Uploaded image for project: 'Public H2O 3'
  1. PUBDEV-4122

Add a h2o.ensemble_performance function to Stacked Ensemble

    Details

    • Type: New Feature
    • Status: Open
    • Priority: Major
    • Resolution: Unresolved
    • Affects Version/s: None
    • Fix Version/s: None
    • Component/s: R, StackedEnsemble
    • Labels:
      None
    • CustomerVisible:
      No

      Description

      In the h2oEnsemble package, we have a `h2o.ensemble_performance` function which will evaluate and print model performance for all the base learners in addition to the ensemble. This is different than the typical `h2o.performance` function in R (or .model_performance() method in Python) which only returns the final model (ensemble) performance.

      Right now, we have to calculate the base learner performance by hand using code like what we have in the ensemble docs: http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html

      We can either choose to do this on the backend, or in the R/Py client... Raymond Peck do you have a preference?

        Attachments

          Activity

            People

            • Assignee:
              navdeep Navdeep
              Reporter:
              erin Erin LeDell
            • Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

              Dates

              • Created:
                Updated: