All Products
Search

This Product

    Platform For AI:Create a pipeline from a template

    Document Center

    Platform For AI:Create a pipeline from a template

    Last Updated:Jun 02, 2026

    Machine Learning Designer provides preset templates for common machine learning scenarios. Use the Heart Disease Prediction template to build a binary classification model, run the pipeline, and optionally deploy the model as an online service.

    Prerequisites

    Step 1: Create a pipeline from a template

    Machine Learning Designer builds models through pipelines — sequences of components arranged to match your model logic. This step uses the Heart Disease Prediction preset template.

    1. Log on to the PAI console.

    2. In the left-side navigation pane, choose Visualized Modeling (Designer).

    3. Select a workspace and click Enter Visualized Modeling (Designer).

    4. Click the Preset Templates tab. Find the Heart Disease Prediction template and click Create.

      Preset Templates tab showing Heart Disease Prediction template

    5. In the Create Pipeline dialog box, configure the parameters and click OK.

      Parameter

      Description

      Workflow name

      Custom workflow name.

      Workflow data storage

      The OSS bucket path for temporary data and models. Defaults to workspace storage if not configured.

      For each run, Designer automatically creates a temporary folder at workflow_storage_path/task_ID/node_ID, which simplifies per-component storage configuration.

      Visibility

      • Visible to Me: Creates workflow in the My Pipelines folder, visible only to you and workspace administrators.

      • Visible to Current Workspace: Creates workflow in the Pipelines Visible to Workspaces folder, visible to everyone in the workspace.

      For more information about the parameters, see Create a workflow.

    6. Click Open to view the pipeline on the canvas.

    Step 2: Explore the model

    The template creates a pipeline with pre-configured components, as shown below.

    Heart Disease Prediction pipeline with pre-configured components

    Click any component to view its parameters. For more information about the components in this template, see Heart disease prediction.

    Note

    To deploy the model in Step 4, enable PMML generation: Click the Logistic Regression component, go to the Fields Setting tab, and select Whether to Generate PMML.

    Step 3: Run and debug the pipeline

    At the top left of the canvas, click the Run icon icon to run the pipeline.

    After the pipeline runs:

    • View data and perform visual analysis: Right-click a component and select View Data.

      For evaluation components such as Confusion Matrix and Binary Classification Evaluation, right-click the component and select Visual Analysis, or click the visualization icon at the top of the canvas. Visualized analysis.

    • View logs: If a component fails, right-click it and select View Log.

    Step 4: Deploy the model (optional)

    Machine Learning Designer integrates with Elastic Algorithm Service (EAS). After training and evaluating a model, deploy it to EAS as an online inference service.

    1. After the pipeline runs successfully, click Models in the left panel. Select the model and click Deploy in EAS.

      Models panel with Deploy in EAS option

    2. On the Deploy Service page, confirm the parameters. The Model File and Processor Type parameters are automatically configured. Modify other parameters as needed. Deploy a model as an online service.

    3. Click Deploy.

      When the service status changes from Creating to Running, the model is deployed.

      Important

      To avoid unnecessary costs, click Stop in the Actions column when the service is not in use.

    What's next