This weekend Brandon and I are at the Datathon for Diabetes in Boston. It starts tonight at 5 and goes all day Saturday. The goal is to use publicly available data to generate an insightful and innovative analysis of diabetes in United States and abroad.
Datathon for Diabetes
We’re sponsoring a prize for the team that makes best use of Data Scientist Workbench in their solution. Novo Nordisk and Deloitte are also sponsoring a prize each.
Our prize consists of a FitBit Charge HR for each member of the winning team.
I think it’s worthwhile to learn and apply Spark as a tool to the problem of diabetes. Spark is an open source framework that lets you run your data analysis in parallel on multiple machines for speed and ability to work with large amounts of data.
Data Scientist Workbench has Spark ready to use with Python, Scala, and R in Jupyter, Zeppelin, and R Studio IDE.
If you run into trouble at the datathon, come up and ask me any question you like. I’ll be there for the duration as a mentor. As always, if you run into a Data Scientist Workbench issue, you should also open a support ticket.
Other events
May 11-12 is Datapalooza Beijing and May 19 is Datapalooza Denver. Also, Big Data University is now posting events on its Facebook page.
Leo on Tech 