Spark SQL & Machine Learning - A Practical Demonstration
Organization:
Atlanta Apache Spark User Group
Category:
Technical/Scientific
Geographical Area:
Atlanta
Start
Date:
10/11/2016
End Date:
10/11/2016
Start Time:
6:30 PM
End Time:
8:30 PM
Event
Info:
What You'll Learn: * Apache Spark - High-level overview, Spark SQL architecture, BI tool access via ODBC/JDBC * Machine Learning - General workflow, Collaborative Filtering basics, Spark MLlib introduction
Details: This presentation explores how developers can deliver powerful machine learning applications by leveraging Spark's SQL and MLlib libraries. A brief overview covering Spark components and architecture kicks things off, and then we dive right in with a live demonstration of loading and querying data using Spark SQL. Next, we'll examine the basics of machine learning algorithms and workflows before getting under the hood of a Spark MLlib-based recommendation engine. Our final demonstration looks at how familiar tools can be used to query our recommendation data before we wrap up with a survey of real-world use cases.
Outline: * Spark Background/Overview - The Spark+Hadoop team, Spark's five main components * Spark SQL Architecture - How DataFrames work, The SQLContext, Data sources * Demo #1: Loading And Querying a Dataset with Spark SQL * Machine Learning with Spark MLlib - Collaborative filtering basics, Alternating Least Squares (ALS) algorithm, General machine learning workflow * Demo #2: Under The Hood With A Spark MLlib Recommendation Engine, Recommender model code review and live demonstration of training-test loop iterations * Demo #3 Putting It All Together - Tableau with Spark SQL ODBC/JDBC * Some Real-World Use Cases
DISCLAIMER: Our aim is to continuously provide our
progressive audience with an open and interactive medium to view
and share relevant,
beneficial and interesting "career, economic, lifestyle and
networking" listings, ads, content and resources.
While the above information may be accurate and viable, the role
of Minority Professional Network, Inc. (MPN) is
strictly as a communications medium, and we do not
accept any responsibility for
cancellation, changes, errors, omissions, inconveniences, or any other form
of liability for any content
displayed or disseminated via our web sites, or e-marketing or social media
promotional services.
If there are any
doubts, we
encourage you to conduct additional research or contact the listed host or responsible entity.
CLICK HERE to inform us about any ads, listings or content
which appear to be
inappropriate,
fraudulent or misleading, or inconsistent with our theme and focus.