This repo hosts personal data projects, as well as those where I have worked with collaborators. Each project includes a folder for data, scripts, and iPython notebooks. In the future, I will include links to my personal website (currently under construction) of results and summaries for each project.
For each project I will provide the data (or colleciton method), scripts, and iPython notebooks. All results can be replicated with the files provided.
- I try to use standard python modules that can be installed using
pip
- While not required, I recommend installing and maintaining packages using anaconda
In this project we try to group NBA teams by playing style. We take a close look at the metrics that define team's playing styles and apply dimensionality reduction, clustering, and trees to find our answer. This project is still in progress.
Some of these projects I have worked on my own, and others I have paired up with awesome data enthusiasts. For more details check the individual project README files.
If you have any questions, suggestions, or requests, you can contact me via e-mail at:
juan "dot" bages "at" columbia "dot" edu
I and my collaborators are open to sharing our findings. If you find any of our work interesting and want to share/use it, just make sure to give us a shout-out. Individual collaborators are listed in the READMEs of each project.