hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Rishabh Garg (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HAMA-594) Implementation of a Semi-Clustering algorithm, described in Pregel paper.
Date Sun, 14 Apr 2013 10:28:15 GMT

    [ https://issues.apache.org/jira/browse/HAMA-594?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13631295#comment-13631295
] 

Rishabh Garg commented on HAMA-594:
-----------------------------------

Thankyou for your reply. I have gone through the paper properly now and was successful in
understanding the algorithm involved. Just trying to get practical experience with Hama and
Hadoop. Would you like me to implement the sample code you had put around a year ago ?

i.e.
 
  @Override
    public void compute(Iterator<SCMessage> messages) throws IOException {
      if (this.getSuperstepCount() == 0) {
        // In superstep 0, V enters itself in that list as a semi-cluster of
        // size 1 and score 1, and publishes itself to all of its neighbors.
      }

      // In subsequent supersteps, V circulates over the received semi-clusters
      SCMessage clusters = null;
      while ((clusters = messages.next()) != null) {
        for (SemiCluster c : clusters.getClusters()) {
          // If a semi-cluster c does not already contain V, V is added to c to
          // form c’.
        }
      }

      // The semi-clusters are sorted by their scores and the
      // best ones are sent to V’s neighbors.

      // Vertex V updates its list of semi-clusters with the
      // semi-clusters that contain V.

      boolean updated = updateLocalClusters(clusters);
      if (!updated) {
        // The algorithm terminates either when the semi-
        // clusters stop changing or the user may provide a
        // limit.

        // At that point, the list of best semi-cluster
        // candidates for each vertex may be aggregated
        // into a global list of best semi-clusters.
        
        voteToHalt();

      } else {
        // The semi-clusters are sorted by their scores and the best ones are
        // sent to V’s neighbors.
      }
    }
  }
                
> Implementation of a Semi-Clustering algorithm, described in Pregel paper.
> -------------------------------------------------------------------------
>
>                 Key: HAMA-594
>                 URL: https://issues.apache.org/jira/browse/HAMA-594
>             Project: Hama
>          Issue Type: New Feature
>          Components: examples, graph
>            Reporter: Edward J. Yoon
>              Labels: gsoc, gsoc2013, mentor
>
> {quote}
> 5.4 Semi-Clustering
> Pregel has been used for several different versions of clus-tering. One version, semi-clustering,
arises in social graphs. Vertices in a social graph typically represent people, and edges
represent connections between them.
> ....
> {quote}
> This issue implements Semi-Clustering algorithm, described in Pregel paper, using Hama
graph APIs.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message