[kepler-users] How to integrate Weka into Kepler? (Mark V)

Tue Apr 22 07:04:09 PDT 2008

Mark,
Rapidminer includes Weka and adds more functionalities and
visualisation tools by means of its graphical environment. So, you are
right that YALE (rapidminer) exceeds Weka in that context, but do not
supersedes it. Weka maintains its independence allied now with Pentaho
(www.pentaho.com), a commercial Open Source Business Intelligence
Platform. Weka is the largest and the most well-known data mining
algorithm collection. Thus, in some way or another YALE depends on the
success of Weka but not in the other way! I've seen Weka embedded in a
lot of projects but never YALE! Probably that is to the dual Licensing
model of YALE, free license (GPL) and proprietary license
(http://rapid-i.com/content/view/16/39/lang,en)

To sum up, it would be extremely useful to have also YALE embedded to
Kepler but it seems to me that Weka is much more embeddable that YALE,
the power of Yale comes basically from its graphical interface unlike
Weka which comes from its machine learning algorithms, easily
embeddable! So, Mark, the question is how to integrate the YALE
graphical interface to Kepler?

Josep Maria,

>  Today's Topics:
>
>    1. Re:  How to integrate Weka into Kepler? (Mark V)
>
>
>  ----------------------------------------------------------------------
>
>  Message: 1
>  Date: Fri, 18 Apr 2008 10:02:51 +1000
>  From: "Mark V" <mvyver at gmail.com>
>  Subject: Re: [kepler-users] How to integrate Weka into Kepler?
>  To: kepler-users at ecoinformatics.org
>  Message-ID:
>         <389c43e40804171702v28354613m7d22e5d4a813ecbf at mail.gmail.com>
>  Content-Type: text/plain; charset=ISO-8859-1
>
>  On Fri, Apr 18, 2008 at 4:23 AM, Ilkay Altintas <altintas at sdsc.edu> wrote:
>  > Hi Josep,
>  >
>  > Thanks for your proposal to integrate Weka into Kepler. We've been
>  > considering this as it is needed in Kepler for many projects.
>  >
>
>  I haven't used weka in anger, but intended to in a few months and
>  hopefully via kepler.... My understanding was that YALE superceeded
>  Weka and YALE has been renamed RapidMiner.  IIRC RapidMiner is still
>  open source.  Did I misunderstand the ancestry and Rapid Miner doesn't
>  replace Weka?  Is there some other reason for not building on top of
>  RapidMiner?
>
>  Cheers
>  Mark
>
>  > An alternative approach might be integrating Weka Web Services using
>  > Kepler's WebService actors. Have you looked into Weka4WS at
>  > http://grid.deis.unical.it/weka4ws/? I meant to do it a while back, but
>  > didn't get the chance.
>  >
>  > I would be interested in collaborating with you on this as I need it for a
>  > research project.
>  >
>  > Thank you!
>  > -ilkay
>  >
>  >
>  >
>  > --
>  > Ilkay ALTINTAS
>  > Lab Director, Scientific Workflow Automation Technologies (SWAT)
>  > San Diego Supercomputer Center(SDSC), UCSD
>  > 9500 Gilman Drive, MC: 0505  La Jolla, CA  92093-0505
>  > phone: (858) 822-5453                        fax: (858) 534-8303
>  > web: http://users.sdsc.edu/~altintas
>  >
>  >
>  >
>  > On Apr 17, 2008, at 8:43 AM, Josep Maria Campanera Alsina wrote:
>  > Dear Community,
>  > I'd like to integrate Weka 3.5.7 into the Kepler environment. Weka is
>  > the most well-known data mining library. It is written in Java
>  > http://www.cs.waikato.ac.nz/ml/weka/.
>  > I consider this software extremely useful and it would add numerous
>  > capabilities to Kepler, like R did! Weka includes: data sources,
>  > Datasinks, filters, classifiers, clusterers, associations, evaluation
>  > and visualization tools! to sum up, It is another piece of jewellery
>  > like kepler!
>  >
>  > Well, there several ways to do that:
>  > (1) Using the RWeka project.
>  > http://cran.r-project.org/web/packages/RWeka/index.html
>  > Then the Weka algorithms can be called like R commands in the R
>  > console actor of Kepler. However it doesn't seem the more powerful way
>  > since Weka algorithms are also designed to run under a workflow
>  > environment (KnowledgeFlow environment).
>  >
>  > (2) Fully integrated: each Weka algorithm is converted to a Kepler
>  > actor. Here comes my advice request. Which is the more efficient way
>  > to undertake that process? Weka is open source software issued under
>  > the GNU General Public License. So, java and class files for each
>  > algorithm are completely available. Since I'm not a computer scientist
>  > the only idea that comes to my mind is to embed/add the Weka java code
>  > into the standard anatomy of a java Kepler actor code (ports,
>  > parameters, action methods ...). Definitely this is a very tedious and
>  > never ending task (it has to be done individually for each algorithm).
>  > An ideas how to tackle that? Anyone can envisage a faster and more
>  > systematic alternative?
>  >
>  > Best wishes,
>  >
>  > Josep Maria,
>  >
>  >
>  > ---------------------------------------------
>  > Josep Maria Campanera Alsina
>  > Juan de la Cierva Researcher
>  > Departament de Fisicoqu?mica
>  > Facultat de Farm?cia
>  > Avgda Joan XXIII, s/n
>  > 08028 Barcelona ? Catalonia ? Spain
>  > Tel: +34 93 4035988
>  > Fax: +34 93 4035987
>  > campanera at ub.edu
>  > --------------------------------------------
>  > _______________________________________________
>  > Kepler-users mailing list
>  > Kepler-users at ecoinformatics.org
>  > http://mercury.nceas.ucsb.edu/ecoinformatics/mailman/listinfo/kepler-users
>  >
>  >
>  > _______________________________________________
>  >  Kepler-users mailing list
>  >  Kepler-users at ecoinformatics.org
>  >  http://mercury.nceas.ucsb.edu/ecoinformatics/mailman/listinfo/kepler-users
>  >
>  >
>
>
>  ------------------------------
>
>  _______________________________________________
>  Kepler-users mailing list
>  Kepler-users at ecoinformatics.org
>  http://mercury.nceas.ucsb.edu/ecoinformatics/mailman/listinfo/kepler-users
>
>
>  End of Kepler-users Digest, Vol 35, Issue 8
>  *******************************************
>