New Weka 3.4.5 and 3.5.0 releases

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

New Weka 3.4.5 and 3.5.0 releases

Mark Hall-11
Hi folks,

We've made a new release of Weka 3.4 and also made a development
release (3.5.0). The development release is for those people
interested in the latest features. Weka 3.4 is the version compatible
with the 2nd edition of the data mining book. You can download these
releases from the Weka home page:

http://www.cs.waikato.ac.nz/ml/weka

Cheers,
the Weka team.

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: New Weka 3.4.5 and 3.5.0 releases

Ed-11
Hi,
I am very interested in data mining and I used weka before and I also
used R. I have three concerns and hope I can get some help from here:
1. In R, the authors for packages of DM will refer to some papers they
use when they built the packages. So, I am wondering where I can find
those information. For example, when I want to do feature selection by
using Information Gain, I want to make sure InfoGainAttributeEval does
what I expect. Clicking "more" button on the "about" can help but I
hope I can get more details. I think I want to say, what kinds of
algorithms used here. Is there any document to describe them in
details?

2. I am wondering Weka's scalability on large dataset, like I have 200
attributes,  30,000 observations in training data?

3. Can anyone list some books or links you think most helpful for weka?

Thanks a lot,

Weiwei

On 7/4/05, Mark Hall <[hidden email]> wrote:

> Hi folks,
>
> We've made a new release of Weka 3.4 and also made a development
> release (3.5.0). The development release is for those people
> interested in the latest features. Weka 3.4 is the version compatible
> with the 2nd edition of the data mining book. You can download these
> releases from the Weka home page:
>
> http://www.cs.waikato.ac.nz/ml/weka
>
> Cheers,
> the Weka team.
>
> _______________________________________________
> Wekalist mailing list
> [hidden email]
> https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
>


--
"Did you always know that?"
"No, I didn't. But I believed"
   ---Matrix III

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: New Weka 3.4.5 and 3.5.0 releases

Peter Reutemann
> I am very interested in data mining and I used weka before and I also
> used R. I have three concerns and hope I can get some help from here:
> 1. In R, the authors for packages of DM will refer to some papers they
> use when they built the packages. So, I am wondering where I can find
> those information. For example, when I want to do feature selection by
> using Information Gain, I want to make sure InfoGainAttributeEval does
> what I expect. Clicking "more" button on the "about" can help but I
> hope I can get more details. I think I want to say, what kinds of
> algorithms used here. Is there any document to describe them in
> details?

There does no such single document exist. You'll have to check out the
javadoc of the single classifiers for references for papers. Some of
this stuff is explained in the book mentioned below.

> 2. I am wondering Weka's scalability on large dataset, like I have 200
> attributes,  30,000 observations in training data?

Since Weka loads the data normally into memory, it's only limited by the
memory Java can allocate. If you happen to use an incremental
classifier, e.g., NaiveBayesUpdateable you can use the KnowledgeFlow and
set up an incremental workflow to avoid memory problems.

> 3. Can anyone list some books or links you think most helpful for weka?

http://www.cs.waikato.ac.nz/~ml/weka/book.html

HTH

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
http://www.cs.waikato.ac.nz/~fracpete/     +64 (7) 838-4466 Ext. 5174

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist