Hey,
I was testing the kmeans driver using the reuters data.
Commands used:
1. bin/mahout seqdirectory -c UTF-8 -i reuters/reuters21578 -o
reuters/reuters-seqfiles
2. bin/mahout seq2sparse -i reuters/reuters-seqfiles/ -o
reuters/reuters-vectors-bigram -ow -a
org.apache.lucene.analysis.Whitespace
...@lucene.apache.org
Subject: Exception while testing reuters data
Hey,
I was testing the kmeans driver using the reuters data.
Commands used:
1. bin/mahout seqdirectory -c UTF-8 -i reuters/reuters21578 -o
reuters/reuters-seqfiles
2. bin/mahout seq2sparse -i reuters/reuters-seqfiles/ -o
reuters
gt; From: sharath jagannath [mailto:sharathjagann...@gmail.com]
> Sent: Monday, June 20, 2011 11:40 AM
> To: mahout-u...@lucene.apache.org
> Subject: Exception while testing reuters data
>
> Hey,
>
> I was testing the kmeans driver using the reuters data.
>
> Commands us
Yup, please bear with us. Something about MAHOUT_LOCAL=true does not seem to
work on OS X.
-Original Message-
From: sharath jagannath [mailto:sharathjagann...@gmail.com]
Sent: Monday, June 20, 2011 10:15 PM
To: user@mahout.apache.org
Subject: Re: Exception while testing reuters data
I
Hi Sharath,
Does the reuters/reuters-vectors-bigram directory contain a
tfidf-vectors directory? If so, try using that as input. If not, what
is in that directory?
This sounds similar to the problem Hector ran into running one of the
examples from the mahout-in-action book.
Thanks,
Drew
On Mon
It is not working with tf-idf vectors too.
Yup, please bear with us. Something about MAHOUT_LOCAL=true does not seem to
work on OS X.
-- I was able to run bunch of other demo code. Is it just reuters? or
vectorizer?
Thanks,
Sharath
On Wed, Jun 22, 2011 at 1:37 PM, Drew Farris wrote:
> Hi Shar
Hi Sharath,
Just getting back to this -- what is in the reuters/reuters21578
directory? Are the text files of some sort or are they the
reuters-21578 sgm files from
http://kdd.ics.uci.edu/databases/reuters21578/reuters21578.tar.gz
To answer your original question -- there isn't anything in parti
