Settings: Size Dependency¶
H2O Model Validation offers an array of settings for a Size Dependency test. Below, each setting is described in turn.
Training dataset¶
Defines the training dataset used in the Driverless AI (DAI) experiment that H2O Model Validation uses for the Size Dependency validation test.
Reference dataset¶
Defines the reference dataset used in the Driverless AI (DAI) experiment that H2O Model Validation uses for the Size Dependency validation test.
Note
By default, you cannot modify this setting; accordingly, a Size Dependency validation test can only run DAI experiments that use a test dataset.
Time column¶
Defines the time column of the train and reference dataset, which H2O Model Validation uses to perform time-based splits.
Number of splits¶
Defines the number of splits that H2O Model Validation performs on the training dataset to assess the dataset Size Dependency.
Note
The more splits, the better in general; it maximizes the test's explanatory power. Each split leads to an extra experiment run; this setting affects the runtime.
Remove validation experiments from DAI after finish¶
Determines if H2O Model Validation should delete the Driverless AI (DAI) artifacts, including experiments and datasets generated during the Size Dependency validation test. By default, H2O Model Validation checks this setting (enables it), and accordingly, H2O Model Validation deletes all DAI artifacts because they are no longer needed after the validation test is complete.
- Submit and view feedback for this page
- Send feedback about H2O Model Validation to cloud-feedback@h2o.ai