Machine Learning Designer provides preset templates for common machine learning scenarios. This topic describes how to 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 allows you to build models by using pipelines. A pipeline consists of components that you can arrange based on your model logic. In this step, you create a pipeline from the Heart Disease Prediction preset template.
Log on to the PAI console.
In the left-side navigation pane, choose Visualized Modeling (Designer).
Select a workspace and click Enter Visualized Modeling (Designer).
Click the Preset Templates tab. Find the Heart Disease Prediction template and click Create.
In the Create Pipeline dialog box, configure the parameters and click OK.
Parameter
Description
Pipeline Name
Specify a name for the pipeline that you want to create.
Data Storage
The path of the Object Storage Service (OSS) bucket that stores the temporary data and models generated during pipeline runtime. We recommend that you configure this parameter. If you leave this parameter empty, the default storage of the workspace is used.
The system automatically creates a temporary directory in the
<Pipeline data path>/<Task ID>/<Node ID>format for each run. This saves you from creating an OSS directory for storing data of each component and allows you to manage data in a centralized manner.Visibility
Visible to Me: A workflow is created in the My Pipelines folder and is visible only to you and the administrator in the workspace.
Visible to Current Workspace: A pipeline is created in the Pipelines Visible to Workspaces folder and is visible to all members of the current workspace.
For more information about the parameters, see Create a pipeline.
Click Open to view the pipeline on the canvas.
Step 2: Explore the model
The preset template creates a complete pipeline with pre-configured components. The following figure shows the Heart Disease Prediction pipeline.
Click any component to view its parameters. For more information about the components in this template, see Predict heart disease.
If you plan to deploy the model in Step 4, you must 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 
icon to run the pipeline.
After the pipeline runs, you can perform the following operations:
View data and perform visual analysis: Right-click a component and select View Data to view the output data of the component.
For evaluation components such as Confusion Matrix and Binary Classification Evaluation, you can visualize the results. Right-click the component and select Visual Analysis, or click the visualization icon at the top of the canvas. For more information, see Visualized analysis.
View logs: If a component fails, right-click the component and select View Log to troubleshoot the issue.
Step 4: Deploy the model (optional)
Machine Learning Designer integrates with Elastic Algorithm Service (EAS). After you train and evaluate a model, you can deploy it to EAS as an online inference service.
After the pipeline runs successfully, click Models in the left panel. Select the model and click Deploy in EAS.
On the Deploy Service page, confirm the parameters. The Model File and Processor Type parameters are automatically configured. You can modify other parameters as needed. For more information, see Deploy a model as an online service.
Click Deploy.
When the service status changes from Creating to Running, the model is deployed.
ImportantTo avoid unnecessary costs, click Stop in the Actions column when the service is not in use.
What's next
Build and debug models: Learn more about pipeline operations in Build and debug a model.
Create custom pipelines: Build pipelines from scratch to meet specific requirements. See Custom pipelines.
Schedule pipelines: Use DataWorks to schedule pipelines for periodic model updates. See Use DataWorks tasks to schedule pipelines.
Understand billing: Review the billing information for Machine Learning Designer in Billing of Machine Learning Designer.
Explore components: Learn about available components in Component reference.
View use cases: Explore real-world examples in Use cases for Designer.