Oct 5th – 6th 2019
The Glasstire Datahack is a two-day event where artists and data scientists unite to analyze and draw findings from a data set of art venues throughout the Greater Houston Area.
Looking through the data set provided by Glasstire, our team noticed a significant increase in the number of small, independent art venues in the Greater Houston Area.
In order to better visualize this trend, I individually contributed the following interactive 3D volumetric plot of the entire data set. Venues are sorted by color, the ones with the fewest total events are blue and gradually turn purple as they increase in total events hosted. It was built using both D3.js and three.js libraries.
Neural Style Transfer refers to the use of neural network algorithms to render an image in the style of a different image. Our team came up with the idea of a Neural Style Transfer art crawl as a cost-free, fun way to attract visitors to smaller venues and get them engaged. This strategy fits the theme of the DataHack by combining data science and fine art.
I took these portraits of audience members at the event and ran them through a more robust NST algorithm than the one we used after the event ended.