Training and Validating a Machine Learning Model

Machine Learning is primarily about training models that you can use to provide predictive services to applications. In this exercise, you’ll see how you can use Azure Databricks to train and validate a machine learning model.


Before starting this lab, complete the Getting Started with Azure Databricks lab to set up your Azure Databricks environment and import the data and notebooks you require.

Train and Validate a Machine Learning Model

In this exercise, you will learn how to load and manipulate data inside the Azure Databricks environment.

  1. In a web browser, open your Azure Databricks workspace.

  2. If your cluster is not running, on the Compute page, select your cluster and use the ▶ Start button to start it

  3. In the Azure Databricks Workspace, using the command bar on the left, select Workspace. Then select Users, and your_user_name. Then in the folder named 02 - Training and Evaluating Machine Learning Models, open the 2.0 Train and Validate ML Model notebook.

  4. Attach the notebook to your cluster. Then read the notes in the notebook, running each code cell in turn.


If you’re finished working with Azure Databricks for now, in Azure Databricks workspace, on the Compute page, select your cluster and select ■ Terminate to shut it down. Otherwise, leave it running for the next exercise.