Using Tessera and R for Distributed Divide and Recombine


Details
Hearkening back to a talk (https://www.meetup.com/nyhackr/events/144947392/) Bill Cleveland gave to our group almost two years ago we have Ryan Hafen presenting on Tessera, a convenient front end in R for utilizing the Divide and Recombine paradigm.
Thank you again to iHeart (http://www.iheart.com/) for hosting us in their theater.
About the talk:
Tessera is an R-based open source project with the goal of providing a simple, back-end agnostic interface that allows data scientists to easily analyze and visualize large complex data sets.
Tessera is powered by Divide and Recombine (https://www.meetup.com/nyhackr/events/144947392/) (D&R), a methodological approach that is designed to provide access to the thousands of statistical, machine learning, and visualization methods available in R at scale. At the front end of Tessera the analyst programs in R. At the back end is a distributed parallel computation environment such as Hadoop. The environment is designed to be back end agnostic, so that the interface stays the same regardless of the back end being used, making the environment useful for small data sets as well, and allowing new distributed computing technologies (such as Spark) to be plugged in.
In this talk I will introduce Tessera and provide some hands-on examples of visualizing data using the Tessera Trelliscope package. More information about Tessera can be found on tessera.io (http://tessera.io/).
About Ryan:
Ryan Hafen is an independent statistical consultant and the chief architect of Tessera (http://tessera.io). His research focuses on methodology, tools, and applications in exploratory analysis, statistical model building, and machine learning on large, complex datasets. He holds a PhD in Statistics from Purdue University.
Pizza begins at 6:30, the talks at 7 and then we will go to a nearby bar.
http://photos1.meetupstatic.com/photos/event/c/9/5/6/600_439551542.jpeg
There are still a few seats left for the three-day Bayes/MCMC/Stan course on July 19th, 20th and 21st and meetup members can use code nyhackr (https://www.eventbrite.com/e/learn-bayes-mcmc-and-stan-with-andrew-gelman-bob-carpenter-daniel-lee-tickets-17503271757?discount=nyhackr) for20% off the ticket price.
http://photos2.meetupstatic.com/photos/event/e/7/5/4/600_438479220.jpeg
And Strata (September 29 through October 1) is once again offering our group a 20% discount using codeUGNYHACKR20 (https://tracking.cirrusinsight.com/d277e80c-e5f3-4ec8-91e8-9e81c918cd64/oreil-ly-1kc2scb) and visiting http://oreil.ly/1KC2sCB (https://tracking.cirrusinsight.com/d277e80c-e5f3-4ec8-91e8-9e81c918cd64/oreil-ly-shwny15ug).

Using Tessera and R for Distributed Divide and Recombine