Modul kategorizace artefaktů pro projekt Analyzátor otevřeného kódu

Abstract

This thesis deals with the extension of the "Open Code Analyzer" system with a new artifact categorization module, which enables project categorization and bug reporting from the Github server. Machine learning methods are used for data processing. Various methods that use clustering algorithms, such as K-Means or hierarchical clustering, are designed and implemented within the work. The module contains methods for finding similar repositories, finding similar problems and estimating a newly created problem in a particular repository.