Sökning: "Filip Isakovski"

Hittade 1 uppsats innehållade orden Filip Isakovski.

  1. 1. APPLYING MACHINE LEARNING ALGORITHMS TO DETECT LINES OF CODE CONTRIBUTING TO TECHNICAL DEBT

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Filip Isakovski; Rafael Antonino Sauleo; [2019-11-12]
    Nyckelord :Technical Debt; Machine Learning; Static Code Analysis;

    Sammanfattning : This paper shows the investigation of the viability of finding lines ofcode (LOC) contributing to technical debt (TD) using machine learning (ML), bytrying to imitate the static code analysis tool SonarQube. This is approached byletting industry professionals choose the SonarQube rules, followed by trainingdifferent classifiers with the help of CCFlex (a tool for training classifiers withlines of code), while using SonarQube as an oracle (a source of training sampledata) which selects the faulty lines of code. LÄS MER