ChiPy Data Science SIG: February 2017

Join us at Metis (https://www.thisismetis.com/)for our first (somewhat belated) meeting of the year. Doors will open at 6pm. Talks will begin at 6:30.

Talks:

• Peter Hirschboeck

A beginner's encounter with distributed computing: the need and the adventure of getting billions of function calls and results processed

• Trevor Grant

Absurdly Large OLS with Apache Mahout:

Ever wish you had a bit more horsepower to run your favorite distributed algorithm but don’t quite have the cash for a Hadoop cluster? Hadoop-as-a-service might be right up your use-case alley then. This talk will show how to get up and running with IBM’s BlueMix using a handful of Python scripts to do the heavy lifting of getting Apache Zeppelin and Mahout installed and configured. Once set up the fun begins, with a demonstration of running a Mahout OLS (ordinary least squares) algorithm on a massive (100 million rows x 100 features) data set.

Thanks to Metis for hosting us and sponsoring this event!

Hope to see you all there!