SQL Saturday Denver #908 Precon

All attendees must agree to abide by the PASS Anti-Harassment Policy.

If you have any questions regarding this event, please email us at sqlsaturday908@sqlsaturday.com.

Getting Started with Data Science and Databricks

Databricks is a very popular environment for developing data science solutions. More and more companies are interested in Databricks as it is very simple to set up and contains a collaborative workspace for working with a team of people. In this session you will see how to create Machine Learning Solutions with multiple workflows starting with ETL, to data exploration, model experimentation, and lastly to a production release of a data science solution.

Today, more and more development is performed on very large datasets. Attendees will learn how to use Apache Spark, which is part of Databricks, to rapidly analyze lots of data. Learn how to use Databricks to reduces operational complexity to create solutions which can be scaled up or down depending on the amount of data needed to process without having to change the underlying code.

Python, Jupyter Notebooks, and Apache Spark are the technologies used to create solutions within this session. No experience is required.

Agenda

• Introduction to Databricks environment
• Hadoop and Apache Spark Basics
• Jupyter Notebooks and Python Foundations
• Machine Learning Data Requirements
• Data extraction and Understanding with Spark
• Creating Machine Learning Models
• Evaluating Machine Learning Models
• Production Machine Learning Pipelines in Databricks
• Machine Learning Data Processing with Databricks

Presented by: Ginger Grant

Ginger is a consultant who shares what she has learned while working with data technology at clients by providing training to people around the world. As a Microsoft MVP in Data Platform and a Microsoft Certified Trainer, she is proficient in creating solutions using the entire Microsoft Data Stack, which includes SQL Server, T-SQL, SSIS, SSAS, Power BI and Azure Data Cloud components including Databricks, Data Factory, Data Lakes, Data Analytics, IOT, Event Hubs, Machine Learning. In addition to blogging at http://www.desertislesql.com, Ginger has authored 70-774 Perform Cloud Data Science with Azure Machine Learning, and an online instructor and a member of the Instructor Board at Datacamp. When not working, she maintains her blog and spends time on twitter @desertislesql.