ClusterOutputPostProcessor ( clusterpp ) groups records in their
respective cluster.
It can be applied after clustering.
See this : https://cwiki.apache.org/MAHOUT/top-down-clustering.html
On 07-05-2012 11:08, pipi wrote:
Hi all,
I have a problem about the output of clustering
algorithm(Kmeans,fuzzyKmeans, etc.), there are cluster-* and clusterpoints
folders, after using ClusterDumper to parse these output to txt format, I
get the VL-*,Centrols, weight,distance,vector, but no pointID - ClusteID
pair. I need to identify one record(vector) belong to which cluster, for
example the Reuters data, I want to konw the reut2-016.sgm-266.txt belong to
which cluster, how do I could get the result?
thanks!
pipi
--
View this message in context:
http://lucene.472066.n3.nabble.com/the-analysis-of-output-of-Clustering-algorithm-by-mahout-tp3967851.html
Sent from the Mahout Developer List mailing list archive at Nabble.com.
