No Detail Found!

A smart model for categorization of GitHub repositories

Author(s)
Muhammad Muneeb Aslam Department of Computer Science COMSATS University Islamabad,Sahiwal Campus, Pakistan
Muhammad Farhan Department of Computer Science COMSATS University Islamabad,Sahiwal Campus, Pakistan
Sana Yaseen Department of Computer Science COMSATS University Islamabad, Sahiwal Campus , Pakistan
Ahmad Raza Department of Computer Science COMSATS University Islamabad, Sahiwal Campus, Pakistan
Muhammad Javed Iqbal Department of Computer Science, University of Engineering and Technology, Taxila, Pakistan
Muhammad Munwar Iqbal Department of Computer Science, University of Engineering and Technology, Taxila, Pakistan
Abstract
There are several datasets of source code available on the World Wide Web. These files are usually grouped into application categories for programming languages. Various repositories of open-source code are now public on GitHub. Users can upload the source code they develop, distribute it to other users, allow other programmers to renew or change the program over time, and announce specific software applications. This study proposes a machine learningbased model for classifying source code. Machine learning algorithms are necessary to train and authenticate predictions of the required tasks. In the future, related software applications will be categorized into multiple source codes. Our machine-learning model trains you to organize your multiprogramming source code according to your problem. Training datasets can be obtained from GitHub. The main goal of this study is to learn different solutions for software classification. This research study aims to use source code to confirm the classification of multilingual software. The outcomes mentioned below in the result section appear to be quite encouraging. This method shows that the source code type can be completed using the earlier criteria. The software's great precision and quick response time make it ideal for the most realistic functions. The software had a 97 percent accuracy when identifying three programming languages.
Publication Details
Page(s) 50-64
DOI 10.51153/kjcis.v6i1.149
Published Journal: KIET Journal of Computing & Information Sciences, Volume: 6, Issue: 1, Year: 2023

Request the full text from PASTIC

Keywords
Deep learning, Categorization, GitHub, Source Code
More from KIET Journal of Computing & Information Sciences
0

Citations

0

Downloads

52

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk