DSC 333: Introduction to Big Data Processing

This course will explore different approaches and a framework for performing data analytics on a dynamic, heterogeneous cluster of computing nodes. The course will begin with studying principles behind MapReduce and implementation of custom distributed queries using Hadoop. It will then expand to cover higher-level languages and tools within Hadoop ecosystem (e.g., Pig, Hive) and cluster configuration techniques. Finally, the course will delve into a comparative evaluation of several NoSQL and NewSQL databases that make fundamentally different assumptions for data processing (e.g., OLAP vs OLTP, disk-bound vs in-memory or real-time streaming data). The primary focus of the course will be hands-on implementation and tuning performance for large-scale clusters and data sets.