Software Metrics for Software Defect Prediction Dataset

Dataset used in the article: "Software Source Code Metrics for Software Defects Prediction"* in which we look at the impact of source code level metrics for software defects prediction models in terms of various metrics of prediction performance and the rankings of the metrics.

* Dominik Arne Rebro, Bruno Rossi, and Stanislav Chren. 2023. Source Code Metrics for Software Defects Prediction. In Proceedings of ACM SAC Conference (SAC’23). ACM, New York, NY, USA, https://doi.org/10.1145/3555776.3577809 

Contents of the package:

dataset/ : main datasets collected and analyzed in the article
results-rankings-plots/ : boxplots with the rankings of the metrics for each of the classifiers
Addendum_ProjectsStatistics.png : table with the mined projects descriptive statistics
Addendum_Acronyms.png : list of the main software source code metrics acronyms used in the article
Addendum_ThreatsToValidity.png : main threats to validity that could not be included in the article due to space constraints