Skip to main content
Version: v0.14.0

Create a drift detection test

A Drift Detection validation test enables you to analyze a Driverless AI experiment or dataset.

Instructions​

Experiment​

To create a Drift Detection validation test for an experiment, consider the following instructions:

  1. In the H2O Model Validation navigation menu, click Experiments.
  2. In the experiments table, select the experiment you want to use for the validation test.
  3. Click Show.
  4. In the H2O Model Validation navigation menu, click Drift Detection.
  5. In the Enter a name box, rewrite or leave as-is the validation test name.
  6. Click New Test.
  7. Define the values for the validation test settings. Settings marked with an * are required to be defined.
    note

    To learn about each setting for a Drift Detection validation test, see Settings: Drift detection.

  8. Click Run Drift Detection.

Dataset​

To create a Drift Detection validation test for a dataset, consider the following instructions:

  1. In the H2O Model Validation navigation menu, click Datasets.
  2. In the datasets table, select the dataset you want to use for the validation test.
  3. Click Show.
  4. In the H2O Model Validation navigation menu, click Drift Detection.
  5. In the Enter a name box, rewrite or leave as-is the validation test name.
  6. Click New Test.
  7. Define the values for the validation test settings. Settings marked with an * are required to be defined.
    note

    To learn about each setting for a Drift Detection validation test, see Settings: Drift detection.

  8. Click Run Drift Detection.
Feedback