Implement a Big Data Math Algorithm in 2hrs - Linear Regression


Details
We will take a simple yet popular & powerful math algorithm such as Linear Regression and implement a distributed version in 2hrs.
Pre-requisites: Knowledge of Java or R
Warning: Only software programmers ignore Warnings! :)
That said, this seriously is a very hands on java-intense exercise. Extinguished engineers may not enjoy the proceedings.
Patrons need to ensure that the following steps have been achieved before hand:
- Downloaded the H2O source from: https://github.com/0xdata/h2ohttp://img1.meetupstatic.com/img/clear.gif
like so,
$ git clone https://github.com/0xdata/h2o.gi...http://img1.meetupstatic.com/img/clear.gif
-
Installed IntelliJ or eclipse on your laptop.
-
Imported project into IDE (by pointing to h2o directory)
-
Run main in water.Boot within IDE
(This should launch H2O within IDE) -
Try out the following samples -
https://github.com/0xdata/h2o/tree/master/src/samples/java/water
- New documentation will be added to http://docs2.0xdata.com/
This session will be hands-on: Hacking & less of a spectator sport.
This session will expose user to concepts of Distributed Fork / Join and working with a consistent Distributed K/V Store and Math-hacking over simplest Map & Reduce concepts, as well as DRemoteTask.
Finally Our API is still being morphed & some of the boilerplate will go away & get a bit easier in time.
Hoping to see the hacker in you.
[ Makers should kindly accept our sincere apology for rescheduling the event due to difficulty grabbing a venue for the size in SF. We are committed to doing more events in SF in this and months ahead.]

Implement a Big Data Math Algorithm in 2hrs - Linear Regression