Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-22111

OnlineLDAOptimizer should filter out empty documents beforehand

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Minor
    • Resolution: Won't Fix
    • 2.3.0
    • None
    • MLlib
    • None

    Description

      OnlineLDAOptimizer should filter out empty documents beforehand in order to make corpusSize, batchSize, and nonEmptyDocsN all refer to the same filtered corpus with all non-empty docs.

      Attachments

        Issue Links

          is blocked by

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-14371 OnlineLDAOptimizer should not collect stats for each doc in mini-batch to driver

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

          Pull request #19565 [Github] Pull Request #19565 (akopich)

          Web Link GitHub Pull Request #19565

          Activity

            People

              Unassigned Unassigned
              weichenxu123 Weichen Xu
              Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: