Description Usage Arguments Value
By default this function will extract out-of-sample/validation/holdout predictions
from original training data (automatically done by h2o) to evaluate the cross-validated MSE.
However, when newdata
is supplied, the predictions for each CV model will
be based on this external validation dataset.
These predictions and the outcome stored in newdata
are then used to re-evalute the CV MSE.
Note that newdata
must be of the same
dimensionality as the original training data used for fitting the h2o models.
1 2 |
modelfit |
Model fit object returned by |
newdata |
Optional new validation data for evaluating MSE, either a |
subset_idx |
Optional row indices if MSE needs to be evaluating for a subset of the input data. |
verbose |
Set to |
A list of MSEs by model.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.