Now rescheduled to February 19th... Yes, even you can create a machine learning (ML) model! Learn how in this hands-on demo with code and data we provide for you. You can watch the demo, or follow along with your own laptop, or download the code and data later and try it at home. During this session, we will write Scala code using Spark and MLIB Decision Tree and Random Forest Classifiers to create your first ML model. If you don't know Scala or these frameworks, don't worry -- the examples are easy to follow, and you'll come away better prepared to do the same thing with the language and frameworks of your choice. Take away from the session: (a) code on GitHub having sample code in Scala implementing MLIB classifiers (b) code on GitHub that runs at scale within a Databricks If you want to follow along on your laptop, you should get set up before you arrive. (We do not have wi-fi access at our meeting location.) Download the code and data from this GitHub repository: https://github.com/aosama/MachineLearningSamples It’s a Scala Maven project, so you can compile the code before the meetup via "mvn install".
Colleagues, let's meet up to kick off the great 2019 with some community discussion and the following line-up of topics: - Productionizing Spark for Extract, Transform, Load (ETL), by Benny Lau, Business Development Manager of Leading Edge Group Limited - Project Hydrogen: State of the Art Deep Learning on Apache Spark, by Arseny Chernov, Lead of Partner Architecture APJ at Databricks. Venue Sponsor: WeWork Lockhart Rd F&B Sponsor: Databricks
ABC Supply has been racing to build a data science capability to the organization. Not an uncommon problem to face these days but with fresh eyes and no existing data science architecture, how did they build their new analytical platform. The discussion will revolve around the architectural choices made at ABC and how recent partnerships in Azure have provided value to ABC. To include some unexpected discoveries and values with using Databricks and Snowflake.