The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pendekatan ramalan kecacatan telah banyak menyumbang kepada aktiviti jaminan kualiti perisian seperti semakan kod atau ujian unit. Pendekatan ramalan kecacatan tepat pada masa dibangunkan untuk meramalkan sama ada komit adalah komit yang menyebabkan kecacatan atau tidak. Kajian terdahulu telah menunjukkan bahawa ramalan peringkat komit tidak mencukupi dari segi usaha, dan komit yang rosak mungkin mengandungi kedua-dua fail yang rosak dan tidak rosak. Memandangkan komuniti ramalan kecacatan mempromosikan pendekatan ramalan butiran halus, kami mencadangkan ramalan peringkat kelas novel kami, yang lebih halus daripada ramalan peringkat fail, berdasarkan fail komit dalam penyelidikan ini. Kami mereka bentuk model kami untuk projek Python dan mengujinya dengan sepuluh projek Python sumber terbuka. Kami melakukan percubaan kami dengan dua tetapan: tetapan dengan metrik produk sahaja dan tetapan dengan metrik produk serta maklumat komitmen. Siasatan kami telah dijalankan dengan tiga pengelas berbeza dan dua strategi pengesahan. Kami mendapati bahawa model kami yang dibangunkan oleh pengelas hutan rawak menunjukkan prestasi terbaik, dan maklumat komit menyumbang dengan ketara kepada metrik produk dalam pengesahan silang 10 kali ganda. Kami juga mencipta ramalan peringkat fail berasaskan komit untuk fail Python yang tidak mempunyai kelas. Model peringkat fail juga menunjukkan keadaan yang sama seperti model peringkat kelas. Walau bagaimanapun, keputusan menunjukkan sisihan besar dalam pengesahan siri masa untuk kedua-dua peringkat dan cabaran untuk meramal kelas dan fail Python dalam senario yang realistik.
Khine Yin MON
Kyoto Institute of Technology
Masanari KONDO
Kyushu University
Eunjong CHOI
Kyoto Institute of Technology
Osamu MIZUNO
Kyoto Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Khine Yin MON, Masanari KONDO, Eunjong CHOI, Osamu MIZUNO, "Commit-Based Class-Level Defect Prediction for Python Projects" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 2, pp. 157-165, February 2023, doi: 10.1587/transinf.2022MPP0003.
Abstract: Defect prediction approaches have been greatly contributing to software quality assurance activities such as code review or unit testing. Just-in-time defect prediction approaches are developed to predict whether a commit is a defect-inducing commit or not. Prior research has shown that commit-level prediction is not enough in terms of effort, and a defective commit may contain both defective and non-defective files. As the defect prediction community is promoting fine-grained granularity prediction approaches, we propose our novel class-level prediction, which is finer-grained than the file-level prediction, based on the files of the commits in this research. We designed our model for Python projects and tested it with ten open-source Python projects. We performed our experiment with two settings: setting with product metrics only and setting with product metrics plus commit information. Our investigation was conducted with three different classifiers and two validation strategies. We found that our model developed by random forest classifier performs the best, and commit information contributes significantly to the product metrics in 10-fold cross-validation. We also created a commit-based file-level prediction for the Python files which do not have the classes. The file-level model also showed a similar condition as the class-level model. However, the results showed a massive deviation in time-series validation for both levels and the challenge of predicting Python classes and files in a realistic scenario.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022MPP0003/_p
Salinan
@ARTICLE{e106-d_2_157,
author={Khine Yin MON, Masanari KONDO, Eunjong CHOI, Osamu MIZUNO, },
journal={IEICE TRANSACTIONS on Information},
title={Commit-Based Class-Level Defect Prediction for Python Projects},
year={2023},
volume={E106-D},
number={2},
pages={157-165},
abstract={Defect prediction approaches have been greatly contributing to software quality assurance activities such as code review or unit testing. Just-in-time defect prediction approaches are developed to predict whether a commit is a defect-inducing commit or not. Prior research has shown that commit-level prediction is not enough in terms of effort, and a defective commit may contain both defective and non-defective files. As the defect prediction community is promoting fine-grained granularity prediction approaches, we propose our novel class-level prediction, which is finer-grained than the file-level prediction, based on the files of the commits in this research. We designed our model for Python projects and tested it with ten open-source Python projects. We performed our experiment with two settings: setting with product metrics only and setting with product metrics plus commit information. Our investigation was conducted with three different classifiers and two validation strategies. We found that our model developed by random forest classifier performs the best, and commit information contributes significantly to the product metrics in 10-fold cross-validation. We also created a commit-based file-level prediction for the Python files which do not have the classes. The file-level model also showed a similar condition as the class-level model. However, the results showed a massive deviation in time-series validation for both levels and the challenge of predicting Python classes and files in a realistic scenario.},
keywords={},
doi={10.1587/transinf.2022MPP0003},
ISSN={1745-1361},
month={February},}
Salinan
TY - JOUR
TI - Commit-Based Class-Level Defect Prediction for Python Projects
T2 - IEICE TRANSACTIONS on Information
SP - 157
EP - 165
AU - Khine Yin MON
AU - Masanari KONDO
AU - Eunjong CHOI
AU - Osamu MIZUNO
PY - 2023
DO - 10.1587/transinf.2022MPP0003
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2023
AB - Defect prediction approaches have been greatly contributing to software quality assurance activities such as code review or unit testing. Just-in-time defect prediction approaches are developed to predict whether a commit is a defect-inducing commit or not. Prior research has shown that commit-level prediction is not enough in terms of effort, and a defective commit may contain both defective and non-defective files. As the defect prediction community is promoting fine-grained granularity prediction approaches, we propose our novel class-level prediction, which is finer-grained than the file-level prediction, based on the files of the commits in this research. We designed our model for Python projects and tested it with ten open-source Python projects. We performed our experiment with two settings: setting with product metrics only and setting with product metrics plus commit information. Our investigation was conducted with three different classifiers and two validation strategies. We found that our model developed by random forest classifier performs the best, and commit information contributes significantly to the product metrics in 10-fold cross-validation. We also created a commit-based file-level prediction for the Python files which do not have the classes. The file-level model also showed a similar condition as the class-level model. However, the results showed a massive deviation in time-series validation for both levels and the challenge of predicting Python classes and files in a realistic scenario.
ER -