Not sure unless I intetionally reproduce this situation, however, Mahout
recommendation seems to be senstive to the carriage code placed at the end
of your final input data record.
For instance,
If your final data record ends like
5 105
5 106CRLF
End of File
and have no succeeding recods, I
You can't have a blank line, if that's what you mean, yes. That's not
a valid record. A terminal newline is fine.
But the error seems to be something else:
java.io.FileNotFoundException: File does not exist:
/user/hadoop/temp/preparePreferenceMatrix/numUsers.bin
In k-means clustering, the clusters are characterized by their mean
vectors, and data samples belong to clusters according to the distance to
these means. If distance is measured using the L-2 norm (Euclidean
distance), assigning data samples to clusters is equivalent to using
maximum likelihood,
Well, my Mahout-0.8-SNAPSHOT is now fine with the analyzer option
org.apache.lucene.analysis.core.WhitespaceAnalyzer, but there are still
some steps to get over with...
This could be the Hadoop version incompatibility issue and if so, then what
should be the right/minimum Hadoop version? (At least
Its definitely not a Mahout-Hadoop compatibility issue and is more to do with
your hadoop setup.
Check this link:
http://stackoverflow.com/questions/15585630/file-jobtracker-info-could-only-be-replicated-to-0-nodes-instead-of-1
From: 万代豊
On Sat, May 11, 2013 at 9:43 AM, Matthew McClain mattmccla...@gmail.comwrote:
This constraint can be
removed by characterizing each cluster by the mean and covariance of its
samples, and using maximum likelihood in place of the distance measurement
for assigning clusters to samples.
Just a
I've found the problem. The separator should be comma. When I use space
with separator , I got the those errors.
Thanks everyone for helping me.
I will pay attention on separator next time.
[Successful Log]
===
[hadoop@localhost