Hands-on Workshop: Using Apache Spark & Azure Databricks to Understand Your Customers

Big Data Hands-on Workshop: Using Apache Spark and Azure Databricks to Better Understand Your Customers

This is a hands-on, three-hour workshop which will allow you to experiment with Apache Spark running in the Azure Databricks platform. You’ll understand how you can use Spark and Azure Databricks to analyze large amounts of customer data, visualize the data to quickly spot patterns, use Spark’s Machine Learning library to generate predictions, and analyze real-time data from online sources (e.g. Twitter).

Agenda:

  1. Introduction to Apache Spark and Azure Databricks
  2. Hands-on Labs
    1. Setting up Azure Databricks and creating Spark clusters
    2. Accessing data from cloud storage
    3. Interactive data analysis and visualization with Databricks notebooks, Spark SQL and Python
    4. Build a product recommendations engine using Spark MLlib and collaborative filtering
    5. Perform customer segmentation using Spark MLlib and clustering
    6. Sentiment Analysis on real-time Twitter data, with Spark Streaming
  3. Wrap-up

IMPORTANT: This is a hands-on workshop. Bring your own laptop (Windows, Linux, or Mac).