Re: Wekalist Digest, Vol 172, Issue 48

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Wekalist Digest, Vol 172, Issue 48

Pierre DEMAJ
Hello,

In the Explorer, I was able to sort by label values in the dataset editor and it generated exactly what I need.
However, I still observe a random permutation of the vectors with the supervised version of the Resample filter launched via CLI.
Could you check on your side?

Regards
Pierre


-----Original Message-----
From: [hidden email] [mailto:[hidden email]] On Behalf Of [hidden email]
Sent: Wednesday, June 14, 2017 1:42
To: [hidden email]
Subject: Wekalist Digest, Vol 172, Issue 48

Send Wekalist mailing list submissions to
        [hidden email]

To subscribe or unsubscribe via the World Wide Web, visit
        https://list.waikato.ac.nz/mailman/listinfo/wekalist
or, via email, send a message with subject or body 'help' to
        [hidden email]

You can reach the person managing the list at
        [hidden email]

When replying, please edit your Subject line so it is more specific than "Re: Contents of Wekalist digest..."


Today's Topics:

   1. Re: Look into a model (Mark Hall)
   2. Re: Explanation of misclassification (Mark Hall)
   3. Re: how to load a class from an installed package in java
      code (Mark Hall)
   4. Re: Explanation of misclassification (Alexander Osherenko)
   5. Re: Grouping similar labels (Eibe Frank)


----------------------------------------------------------------------

Message: 1
Date: Tue, 13 Jun 2017 09:50:31 -0400
From: Mark Hall <[hidden email]>
To: "Weka machine learning workbench list."
        <[hidden email]>
Subject: Re: [Wekalist] Look into a model
Message-ID: <[hidden email]>
Content-Type: text/plain; charset="UTF-8"

If you are using Weka's Vote meta classifier then it will print the base models in the output. For RandomForest, you will need to set the printClassifiers option to true (-print if you are using the command line) in order to see the individual trees in the forest.

Cheers,
Mark.

On 13/06/17, 1:40 AM, "Thomas Pfau" <[hidden email] on behalf of [hidden email]> wrote:

    Hi,
   
    I have a model represented by a voter combination of multiple random
    forests. I'm wondering, whether there is any way to actually have a look
    at the individual random forests i.e. see what the forests are
    doing/which decisions they make.
   
    Best
   
    Thomas
   
    --
    Universit? du Luxembourg
    Facult? des Sciences, de la Technologie et de la Communication
    Campus Belval, Biotech II 115
    6 avenue du Swing
    L-4367 Belvaux
    Tel: (+352) 46 66 44 5309
    Email: [hidden email]
   
    _______________________________________________
    Wekalist mailing list
    Send posts to: [hidden email]
    List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
    List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
   




------------------------------

Message: 2
Date: Tue, 13 Jun 2017 09:54:23 -0400
From: Mark Hall <[hidden email]>
To: "Weka machine learning workbench list."
        <[hidden email]>
Subject: Re: [Wekalist] Explanation of misclassification
Message-ID: <[hidden email]>
Content-Type: text/plain; charset="UTF-8"

Your best bet would be to read a good book on machine learning. Strengths, weaknesses and representational power of algorithms will be discussed, along with data characteristics that each is best suited to handle.

Cheers,
Mark.

On 13/06/17, 3:34 AM, "Alexander Osherenko" <[hidden email] on behalf of [hidden email]> wrote:

    I wonder: are there some articles that aim at the ?error explanation?? of
    classification results that consider ?the chosen classifier, the data or
    some other aspects and explain the probable reason of misclassification? For
    example, a typical answer of this question would be "a classifier works not
    good with sparse data" or "a classifier works not good because of data
    overfitting".
   
    Best, Alexander
   
   
   
    --
    View this message in context: http://weka.8497.n7.nabble.com/Explanation-of-misclassification-tp40936.html
    Sent from the WEKA mailing list archive at Nabble.com.
    _______________________________________________
    Wekalist mailing list
    Send posts to: [hidden email]
    List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
    List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
   




------------------------------

Message: 3
Date: Tue, 13 Jun 2017 10:02:04 -0400
From: Mark Hall <[hidden email]>
To: "Weka machine learning workbench list."
        <[hidden email]>
Subject: Re: [Wekalist] how to load a class from an installed package
        in java code
Message-ID: <[hidden email]>
Content-Type: text/plain; charset="UTF-8"

To get rid of the mtj warnings you will need the weka.jar file in your CLASSPATH. In order to instantiate learning schemes from packages, if you are using the package manager to load them, you will need to remove explicit imports of the scheme in question from your code, use the generic Classifier interface, and then create an object via the static WekaPackageClassLoaderManager.objectForName() method.

