Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-24103

BinaryClassificationEvaluator should use sample weight data

Attach filesAttach ScreenshotVotersWatch issueWatchersCreate sub-taskLinkCloneUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • 2.0.2
    • 3.0.0
    • ML

    Description

      The LogisticRegression and LinearRegression models support training with a weight column, but the corresponding evaluators do not support computing metrics using those weights. This breaks model selection using CrossValidator.

      Attachments

        Issue Links

        is a child of

        Improvement - An improvement or enhancement to an existing feature or task. SPARK-18693 BinaryClassificationEvaluator, RegressionEvaluator, and MulticlassClassificationEvaluator should use sample weight data

        • Major - Major loss of function.
        • Resolved
        links to

        Pull request #17084 [Github] Pull Request #17084 (imatiach-msft)

        Web Link GitHub Pull Request #17084

        Activity
          This comment will be Viewable by All Users Viewable by All Users
          Cancel

          People

            imatiach Ilya Matiach
            imatiach Ilya Matiach
            Votes:
            0 Vote for this issue
            Watchers:
            5 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved:

              Slack

                Issue deployment