Hadoop just got a lot more sexier - Spark on Yarn

Topic: Apache Spark on Yarn

Apache Spark is the latest chapter in distributed, open source software. It is 100 times faster than Hadoop, scalable, and able to cache data in memory, making it more suited for machine learning and data analysis. It can process real time data (like Twitter Storm), slice and dice large datasets (like Hive), and comes with apis in Java, Scala and Python. It's a comprehensive software stack that anyone can use: And we're lucky enough to have someone that can show us how! Stay tuned for this Meetup's exact Date (mid-July) and Location, look forward to seeing everyone there :)

Speaker/Bio: Xuefeng Wu is a senior consultant, helping customers build large-scale business solutions on the Scala stack, which include: Play Framework for web development, Akka for concurrent programming, and Spark for big data analysis.

Date: July 21st from 7:30 pm - 9 pm
Location: Thoughtworks Shanghai Offices, please see address.

*Please note that the slides and demo will be in English but the talk will be in Chinese.