Alternatively, if you don't require lots of Weka packages in your application and, as a consequence, third-party library clashes won't be a problem, you can place the ClassificationViaClustering package's jar files into your CLASSPATH explicitly (rather than loading via the package manager). Then you can use explicit imports and normal object instantiation.

Cheers,
Mark.

On 13/06/17, 6:14 AM, "Ignacio Arganda-Carreras" <[hidden email] on behalf of [hidden email]> wrote:

    Dear all,
   
   
    I have installed the ClassificationViaClustering classifier using the package manager on my Weka 3.9.1 and now I would like to instantiate it from java code. So far I have not been successful and I can only load the classifier classes that come by default in the weka jar.
   
   
    This is what I tried:
   
    import weka.core.WekaPackageManager;
   
    WekaPackageManager.loadPackages( true );
   
   
    Which outputs:
   
    WARNING: core mtj jar files are not available as resources to this classloader (sun.misc.Launcher$AppClassLoader@764c12b6)
    [WekaPackageManager] loading package collective-classification
    [WekaPackageManager] loading package classificationViaClustering
    Registering weka.classifiers.collective.util.Flipper weka.gui.GenericObjectEditor
    Refreshing GOE props...
   
    So the package seems to be loaded, but then, when I try to instantiate it, I get a "class not found error":
   
    ClassificationViaClustering classifier = new ClassificationViaClustering();
   
   
    What am I missing?
   
   
    Thanks a lot in advance!
   
   
    ignacio
   
   
   
    --
    Ignacio Arganda-Carreras, Ph.D.
    Ikerbasque Research Fellow
    Departamento de Ciencia de la Computacion e Inteligencia Artificial
    Facultad de Informatica, Universidad del Pais Vasco
    Paseo de Manuel Lardizabal, 1
    20018 Donostia-San Sebastian
    Guipuzcoa, Spain
   
    Phone : +34 943 01 73 25
    Website: http://sites.google.com/site/iargandacarreras/ <http://biocomp.cnb.csic.es/%7Eiarganda/index_EN.html>
   
   
   
   
   
   
   
   
   
   
   
   
   
   
    _______________________________________________
    Wekalist mailing list
    Send posts to: [hidden email]
    List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
    List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
   




------------------------------

Message: 4
Date: Tue, 13 Jun 2017 19:52:27 +0100
From: Alexander Osherenko <[hidden email]>
To: "Weka machine learning workbench list."
        <[hidden email]>
Subject: Re: [Wekalist] Explanation of misclassification
Message-ID:
        <[hidden email]>
Content-Type: text/plain; charset="utf-8"

I read a couple of good books on machine learning, but they were not about the question I am interested in. Maybe, you can recommmend something?

Best, Alexander

2017-06-13 14:54 GMT+01:00 Mark Hall <[hidden email]>:

> Your best bet would be to read a good book on machine learning.
> Strengths, weaknesses and representational power of algorithms will be
> discussed, along with data characteristics that each is best suited to handle.
>
> Cheers,
> Mark.
>
> On 13/06/17, 3:34 AM, "Alexander Osherenko" <wekalist-bounces@list.
> waikato.ac.nz on behalf of [hidden email]> wrote:
>
>     I wonder: are there some articles that aim at the ?error explanation??
> of
>     classification results that consider ?the chosen classifier, the
> data or
>     some other aspects and explain the probable reason of
> misclassification? For
>     example, a typical answer of this question would be "a classifier
> works not
>     good with sparse data" or "a classifier works not good because of data
>     overfitting".
>
>     Best, Alexander
>
>
>
>     --
>     View this message in context: http://weka.8497.n7.nabble.
> com/Explanation-of-misclassification-tp40936.html
>     Sent from the WEKA mailing list archive at Nabble.com.
>     _______________________________________________
>     Wekalist mailing list
>     Send posts to: [hidden email]
>     List info and subscription status: https://list.waikato.ac.nz/ 
> mailman/listinfo/wekalist
>     List etiquette: http://www.cs.waikato.ac.nz/~
> ml/weka/mailinglist_etiquette.html
>
>
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email] List info and subscription
> status: https://list.waikato.ac.nz/ mailman/listinfo/wekalist List
> etiquette: http://www.cs.waikato.ac.nz/~
> ml/weka/mailinglist_etiquette.html
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://list.waikato.ac.nz/pipermail/wekalist/attachments/20170613/751093d1/attachment-0001.html>

------------------------------

Message: 5
Date: Wed, 14 Jun 2017 11:41:42 +1200
From: Eibe Frank <[hidden email]>
To: "Weka machine learning workbench list."
        <[hidden email]>
Subject: Re: [Wekalist] Grouping similar labels
Message-ID: <[hidden email]>
Content-Type: text/plain; charset=utf-8

In the Explorer, you can sort by column value in the dataset editor (click ?Edit?? in the Preprocess panel).

