Mining Code Reviews and Using Pre-trained Models for Code Suggestions Automation

31 May 2023, by Aref El-Maarawi Tefur

Photo: Andrea de Santis

This project aims to understand code suggestions and feedback of developers reviewing pull requests on GitHub and to propose a machine learning-based solution for automating code suggestions for these pull requests. To this end, a representative data set of open-source software repositories hosted on GitHub will be created

The mined data, which consist of the pull requests and their corresponding comments and code suggestions, will be pre-processed, and analyzed using an empirical methodology. In the next step, the gathered data will be used to train a Transformer- based machine learning model to automatically recommend code suggestions.

Participants: Aref El-Maarawi Tefur

Latest articles

White domes in the wadden sea during low tide

Photo: base.camp

10.06.2024|basecamp-projects

Digitales Wattenmeer: a digital twin for biological field research

Understanding the changes that may occur in our biosphere as climate change progresses has significant, widespread implications for all areas of life and related policy decisions. Efforts are underway to study the impacts of elevated temperatures at the MERIT field site in the wadden sea. MERIT...

A lowpoly image of a bicycle with a box of sensors on the back.

Photo: base.camp

31.05.2024|basecamp-projects

Improving sensor networks with on-bicycle mobile nodes

This project aims to increase the geo-spatial resolution in environmental sensor networks using a mobile sensor kit. Within this work, the kit will be built and the data quality validated against existing public and official measuring networks. In the experiment, the sensor is mounted to a bicycle...