www.ijtra.com

Apache Spark [2] is an open source platform for scalable MapReduce computing on clusters. The role of the Spark platform is to tackling the volume, velocity, and volatility aspects of MBD. Essentially, the Spark engine tackles the volume aspect by parallelizing the learning task into many sub-tasks and each task performed on a small partition ... ................
................

In order to avoid copyright disputes, this page is only a partial summary.