Using Spark and SparkML we can do some simple correlation exercises to see if the weather has any impact on NFL losses /wins. Our headline speaker will walk through some simple techniques to clean up the data and shape it to be analyzed.
This event is a great opportunity to learn some simple and quick ways to get data, cleanse data and rapidly spin up a place to work on it. The presentation will be done on the Data Science Workbench, a free tool that makes it fun and easy to learn these skills.
Beginner to Intermediate – Python, Spark and some simple statistical approaches.
Braden Callahan is a Spark and Big Data Evangelist at IBM. He speaks often on topics around Big Data and leveraging different data sources and approaches to gain insight. In his past he has been a Sr. Director of Business Intelligence at Demand Media and held Architecture roles at IBM and MapR.