Big data brings big challenges to industry and research. Hadoop is a critical platform used to solve big data problems, and is also one of the driving forces to make big data technologies popular. In recent years, a big ecosystem has been built on top of Hadoop. Spark is a relatively new player in big data, but has quickly become mainstream due to its computing speed and flexibility.
This session will start with the fundamentals and an introduction to CCS' Bigfoot cluster. You will learn how big data is handled with examples. Multiple user interfaces to Bigfoot cluster will be presented, including Hue web, command line interactive session and job submission, and Rstudio server. You will practice basic Hadoop and Spark tasks like data loading, processing, and task management on the Bigfoot cluster.
We will explore the differences between Big Data systems and traditional high-performance computing, and you will run some Hadoop and Spark jobs using sample data. This is an excellent opportunity to grow your projects by making use of CCS' Bigfoot cluster, and to develop skills that are indispensable for industry careers. This free event is open to UM Faculty, Staff and Students
Dowload the flyer here.
Register here: http://ccs.miami.edu/hadoop-and-spark/
Speaker: Zongjun Hu, PhD. Lead, Big Data and Advanced Computing
Date: Friday, 08/1112017 1-4 PM
Location: RSMAS Campus SLAB 114, Science Lab. & Admin Bldg., 4600 Rickenbacker Cswy, Key Biscayne
Refreshments will be provided.
