figshare
Browse
TEXT
data-class.arff (148.66 kB)
TEXT
feature-envy.arff (191.73 kB)
TEXT
god-class.arff (148.66 kB)
TEXT
long-method.arff (191.73 kB)
DATASET
DataClass Results.csv (1.17 kB)
DATASET
LongMethod Results.csv (1.17 kB)
DATASET
FeatureEnvy Results.csv (1.17 kB)
DATASET
GodClass Results.csv (1.17 kB)
TEXT
GainRatio DataClass.txt (2.21 kB)
TEXT
GainRatio FeatureEnvy.txt (2.82 kB)
TEXT
GainRatio GodClass.txt (2.21 kB)
TEXT
GainRatio LongMethod.txt (2.82 kB)
DATASET
statistics.csv (12.39 kB)
1/0
13 files

Detecting Code Smells using Machine Learning Techniques: Are We There Yet?

Version 2 2018-01-14, 09:23
Version 1 2018-01-13, 18:09
dataset
posted on 2018-01-14, 09:23 authored by Dario Di NucciDario Di Nucci, Fabio PalombaFabio Palomba, Damian A. Tamburri, Alexander Serebrenik, Andrea De Lucia

Code smells are symptoms of poor design and im- plementation choices weighing heavily on the quality of produced source code. During the last decades several code smell detection tools have been proposed. However, the literature shows that the results of these tools can be subjective and are intrinsically tied to the nature and approach of the detection. In a recent work the use of Machine-Learning (ML) techniques for code smell detection has been proposed, possibly solving the issue of tool subjectivity giving to a learner the ability to discern between smelly and non-smelly source code elements. While this work opened a new perspective for code smell detection, it only considered the case where instances affected by a single type smell are contained in each dataset used to train and test the machine learners. In this work we replicate the study with a different dataset configuration containing instances of more than one type of smell. The results reveal that with this configuration the machine learning techniques reveal critical limitations in the state of the art which deserve further research.

History

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC