Skip to main content

CloudMLPredictIcon (2)63bd.png Machine Learning Predict

Use the Machine Learning Predict tool to use models you've built in Alteryx Machine Learning to make predictions about new data.

Important

The Machine Learning Predict tool requires the AMP engine to run. Note that AMP is the default engine for all new workflows starting with Designer 22.1. Learn more about the AMP engine.

Install the Tool

To install the Machine Learning Predict tool in Designer...

  1. Go to the downloads page.

  2. Go to Alteryx Intelligence Suite > Alteryx Intelligence Suite (your Designer version).

    1. Note that you must have Designer 22.3 or higher installed.

  3. Download the Alteryx Machine Learning Designer Integration Tools YXI file.

  4. Open Designer with the "Run as Administrator" option enabled.

  5. Open the YXI file to start the installation process.

    1. Note that the Machine Learning Predict tool appears in the Machine Learning tool palette.

Important

The integration tools are separate from the tools included in Alteryx Intelligence Suite.

Configure the Tool

Connect to Alteryx Machine Learning (OAuth)

For first time setup of the Machine Learning Integration tools, you must add your Alteryx Analytics Cloud (AAC) workspace as a Data Source…

  1. Add a Machine Learning Integration tool to your workflow.

  2. From the tool Configuration window, select Set Up a Connection to open the Data Connection Manager (DCM).

  3. On the Data Sources page, select New.

  4. Enter a Data Source Name that describes your AAC workspace.

  5. Enter the Base URL of your AAC workspace. For example, https://us1.alteryxcloud.com/.

  6. Enter your AAC Workspace Name.

  7. Select Save.

  8. From the Connections section, select Connect Credential.

  9. Leave OIDC as the Authentication Method.

  10. From the Credential dropdown, select your authorization credential.

    1. If you don’t have an authorization credential, select Create New Credential.

    2. Enter a Credential Name. For example, the name of your AAC workspace.

  11. Select the Allow connection for SDK checkbox.

  12. Select Link if you’ve used the Credential before, or select Create and Link if you just created it.

  13. Select Connect. Designer directs you to sign in to your AAC workspace.

If you already have a Data Source configured…

  1. Add a Machine Learning Integration tool to your workflow.

  2. From the tool Configuration window, select Set Up a Connection to open the Data Connection Manager (DCM).

  3. On the Data Sources page, select the Data Source you set up previously.

  4. Select Connect. Designer directs you to sign in to your AAC workspace.

Connect to Alteryx Machine Learning (Access Tokens)

Important

API tokens created on the Access Tokens Page have been deprecated. Please migrate your Machine Learning Integration tool to OAuth authentication by July 11, 2024.

Follow these steps for previous installations of the Machine Learning Integration tools (23.2 or earlier). Note that the Machine Learning Integration tools available now on the Download Portal only support OAuth authentication described in the previous section.

Note that if you want to run the Machine Learning Predict tool on Server, follow these additional steps. If not, follow these steps:

  1. First, you need to create an access token if you don’t already have one. Follow these steps to create one from the home page.

  2. Next, in the tool configuration panel, enter the URL that you use to access your account.

  3. Select Sign In.

  4. Add a new data source in the Connection Manager. The Connection Manager should appear after you enter the URL for the first time.

    1. To open the Connection Manager, go to File > Manage Connections.

  5. Select + Add Data Source.

  6. Enter a Data Source Name.

  7. Under Technology, select Trifacta Auth if not already selected.

  8. Select Save.

  9. Within your new data source page under Connections, select Access Token under Authentication Method.

  10. Check the Allow connection for SDK box.

  11. Under Credential, select your authorization credential.

  12. If you don’t have an authorization credential, select Create New Credential.

    1. Enter a Credential Name.

    2. Enter your Access Token from step 1.

  13. Select Create and Link.

  14. Select Link.

  15. When you've successfully connected to your account, the tool displays an "Authentication Verified" message.

  16. To change credentials, select Change Credentials.

Modeling Selection

  1. Prepare your new data for model prediction.

    1. Make sure to remove the target variable from your dataset.

    2. Match column names and data types to the dataset used to train your model.

  2. From the Machine Learning Predict tool, select the model you want to apply to your new data by selecting your Project.

    1. The Project Details, Model Details, and Ranking Metrics are all filled in from the model you've built in Alteryx Machine Learning.

  3. Select Run to apply the model to your new data.

  4. The Machine Learning Predict tool creates new columns of data in the output, which contain predictions.

Note

To avoid type warnings in your workflow, use a typing tool like the Select tool or Auto Field tool to change the column type. You can also manually fix type warnings.

In this section: