We are going to introduce the Spark Platform

Hello Experimenters,

All,

We have had a change of plans. Paul Hargis (https://www.linkedin.com/in/pmhargis) (Hortonworks, formerly with Google)will be our presenter for the first meeting. He will carry the introductory discussion regarding Spark.

We will begin with an overview of Spark's core functionality, including SparkContext, RDDs, and parallelism. Then, we will go into more detailed coverage of Spark's Machine Learning library (ML lib), discussing Supervised Learning, Unsupervised Learning, Classification, and Collaborative Filtering. We will discuss mathematical concepts like logistic regression, feature matrix, and the confusion matrix. Finally, we'll walk through use of Spark with Scala and Python interfaces, and demo a data science notebooks using IPython Notebook.

For those who were looking forward to meeting Alvin - not to fear: he will still be there and will still contribute to the meeting. He could not take the lead for this meeting due to some unexpected responsibilities that he incurred in the last 24 hours.

This should be a very fun meeting.

Regards,

SCott

Prior post

I am pleased to announce our very first get together. Improving Enterprises has generously offered their facilities along with food and drink to host our own local Data Science Guru and Apache Tajo (http://tajo.apache.org/) commiter, Alvin Henrick (https://www.linkedin.com/in/alvinhenrick). For those who have wanted to "start" investigating Spark, he will provide an introduction that will "kick you into gear". This will NOT be a quiet lecture but a lively running discussion on the use of the tool.

Am still looking for other local scientists who would like to discuss ANY data science project.

My analysis indicates that experimenters will be there. Hopefully, you will be there too :) We will start with a small venue (max 30 attendees) and as we attract attention, our venue and visibility will grow.

Regards,

SCott