Conceptual Coupling Values - Github Projects Dataset

<p>A Dataset that contains conceptual coupling measures obtained on 61 opensource projects hosted in github.The conceptual coupling measure was calculated by 18 diferent ways. A way is called model. There are 299 software major version colected to calculate these values.</p> <p>To understand how each model was applyed, see the label meaning:</p> <ul> <li>Yco: Use code comment</li> <li>Nco: No use code comment</li> <li>Yca: Divide tokens by CamelCase</li> <li>Nca: no divide tokens by CamelCase</li> <li>Ns: no stemming tokens low frequency occurrence</li> <li>Ys: stemming tokens low frequeny occurrence</li> <li>Qth: remove third quantile&nbsp;</li> <li>Qfi: remove first quantile</li> <li>Lsi: Latent Semantic Indexing</li> <li>TFIDF: term frequency - inverse document frequency</li> <li>Naive: Term-Frequency</li> </ul> <p>All projects are from github and developed in the following language:</p> <ul> <li>C++</li> <li>Java</li> <li>Javascript</li> <li>Python</li> <li>Ruby</li> </ul> <p>This dataset also contains the following resources:</p> <ul> <li>Commits between those project versions</li> <li>List of versions used in this study</li> <li>Scripts used in some works</li> </ul>