Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-14159

StringIndexerModel sets output column metadata incorrectly

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Resolved
    • Minor
    • Resolution: Fixed
    • None
    • 1.6.2, 2.0.0
    • ML
    • None

    Description

      StringIndexerModel.transform sets the output column metadata to use name inputCol. It should not. Fixing this causes a problem with the metadata produced by RFormula.

      Fix in RFormula: I added the StringIndexer columns to prefixesToRewrite, and I modified VectorAttributeRewriter to find and replace all "prefixes" since attributes collect multiple prefixes from StringIndexer + Interaction.

      Note that "prefixes" is no longer accurate since internal strings may be replaced.

      Attachments

        Activity

          People

            josephkb Joseph K. Bradley
            josephkb Joseph K. Bradley
            Xiangrui Meng Xiangrui Meng
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: