Big Data Computing with Spark

Big data systems such as Hadoop and Spark emerge as enabling technologies in managing massive amounts of data across hundreds or even thousands of computing nodes. Meanwhile, cloud computing platforms have made these technologies easily accessible to individuals as well as large enterprises. This course is an online adaptation of the signature course MSBD 5003 Big Data Computing offered to our popular MSc Program in Big Data Technology. In addition to 20+ hours of lecture videos, the course contains 100+ multiple-choice questions and 20 coding questions, aimed at equipping learners with both the theory and practical skills of big data systems, using Spark as the exemplary platform.

• Spark programming using both RDD and DataFrame APIs
• Useful packages including ML, GraphX/GraphFrames, and SparkStreaming
• Spark internals and performance optimizations
• Algorithm design for big data systems

• Week 1: Overview, MapReduce, and Hadoop
• Week 2-3: Spark Basics and RDD
• Week 4: SparkSQL and MLib
• Week 5: Spark internals
• Week 6: Algorithm design for big data
• Week 7: GraphX/GraphFrames
• Week 8: Spark Streaming