The project is aimed at large software project maintainers who wish to have a system which is able to identify and prevent possible issues in the early stage of development. The project implements a system which will be able to predict bugs and / or types of bugs appearing as a result of a pull request.
The analysis looks at the contents of the title, body and labels of the pull request, as well as information related to other details, such as date or if the pull request is a bug fix associated with a certain bug.
The main benefactors of this project are large scale projects, since they have generated a sufficient amount of data needed for this type of analysis. Smaller projects will benefit, as long as they are using a popular software stack (i.e. MERN stack for web development). This approach can also be used to identify problem areas of a code base, by looking at the type of pull requests and the type of issues they are addressing.
All the data is gathered from Github's API, mainly the VSCode project, since it's a massive open source project. Three main endpoints are being used to gather and organize the data: issues, pull requests and releases.
BSc (Honours) in Computing part time (evening) student specialising in Data Analytics at National College of Ireland. Currently working as Associate Software Dev Engineer for Yahoo and was an intern for Yahoo (formerly Verizon Media) between February 2021 – September 2021.
When it comes to coding, I am primarily self-taught, starting in 2016. In 2018, I started college in order to improve and certify my knowledge. I am interested in all things Data Analysis and Software Engineering.
My technical skills include professional experience with Java, Javascript, MySQL, MongoDB, EmberJS, ReactJS, NodeJS. As part of my studies, I have gained experience with R and Python and for personal projects I have extensively used Vue.js and PostgreSQL.