Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-11730

Feature Importance for GBT

    XMLWordPrintableJSON

Details

    • New Feature
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • 2.0.0
    • ML, MLlib
    • None

    Description

      Random Forests have feature importance, but GBT do not. It would be great if we can add feature importance to GBT as well. Perhaps the code in Random Forests can be refactored to apply to both types of ensembles.

      See https://issues.apache.org/jira/browse/SPARK-5133

      Attachments

        Issue Links

          is blocked by

          New Feature - A new feature of the product, which has yet to be developed. SPARK-11861 Expose feature importances API for decision trees

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved
          Is contained by

          Umbrella - An overarching type made of sub-tasks SPARK-14047 GBT improvement umbrella

          • Major - Major loss of function.
          • Resolved
          is related to

          New Feature - A new feature of the product, which has yet to be developed. SPARK-7674 R-like stats for ML models

          • Critical - Crashes, loss of data, severe memory leak.
          • Resolved
          links to

          Pull request #11961 [Github] Pull Request #11961 (sethah)

          Activity

            People

              sethah Seth Hendrickson
              bwebb Brian Webb
              Joseph K. Bradley Joseph K. Bradley
              Votes:
              3 Vote for this issue
              Watchers:
              8 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: