining; Data Mining and Machine Learning; Detection; Java (Computer program language); Large class; Long method; Machine learning; Python; Software Engineering; Large class; Code smell; Detection; Long method; Machine learning; Python
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.1370

Code smells are poor code design or implementation that affect the code maintenance process and reduce the software quality. Therefore, code smell detection is important in software building. Recent studies utilized machine learning algorithms for code smell detection. However, most of these studies focused on code smell detection using Java programming language code smell datasets. This article proposes a Python code smell dataset for Large Class and Long Method code smells. The built dataset contains 1,000 samples for each code smell, with 18 features extracted from the source code. Furthermore, we investigated the detection performance of six machine learning models as baselines in Python code smells detection. The baselines were evaluated based on Accuracy and Matthews correlation coefficient (MCC) measures. Results indicate the superiority of Random Forest ensemble in Python Large Class code smell detection by achieving the highest detection performance of 0.77 MCC rate, while decision tree was the best performing model in Python Long Method code smell detection by achieving the highest MCC Rate of 0.89.