In the KnowledgeFlow, there is the ?Sorter? component, under ?Tools?.

A (hacky) way that works in all user interfaces is to use the supervised version of the Resample filter. A command-line example:

  java weka.Run .supervised.instance.Resample -no-replacement -c last < ~/datasets/UCI/optdigits.arff

Cheers,
Eibe

> On 14/06/2017, at 1:39 AM, Pierre DEMAJ <[hidden email]> wrote:
>
> Dear Weka experts,
>  
> I am using a .arff that looks like this:
>  
> 0.562,-0.90659,4.717,Class.1
> 1.762,-0.69157,3.022,Class.1
> 0.222,-0.2993,2.147,Class.1
> -1.435,-1.15904,3.751,Class.2
> -2.029,-0.22442,3.424,Class.2
> -0.331,0.65621,6.292,Class.2
> -2.242,-0.12325,3.294,Class.3
> -3.57,0.12794,5.052,Class.3
> -2.263,0.14772,3.362,Class.3
> -4.604,-0.71211,1.574,Class.3
> -1.722,-0.71604,5.424,Class.1
> -6.149,-0.43472,-1.944,Class.1
> -6.197,-0.22146,-2.302,Class.1
> -2.231,-1.1015,0.839,Class.2
> -3.172,-0.36353,1.795,Class.2
> -1.799,-0.93137,0.663,Class.2
>  
> I would like to group vectors of same classes without random permutation, so that the output arff looks like this:
>  
> 0.562,-0.90659,4.717,Class.1
> 1.762,-0.69157,3.022,Class.1
> 0.222,-0.2993,2.147,Class.1
> -1.722,-0.71604,5.424,Class.1
> -6.149,-0.43472,-1.944,Class.1
> -6.197,-0.22146,-2.302,Class.1
> -1.435,-1.15904,3.751,Class.2
> -2.029,-0.22442,3.424,Class.2
> -0.331,0.65621,6.292,Class.2
> -2.231,-1.1015,0.839,Class.2
> -3.172,-0.36353,1.795,Class.2
> -1.799,-0.93137,0.663,Class.2
> -2.242,-0.12325,3.294,Class.3
> -3.57,0.12794,5.052,Class.3
> -2.263,0.14772,3.362,Class.3
> -4.604,-0.71211,1.574,Class.3
>  
> Is there any Weka function that implement this ?
>  
> Thanks in advance for your help.
> Pierre
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email] List info and subscription
> status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette:
> http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html



------------------------------

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


End of Wekalist Digest, Vol 172, Issue 48
*****************************************
_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Wekalist Digest, Vol 172, Issue 48

Eibe Frank-2
Administrator
Did you use the command-line with the -no-replacement parameter? It appears to work fine for me, both with WEKA 3.8.1 and the latest trunk version of WEKA.

