BTW, you can also run all the synthetic control jobs with no arguments
and they will run with default arguments similar to those below. See the
various Job classes' main methods for per-algorithm defaults.
On 9/27/10 10:04 AM, Jeff Eastman wrote:
Are you running trunk? It should not be possible to get that error
any more since the initial clusters are internally computed by Canopy
and the -c argument has been removed from the K-means and Fuzzy
K-means synthetic control jobs. Try running trunk with the following
arguments:
-i testdata
-o output
-dm org.apache.mahout.common.distance.EuclideanDistanceMeasure
-t1 80
-t2 55
-x 10
-ow
-m 2
If you have a different set of arguments that can reproduce this
problem please post them and I will investigate further.
Jeff
On 9/27/10 6:29 AM, Lahiru Samarakoon wrote:
Dear All,
When I try to run the Synthetic Data example for Clustering using
K-means
and Fuzzy K-means algorithms following error was prompted.
Please advice.
10/09/27 15:42:23 INFO mapred.JobClient: Task Id :
attempt_201009271237_0012_m_000000_1, Status : FAILED
java.lang.IllegalStateException: Cluster is empty!!!
at
org.apache.mahout.clustering.fuzzykmeans.FuzzyKMeansClusterMapper.setup(FuzzyKMeansClusterMapper.java:55)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:621)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:305)
at org.apache.hadoop.mapred.Child.main(Child.java:170)
Thanks,
Lahiru.
