[
https://issues.apache.org/jira/browse/MAHOUT-741?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13053289#comment-13053289
]
Sean Owen commented on MAHOUT-741:
----------------------------------
Code looks clean and simple as expected, and has a test so I'm guessing it
works.
I do think it's interesting to push into the graph algorithms area as a new
"talent" for the project so I do think it's worth stacking in some clean,
simple initial implementations like this.
> MapReduce job to compute the local clustering coefficient in an undirected
> graph
> --------------------------------------------------------------------------------
>
> Key: MAHOUT-741
> URL: https://issues.apache.org/jira/browse/MAHOUT-741
> Project: Mahout
> Issue Type: New Feature
> Components: Graph
> Affects Versions: 0.6
> Reporter: Sebastian Schelter
> Assignee: Sebastian Schelter
> Fix For: 0.6
>
> Attachments: MAHOUT-741.patch
>
>
> Distributed computation of the local clustering coefficient of the vertices
> of an undirected graph. The local clustering coefficient is a measure for the
> "connectedness" of a vertex in its neighborhood and is computed by dividing
> the number of closed triangles with a vertex neighbors by the number of
> possible triangles of this vertex with it's neighbours.
> http://en.wikipedia.org/wiki/Clustering_coefficient#Local_clustering_coefficient
> This measure is easy to compute when we already have enumerated the triangles
> of the graph.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
