Skip to content

uazadi/WekaNose

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WekaNose

Allows weka to smell your code

codebeat badge Codacy Badge

WekaNose is a tool that allows to perform an experiment, that aims to study code smell detection through machine learning techniques. The experiment's purpose is to select rules, or obtain trained algorithms, that can classify an instance (method or class) as affected or not by a code smell. These rules have the main advantage that they are extracted through an example-based approach, rather then a heuristic-based one. This experiment is divided in two main part:

  • the first one concern the creation of the dataset
  • the second part where the machine learning algorithms are trained and tested using the dataset created in the first part.

Information

For every further information about this tool:

Problems

For report any problem please check if already exist an Issue on GitHub about it:

  • if there isn't one please add an Issue
  • if there is one please leave a comment

SonarQube plugin

It is now available a SonarQube plugin that allows to use the machine learning algorithms, provided by WEKA and trained using the dataset generated by WekaNose, as actual code smell detector and it is available here.

Road map

The next steps in this project are:

  • integrating Auto-WEKA in order to make the training of the machine learning algorithms more user-friendly;
  • add a new feature that allows the user to exploit semi-supervised learning (such as active learning) to speed-up the labelling process;

If you are interested in contributing to this project in any way (suggestion of improvement, hint on what feature to add or even pull request) do not hesitate to contact me at u.azadi@campus.unimib.it.

Tools used by this one