Apache Spark has taken the data-science world by storm, offering a new way to process and analyze large quantities of data. Spark provides interfaces in a number of popular languages, such as Java, Scala, and Python, making it possible to perform large-scale data analysis in relatively short periods of time. Indeed, Spark’s claim to fame is that it can do very fast analysis of very large quantities of data. In this talk, Spark inventor Matei Zaharia introduces the technology, describes how it compares and interacts with others, and provides examples of how to use Spark to answer questions about large-scale data sets.

Time: 1:02