Chicago R User Group (Chicago RUG) Data and Statistics Message Board › Distributed R -- A scalable high-performance platform and parallel programmi
|A former member||
Dear R enthusiasts,
I am pleased to inform you that HP Vertica has released a Distributed R platform that enables R to scale-out for the Big Data Advanced Analytic needs.
HP Vertica Distributed R is a High-Performance Scalable Platform for the R language. Distributed R provides R language extensions -- distributed arrays, data frames, data partitioning and parallel looping constructs. These extensions enable R developers to parallelize statistical and machine learning algorithms for the scalability and performance needs of Big Data. HP Vertica has developed distributed versions of logistic, linear and poisson regression on this platform. These algorithms show near linear scalability and can be used to build models on terabytes of training data. This early access beta software includes Distributed R platform, HP Distributed Generalized Linear Model (HPDGLM) R package and vRODBC driver for faster data load from the Vertica database. The HPDGLM package also includes a parallel data loader for high-performance data loading from the Vertica database.
Download of Distributed R free beta software, documentation and HPDGLM source code available from HP Vertica website http://vertica.com/marketplace . Distributed R is under the Innovations section of the market place.
Following publications will provide more insight into Distributed R.
• Distributed Machine Learning and Graph Processing with Sparse Matrices . Shivaram Venkataraman, Erik Bodzsar, Indrajit Roy, Alvin AuYoung, Rob Schreiber. Eurosys 2013, Prague, Czech Republic.
• Using R for Iterative and Incremental Processing . Shivaram Venkataraman, Indrajit Roy, Alvin AuYoung, Rob Schreiber. HotCloud 2012, Boston, USA.
For a high-level introduction of this new platform, you can watch these short YouTube videos
• HP Vertica Distributed R: Advanced Analytics for Big Data
• XLDB 2013: Distributed R for Big Data
We want to hear from you! Try the Distributed R and let us know what you think! Would this functionality have an impact in your business? What aspect did we overlook? Posting to the Vertica community http://community.vert... with your feedback is the surest way to help us bring the most important efforts to market.
Sr. Technical Product Manager @ HP Vertica