Mahout 0.3 depends on Hadoop 0.20.2 so that could be an issue. It's
always better to try things out on trunk if you have problems as Mahout
is still changing rapidly. It is possible that particular example had a
problem in 0.3 but the examples are all working in trunk now.
On 7/8/10 9:38 PM, Amit Kolhe wrote:
Hi Jeff,
Thanks for response.
I am using version 0.3 not trunk.
Job name is KMean...
bin/hadoop jar
$MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job
org.apache.mahout.clustering.syntheticcontrol.kmeans.Job
right now using hadoop-0.19.0 on single node.
Meantime will try out trunk version too..
Regards,
Amit
-----Original Message-----
From: Jeff Eastman [mailto:[email protected]]
Sent: Thursday, July 08, 2010 9:44 PM
To: [email protected]
Subject: Re: Getting error while running Synthetic Control Data clustering
example
Hi Amit,
Can you please provide more information? What version (0.3 or trunk)?
Which Job (Canopy and KMeans both use Canopy)? What is your command line
invocation? What is your hardware configuration (Hadoop (cluster size),
stand-alone)? Have you verified the data file is in examples/testdata?
I've just run both Canopy and KMeans from trunk stand-alone without error.
Jeff
On 7/8/10 5:36 AM, Amit Kolhe wrote:
Hi All,
I am getting below error while running Synthetic Control Data clustering
example.
10/07/08 18:16:40 INFO mapred.JobClient: Task Id :
attempt_201007081615_0014_m_000001_0, Status : FAILED
org.apache.mahout.math.CardinalityException: My cardinality is: 0, but the
other is: 60
at
org.apache.mahout.math.RandomAccessSparseVector.dot(RandomAccessSparseVector
.java:275)
at
org.apache.mahout.common.distance.SquaredEuclideanDistanceMeasure.distance(S
quaredEuclideanDistanceMeasure.java:57)
at
org.apache.mahout.common.distance.EuclideanDistanceMeasure.distance(Euclidea
nDistanceMeasure.java:39)
at
org.apache.mahout.clustering.canopy.CanopyClusterer.addPointToCanopies(Canop
yClusterer.java:108)
at
org.apache.mahout.clustering.canopy.CanopyMapper.map(CanopyMapper.java:49)
at
org.apache.mahout.clustering.canopy.CanopyMapper.map(CanopyMapper.java:34)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:50)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:332)
at org.apache.hadoop.mapred.Child.main(Child.java:155)
thanks and regards,
amit
