%0 Generic %1 sanatinia2016githubs %A Sanatinia, Amirali %A Noubir, Guevara %D 2016 %K php %T On GitHub's Programming Languages %U http://arxiv.org/abs/1603.00431 %X GitHub is the most widely used social, distributed version control system. It has around 10 million registered users and hosts over 16 million public repositories. Its user base is also very active as GitHub ranks in the top 100 Alexa most popular websites. In this study, we collect GitHub's state in its entirety. Doing so, allows us to study new aspects of the ecosystem. Although GitHub is the home to millions of users and repositories, the analysis of users' activity time-series reveals that only around 10% of them can be considered active. The collected dataset allows us to investigate the popularity of programming languages and existence of pattens in the relations between users, repositories, and programming languages. By, applying a k-means clustering method to the users-repositories commits matrix, we find that two clear clusters of programming languages separate from the remaining. One cluster forms for "web programming" languages (Java Script, Ruby, PHP, CSS), and a second for "system oriented programming" languages (C, C++, Python). Further classification, allow us to build a phylogenetic tree of the use of programming languages in GitHub. Additionally, we study the main and the auxiliary programming languages of the top 1000 repositories in more detail. We provide a ranking of these auxiliary programming languages using various metrics, such as percentage of lines of code, and PageRank.

@misc{sanatinia2016githubs, abstract = {GitHub is the most widely used social, distributed version control system. It has around 10 million registered users and hosts over 16 million public repositories. Its user base is also very active as GitHub ranks in the top 100 Alexa most popular websites. In this study, we collect GitHub's state in its entirety. Doing so, allows us to study new aspects of the ecosystem. Although GitHub is the home to millions of users and repositories, the analysis of users' activity time-series reveals that only around 10% of them can be considered active. The collected dataset allows us to investigate the popularity of programming languages and existence of pattens in the relations between users, repositories, and programming languages. By, applying a k-means clustering method to the users-repositories commits matrix, we find that two clear clusters of programming languages separate from the remaining. One cluster forms for "web programming" languages (Java Script, Ruby, PHP, CSS), and a second for "system oriented programming" languages (C, C++, Python). Further classification, allow us to build a phylogenetic tree of the use of programming languages in GitHub. Additionally, we study the main and the auxiliary programming languages of the top 1000 repositories in more detail. We provide a ranking of these auxiliary programming languages using various metrics, such as percentage of lines of code, and PageRank.}, added-at = {2017-12-30T11:14:12.000+0100}, author = {Sanatinia, Amirali and Noubir, Guevara}, biburl = {https://www.bibsonomy.org/bibtex/2c77ed5ea1817eb035511f59fca1f2f13/s_bergmann}, description = {On GitHub's Programming Languages}, interhash = {2c1ce6de862faa971232a45b38ac6210}, intrahash = {c77ed5ea1817eb035511f59fca1f2f13}, keywords = {php}, note = {cite arxiv:1603.00431}, timestamp = {2017-12-30T11:14:12.000+0100}, title = {On GitHub's Programming Languages}, url = {http://arxiv.org/abs/1603.00431}, year = 2016 }