See the response "Re: Clustering without hadoop" by Johannes Schulte two
postings earlier than yours on [email protected]. The driver functions can also
be run in sequential mode from a local file system and do not require
Hadoop. There are several examples of Java invocation in the unit tests.
TestClusterEvaluator.testKmeans() uses sequential execution from points
written to a local file.
On 11/13/12 4:37 AM, joshuathree wrote:
I am trying to cluster a sparse matrix with using K-means algorithm. I will
use Apache mahout but I did not find any example about how can it be
implement with Java. Is there any tutorial or function javadoc about it?
I have tried KmeansDriver's run() function but I did not give true
parameters. Trustly, I did not understand implementation of this function.
Is there a clear example about that which takes a matrix, dataset or file
and gives clustered data?
--
View this message in context:
http://lucene.472066.n3.nabble.com/Introduction-to-Apache-Mahout-K-means-clustering-tp4019975.html
Sent from the Mahout User List mailing list archive at Nabble.com.
