Print Email Facebook Twitter Improvement of Source Code Conversion for Code Completion Title Improvement of Source Code Conversion for Code Completion Author Turk, Mika (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Izadi, M. (mentor) van Deursen, A. (mentor) Lukina, A. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-24 Abstract Code Completion is advancing constantly, with new research coming out all the time. One such advancement is CodeFill, which converts source files into token sequences for type prediction. To train the CodeFill model, a lot of source files are needed which take a long time to convert before training can begin. Converting the file the end-user is working on for completions is also essential for the total latency as longer files can affect the experience of using the model. In this study we aimed to improve the performance and success rate of this conversion. Our results indicate that we increased both the performance by 83 times or more depending on the input file length and the success rate by up to 45%. Subject code completionperformance improvementpythonJavaScript To reference this document use: http://resolver.tudelft.nl/uuid:9acaa0c3-ba8d-443a-8d06-c296f65c6895 Part of collection Student theses Document type bachelor thesis Rights © 2022 Mika Turk Files PDF CSE3000_Paper_Mika_Turk.pdf 437.73 KB Close viewer /islandora/object/uuid:9acaa0c3-ba8d-443a-8d06-c296f65c6895/datastream/OBJ/view