Hitachi Vantara Pentaho Community Forums
Results 1 to 3 of 3

Thread: Hierarchical Clustering - Visualize Cluster Characteristics?

  1. #1
    Join Date
    Jun 2016
    Posts
    5

    Default Hierarchical Clustering - Visualize Cluster Characteristics?

    Hey all,

    I am currently working on a dataset with 18Tsd instances and want to apply hierarchical clustering.


    First, I applied X-Means and got a meaningful result as Cluster centroids, but with hierarchical clustering I can only infer, which instances belong to which cluster.
    But that's in my case not sufficient as I cannot extract knowledge from that.

    Is there any way to see characteristics like cluster centroids in partitioning clustering in hierarchical clustering?


    Thank you very much in advance .

    Greetings,
    Markus
    Last edited by matze91; 06-19-2016 at 04:35 AM.

  2. #2
    Join Date
    Aug 2006
    Posts
    1,741

    Default

    You could use the ClusterMembership filter to produce a dataset with the cluster assignment appended for each instance and then build a decision tree or rule set with that as the class. Not exactly centroids, but the rules/tree will characterise the clusters.

    Cheers,
    Mark.

  3. #3
    Join Date
    Jun 2016
    Posts
    5

    Default

    Thank you .

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  
Privacy Policy | Legal Notices | Safe Harbor Privacy Policy

Copyright © 2005 - 2019 Hitachi Vantara Corporation. All Rights Reserved.