org.apache.mahout.clustering.topdown.postprocessor

Class ClusterOutputPostProcessor

java.lang.Object

org.apache.mahout.clustering.topdown.postprocessor.ClusterOutputPostProcessor

public final class ClusterOutputPostProcessor
extends Object

This class reads the output of any clustering algorithm, and, creates separate directories for different clusters. Each cluster directory's name is its clusterId. Each and every point is written in the cluster directory associated with that point.

This class incorporates a sequential algorithm and is appropriate for use for data which has been clustered sequentially.

The sequential and non sequential version, both are being used from ClusterOutputPostProcessorDriver.

Constructor Summary

Constructors

Constructor and Description
ClusterOutputPostProcessor(org.apache.hadoop.fs.Path clusterOutputToBeProcessed, org.apache.hadoop.fs.Path output, org.apache.hadoop.conf.Configuration hadoopConfiguration)

Method Summary

Modifier and Type	Method and Description
Map<String,org.apache.hadoop.fs.Path>	getPostProcessedClusterDirectories()
void	process() This method takes the clustered points output by the clustering algorithms as input and writes them into their respective clusters.
void	setClusteredPoints(org.apache.hadoop.fs.Path clusteredPoints)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ClusterOutputPostProcessor

public ClusterOutputPostProcessor(org.apache.hadoop.fs.Path clusterOutputToBeProcessed,
                                  org.apache.hadoop.fs.Path output,
                                  org.apache.hadoop.conf.Configuration hadoopConfiguration)
                           throws IOException

Throws:

IOException

Method Detail

process

public void process()
             throws IOException

This method takes the clustered points output by the clustering algorithms as input and writes them into their respective clusters.

Throws:

IOException

getPostProcessedClusterDirectories

public Map<String,org.apache.hadoop.fs.Path> getPostProcessedClusterDirectories()

Returns:

the set of all post processed cluster paths.

setClusteredPoints

public void setClusteredPoints(org.apache.hadoop.fs.Path clusteredPoints)