Altair SmartWorks Analytics

 

Using the Rapids AI node

The Rapids AI node leverages GPUs using Rapids AI to train a classifier by using built-in feature transformations and optional automated hyperparameter tuning of logistic regression and decision tree algorithms.

Prerequisites

  • An Execution Profile with an active session linked to the workflow

  • An MLFlow application configured as part of the Execution Profile's internal connections

  • A Data Frame node produced by importing a CSV or database table

Steps

  1. From the Machine Learning group of  the Nodes tabbed page, drag and drop the Rapids AI node to the workflow canvas.

  2. Connect the output socket of the Data Frame node to the input socket of the Rapids AI node.

  3.  

  4. Configure the Rapids AI node by double-clicking on the node or using the Open option provided in the node menu.

  5.  

  6. Select the previously configured connection from the Connection Profile dropdown.

  7.  

  8. Specify the following settings:

  9. Property

    Description

    Dependent variable

    Select a dependent variable of text data type only (the column from the resultant data set on which the prediction will be based) from the list of available variables of the input data source.

    Column names

    Select columns of the input data source that are to be included in the resultant model.

    Fitting option

    By default, the fitting option selected is Default.

    • Default indicates that you can create a logistic regression model with built-in transformations

    Application Connection profile

    Select the application connection profile from the Connection list and then select the configured ML flow server added from an internal connection.

     

  10. Check the code that will be executed for your Rapids AI configuration by saving your specifications and then clicking on the Code tab of the Rapids AI Node Viewer. You can also use the tab that displays to refine the code further.

  11. The auto generated code is displayed in the Code tabbed page. The Input Properties section is read-only and pre-populated with the input table name. However, you can modify the object name in the Output Properties section.

     

  12. Complete the Rapids AI configuration by clicking Save. Otherwise, cancel your changes and return to the workflow canvas by clicking Discard or simply closing the Rapids AI Viewer. Execute your configuration by clicking the Run button. When the operation has been completed, the workflow canvas is populated with the model that is generated.

  13.  

  14. Double-click Model on the workflow canvas to view Variable Information, Chart, Column metrics, and so on.

    After running the Rapids AI process node, a record is created in the ML Flow server and displays the details of the experiments.

  15.  

  16. Click on any Experiment ID to view more details of the experiment such as parameters, metrics, artifacts, and so on.