Databricks June Meetup

Come join us for the next North East Databricks meet-up in The Catalyst, June 8th at 6pm!

We are pleased to welcome Gavita and Luke from Advancing Analytics to our North East Databricks Meetup. The event is open to Databricks experts, people who are totally new to the platform, or anyone who is enthusiastic about data!

18:00 - 18:10 Welcomes & Introduction
18:10 - 18:50 Luke Menzies - "GIS using Databricks"
18:50 - 19:20 Networking, Food and Drinks
19:20 - 20:00 Gavita Regunath - "Democratising Machine Learning with End-to-End Models on Databricks"
20:00 Close

Luke Mendes - I am a data scientist at Advancing Analytics that has been in the field for over four years. Before entering the data science world, I completed a PhD in computational materials modelling for applications in nuclear fusion. I have always taken an interest in using the language of mathematics to deliver tangible solutions to the world around me.

Talk Abstract – The topic of Geographic Information Systems (GIS), finds its way into the data analytics arena all too often without much consideration of how to implement it within big data solutions or pipelines. GIS data is large! Due to it comprising many layers of spatial information. This makes it tricky to deal with. The right methodology for handling it needs to be picked. If the GIS data requires transformations, machine learning or visualisations, naturally Python code is a good choice to cover all these aspects. Although there are Python libraries such as GeoPandas, to help with geospatial operations, they’re often not scalable when dealing with copious amounts of data. Many big data projects that require GIS call upon external software tools to handle the data. Tools such as ArcGIS, can come at a hefty additional expense. Is there a way to integrate GIS into the current data engineering pipeline one may have, without relying on external tools? The answer is yes! Databricks, a popular big data tool that is powered by a mighty Spark engine, has released a GIS tool named ‘Mosaic’. It aims to bring performance and scalability to design architectures. This also paves the way for any ML or AI that is desired alongside any ETL. This talk aims to give an introduction to Mosaic, walking listeners through the tool’s capabilities. The talk will also demonstrate how to use Mosaic to deliver some very sought-after business use cases such as routing, fraud detection and more.

Gavita Regunath is a principal data scientist consultant with Advancing Analytics and a Microsoft AI MVP. She has a PhD in Computational and Experimental Fluid Dynamics and has over a decade of experience working with Data and AI. She is addicted to learning and in her spare time when she is not blogging about AI, she enjoys being a mother, going for a run and cooking something new.

Talk Abstract – In this session, we will delve into the world of end-to-end machine learning models on Databricks. We will explore how machine learning models can be built using Databricks' data-centric AI platform, and how this platform democratises machine learning on the data lakehouse platform. The session will cover various aspects of machine learning, including data exploration, feature engineering, model development, and deployment. Through a demo, attendees will learn how to use Databricks to develop and deploy machine learning models in a scalable and efficient manner. Whether you are a data analyst, data engineer, data scientist, or machine learning engineer, this session is designed to help you overcome the barriers to entry and start leveraging machine learning in your work. Join us to learn how to build end-to-end machine learning models on Databricks and democratise the power of AI.

About Us
If you need to contact us for any reason you can email us at: northeastdatabricks@gmail.com
We are sponsored by:

• Databricks
• Waterstons - an IT consultancy based in Durham. Helping you become more data-driven!
• The National Innovation Centre for Data (NICD)