If you have 45 minutes plus some coding experience in Scala, this workshop provides a crash introduction to Apache Spark.

This workshop will cover the basics of Spark, how it operates on a cluster. We will look at how Spark differs from other approaches to achieve performance and scale – even if you only need 8 servers instead of 8000 in a cluster. Then we'll work together on a programming exercise that leverages an open data set, comparing a range of machine learning models, and leveraging graph analytics to approximate Google Maps directions.

In advance of the workshop, please download the "Pre-built for Hadoop 2.x" binary from spark.apache.org/downloads.html on your laptop. We will provide links for data and code repo to follow along.