Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-5572

LDA improvement listing

    XMLWordPrintableJSON

Details

    • Umbrella
    • Status: Resolved
    • Major
    • Resolution: Incomplete
    • None
    • None
    • MLlib

    Description

      This is an umbrella JIRA for listing planned improvements to Latent Dirichlet Allocation (LDA).

      Attachments

        Issue Links

          incorporates

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-9134 LDA Asymmetric topic-word prior

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-7090 Introduce LDAOptimizer to LDA to further improve extensibility

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

          Sub-task - The sub-task of the issue SPARK-7455 Perf test for LDA (EM/online)

          • Major - Major loss of function.
          • Resolved

          Wish - General wishlist item. SPARK-5104 Distributed Representations of Sentences and Documents

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

          New Feature - A new feature of the product, which has yet to be developed. SPARK-8696 Streaming API for Online LDA

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-8555 Online Variational Inference for the Hierarchical Dirichlet Process

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

          Documentation - Documentation or Website SPARK-9888 Update LDA User Guide

          • Major - Major loss of function.
          • Resolved
          requires

          Bug - A problem which impairs or prevents the functions of the product. SPARK-13355 Replace GraphImpl.fromExistingRDDs by Graph

          • Major - Major loss of function.
          • Resolved

          Bug - A problem which impairs or prevents the functions of the product. SPARK-14322 Use treeAggregate instead of reduce in OnlineLDAOptimizer

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-5556 Latent Dirichlet Allocation (LDA) using Gibbs sampler

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-5565 LDA wrapper for spark.ml package

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-5566 Tokenizer for mllib package

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-8936 Hyperparameter estimation in LDA

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-9245 DistributedLDAModel predict top topic per doc-term instance

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-9246 DistributedLDAModel predict top docs per topic

          • Major - Major loss of function.
          • Resolved

          New Feature - A new feature of the product, which has yet to be developed. SPARK-9231 DistributedLDAModel method for top topics per document

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

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-5560 LDA EM should scale to more iterations

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-5563 LDA with online variational inference

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-5564 Support sparse LDA solutions

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-5567 Add prediction methods to LDA

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-5571 LDA should handle text as well

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-6793 Implement perplexity for LDA

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-8536 Generalize LDA to asymmetric doc-topic priors

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-9224 OnlineLDAOptimizer Performance Improvements

          • Major - Major loss of function.
          • Resolved

          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

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-9481 LocalLDAModel logLikelihood

          • Trivial - Cosmetic problem like misspelt words or misaligned text.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-14370 Avoid creating duplicate ids in OnlineLDAOptimizer

          • Trivial - Cosmetic problem like misspelt words or misaligned text.
          • Resolved

          Test - A new unit, integration or system test. SPARK-5562 LDA should handle empty documents

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

          Test - A new unit, integration or system test. SPARK-9225 LDASuite needs unit tests for empty documents

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

          Activity

            People

              Unassigned Unassigned
              josephkb Joseph K. Bradley
              Votes:
              3 Vote for this issue
              Watchers:
              9 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: