After you succeed to run a pipeline on the pipeline configuration tab in Machine Learning Designer, you can use the dashboard to view the analytical report. This topic describes the components that support dashboards and how to go to the dashboard page.
Limits
The following components support dashboards:
Visualized data analysis:
Feature engineering:
Model evaluation:
Model visualization:
Statistical analytics:
Procedure
Log on to the Machine Learning Platform for AI (PAI) console and go to the details page of the pipeline that you created in Machine Learning Designer.
In this topic, the Heart Disease Prediction pipeline is used as an example. For more information about how to create a pipeline and how to go to the configuration tab of the pipeline, see Predict heart disease.
Go to the dashboard page.
You can use one of the following methods to go to the dashboard page:
Method 1: After the pipeline is successfully run, click
to view the visualized results of all pipeline components that support dashboards.
Method 2: After a pipeline component that supports dashboards is successfully run, right-click the component. In the shortcut menu, select Visual Analysis to view the visualized results of each component.
View the visualized results.
On the Visualized Nodes section, you can select a node to view its visualized results. This section displays the nodes based on the node category, and the nodes have the same names as the corresponding pipeline components.
In the right-side dashboards, the visualized results of each node are displayed. You can drag the dashboards to change their sizes or positions. This helps you compare the visualized results displayed in the dashboards. You can also close the dashboard of a node and drag the node to the right side to generate the dashboard again.