I think you need to add the --clustering (-cl) option to your KMeans step. By
default, we only calculate the centroids. FWIW, the ClusterDumper can also
dump out the points associated w/ a cluster once you have run the --clustering
step.
Also I don't think the clusterData/part-randomSeed is the directory you want.
On Nov 25, 2011, at 4:03 AM, syed kather wrote:
> Team,
> While reading the sequencial file . it is returning null
> These are the command which i executed.
> For Converting the Sequence File to Chunk(sequence vector) :
>
> raghu@Syed:/media/Work/mahout$ bin/mahout seqdirectory -i
> /media/Work/mahout/examples/bin/sample/fileList -o
> /media/Work/mahout/examples/bin/sample/seq-ve
>
> ctor -c UTF-8 -chunk 5
>
> For Converting the Chunk(sequence vector) to sparse :
>
> raghu@Syed:/media/Work/mahout$ bin/mahout seq2sparse -i
> /media/Work/mahout/examples/bin/sample/seq-vector/ -o
> /media/Work/mahout/examples/bin/sample/sparse
>
> For Converting the sparse to Cluster :
>
> raghu@Syed:/media/Work/mahout$ bin/mahout kmeans -i
> /media/Work/mahout/examples/bin/sample/sparse/tfidf-vectors/ -c
> /media/Work/mahout/examples/bin/sample/clusterData/ -o
> /media/Work/mahout/examples/bin/sample/clusers -x 10 -k 20 -ow
>
> For Converting the Cluster to clusterdump :
>
> raghu@Syed:/media/Work/mahout$ bin/mahout clusterdump -s
> /media/Work/mahout/examples/bin/sample/clusers/clusters-10 -d
> /media/Work/mahout/examples/bin/sample/sparse/dictionary.file-0 -dt
> sequencefile -b 100 n 20
> To get the documents which belong to cluster i wrote these code
> Configuration conf =new Configuration()
>
> Path path1=n*ew* Path("/media/Work/mahout/examples/bin/sample/clusterData/
> part-randomSeed");
>
> FileSystem fs = FileSystem.*get*(path1.toUri(),conf);
>
> SequenceFile.Reader reader = *new* SequenceFile.Reader(fs,path1, conf);
>
> IntWritable key = *new* IntWritable();
>
> WeightedVectorWritable value = *new* WeightedVectorWritable();
> *while* (reader.next(key, value))
> {
>
> System.*out*.println(value.toString() + " belongs to cluster "+
> key.toString());
>
> }
>
> reader.close();
> But it is returning null .
> Please help me to move further .
>
> Thanks and Regards,
> S SYED ABDUL KATHER
--------------------------------------------
Grant Ingersoll
http://www.lucidimagination.com
