Data Science and Machine Learning

AIT08 Machine Learning with Azure Databricks

12/04/2018

2:45pm - 4:00pm

Level: Intermediate

Leila Etaati

Data Scientist, PhD, MVP, and BI Consultant, and Speaker

Azure Databricks is an Apache Spark-based platform optimized for use for data science and machine learning (ML). Data scientists can use Azure Databricks to collect and clean data, then design and test machine learning models using R, Python, Scala or SQL scripts. In this session, Leila will provide a brief introduction and demonstration on machine learning with Azure Databricks. She’ll show you how to fetch data from Azure Data Lake Storage, then clean the data using Scala and SQL scripts. Next, she will demonstrate how to visualize the data to profile the data, find outliers and more. Finish by showing how to build a machine learning model on the collected and cleaned data and view the results in Power BI. This session will build on the Introduction to Azure Databricks session earlier in the day, giving you a deeper dive on Azure Databricks’ AI and ML capabilities.

You will learn:

  • How to use Azure Databricks for Machine Learning Purpose
  • How to get data from Azure Data Lake Store for ML Purpose and how to send the final result to Power BI
  • How to Run R, Python, Scala, and SQL codes for ML purpose inside Azure Databricks