mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Paritosh Ranjan <pran...@xebia.com>
Subject Re: t3 and t4 : CanopyDriver
Date Sun, 02 Oct 2011 08:42:06 GMT
I found this link about t3 and t4 parameters.

http://mail-archives.apache.org/mod_mbox/mahout-user/201106.mbox/%3C99CF5A2B2A1D9542A589C5F5EBD3DA03040B124B14@rock.narus.com%3E

This discussion, says that, t3 and t4 values needs to be guessed. And, 
the vectors will not be that sparse in reduce phase.
I have tried t1/1000000000 and t2/1000000000 values for t3 and t4. Still 
it does not work.

I am stuck due to this, because I am getting different results on 
sequential and mapreduce for Canopy Clustering, and, I am not able to 
guess t3 and t4's value which is supposed to solve this problem ( 
according to the discussion in the link pasted above ).

Can someone help me?

On 01-10-2011 17:41, Paritosh Ranjan wrote:
> Hi,
>
> I am not able to find any info on what t3 and t4 parameters are in 
> CanopyDriver's run method. Can someone explain these two parameters ( 
> t3 and t4 )  or point me to a link where it is explained?
>
> PS : In CanopyClustering's explanation I only see t1 and t2 which I 
> understand.
>
> Thanks and Regards,
> Paritosh Ranjan
>
>
> -----
> No virus found in this message.
> Checked by AVG - www.avg.com
> Version: 10.0.1410 / Virus Database: 1520/3932 - Release Date: 10/01/11


Mime
View raw message