Cheers,
Eibe

> On 15/06/2017, at 12:41 AM, Pierre DEMAJ <[hidden email]> wrote:
>
> Hello,
>
> In the Explorer, I was able to sort by label values in the dataset editor and it generated exactly what I need.
> However, I still observe a random permutation of the vectors with the supervised version of the Resample filter launched via CLI.
> Could you check on your side?
>
> Regards
> Pierre
>
>
> -----Original Message-----
> From: [hidden email] [mailto:[hidden email]] On Behalf Of [hidden email]
> Sent: Wednesday, June 14, 2017 1:42
> To: [hidden email]
> Subject: Wekalist Digest, Vol 172, Issue 48
>
> Send Wekalist mailing list submissions to
> [hidden email]
>
> To subscribe or unsubscribe via the World Wide Web, visit
> https://list.waikato.ac.nz/mailman/listinfo/wekalist
> or, via email, send a message with subject or body 'help' to
> [hidden email]
>
> You can reach the person managing the list at
> [hidden email]
>
> When replying, please edit your Subject line so it is more specific than "Re: Contents of Wekalist digest..."
>
>
> Today's Topics:
>
>   1. Re: Look into a model (Mark Hall)
>   2. Re: Explanation of misclassification (Mark Hall)
>   3. Re: how to load a class from an installed package in java
>      code (Mark Hall)
>   4. Re: Explanation of misclassification (Alexander Osherenko)
>   5. Re: Grouping similar labels (Eibe Frank)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Tue, 13 Jun 2017 09:50:31 -0400
> From: Mark Hall <[hidden email]>
> To: "Weka machine learning workbench list."
> <[hidden email]>
> Subject: Re: [Wekalist] Look into a model
> Message-ID: <[hidden email]>
> Content-Type: text/plain; charset="UTF-8"
>
> If you are using Weka's Vote meta classifier then it will print the base models in the output. For RandomForest, you will need to set the printClassifiers option to true (-print if you are using the command line) in order to see the individual trees in the forest.
>
> Cheers,
> Mark.
>
> On 13/06/17, 1:40 AM, "Thomas Pfau" <[hidden email] on behalf of [hidden email]> wrote:
>
>    Hi,
>
>    I have a model represented by a voter combination of multiple random
>    forests. I'm wondering, whether there is any way to actually have a look
>    at the individual random forests i.e. see what the forests are
>    doing/which decisions they make.
>
>    Best
>
>    Thomas
>
>    --
>    Universit? du Luxembourg
>    Facult? des Sciences, de la Technologie et de la Communication
>    Campus Belval, Biotech II 115
>    6 avenue du Swing
>    L-4367 Belvaux
>    Tel: (+352) 46 66 44 5309
>    Email: [hidden email]
>
>    _______________________________________________
>    Wekalist mailing list
>    Send posts to: [hidden email]
>    List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
>    List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
>
>
> ------------------------------
>
> Message: 2
> Date: Tue, 13 Jun 2017 09:54:23 -0400
> From: Mark Hall <[hidden email]>
> To: "Weka machine learning workbench list."
> <[hidden email]>
> Subject: Re: [Wekalist] Explanation of misclassification
> Message-ID: <[hidden email]>
> Content-Type: text/plain; charset="UTF-8"
>
> Your best bet would be to read a good book on machine learning. Strengths, weaknesses and representational power of algorithms will be discussed, along with data characteristics that each is best suited to handle.
>
> Cheers,
> Mark.
>
> On 13/06/17, 3:34 AM, "Alexander Osherenko" <[hidden email] on behalf of [hidden email]> wrote:
>
>    I wonder: are there some articles that aim at the ?error explanation?? of
>    classification results that consider ?the chosen classifier, the data or
>    some other aspects and explain the probable reason of misclassification? For
>    example, a typical answer of this question would be "a classifier works not
>    good with sparse data" or "a classifier works not good because of data
>    overfitting".
>
>    Best, Alexander
>
>
>
>    --
>    View this message in context: http://weka.8497.n7.nabble.com/Explanation-of-misclassification-tp40936.html
>    Sent from the WEKA mailing list archive at Nabble.com.
>    _______________________________________________
>    Wekalist mailing list
>    Send posts to: [hidden email]
>    List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
>    List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
>
>
> ------------------------------
>
> Message: 3
> Date: Tue, 13 Jun 2017 10:02:04 -0400
> From: Mark Hall <[hidden email]>
> To: "Weka machine learning workbench list."
> <[hidden email]>
> Subject: Re: [Wekalist] how to load a class from an installed package
> in java code
> Message-ID: <[hidden email]>
> Content-Type: text/plain; charset="UTF-8"
>
> To get rid of the mtj warnings you will need the weka.jar file in your CLASSPATH. In order to instantiate learning schemes from packages, if you are using the package manager to load them, you will need to remove explicit imports of the scheme in question from your code, use the generic Classifier interface, and then create an object via the static WekaPackageClassLoaderManager.objectForName() method.
>
> Alternatively, if you don't require lots of Weka packages in your application and, as a consequence, third-party library clashes won't be a problem, you can place the ClassificationViaClustering package's jar files into your CLASSPATH explicitly (rather than loading via the package manager). Then you can use explicit imports and normal object instantiation.
>
> Cheers,
> Mark.
>
> On 13/06/17, 6:14 AM, "Ignacio Arganda-Carreras" <[hidden email] on behalf of [hidden email]> wrote:
>
>    Dear all,
>
>
>    I have installed the ClassificationViaClustering classifier using the package manager on my Weka 3.9.1 and now I would like to instantiate it from java code. So far I have not been successful and I can only load the classifier classes that come by default in the weka jar.
>
>
>    This is what I tried:
>
>    import weka.core.WekaPackageManager;
>
>    WekaPackageManager.loadPackages( true );
>
>
>    Which outputs:
>
>    WARNING: core mtj jar files are not available as resources to this classloader (sun.misc.Launcher$AppClassLoader@764c12b6)
>    [WekaPackageManager] loading package collective-classification
>    [WekaPackageManager] loading package classificationViaClustering
>    Registering weka.classifiers.collective.util.Flipper weka.gui.GenericObjectEditor
>    Refreshing GOE props...
>
>    So the package seems to be loaded, but then, when I try to instantiate it, I get a "class not found error":
>
>    ClassificationViaClustering classifier = new ClassificationViaClustering();
>
>
>    What am I missing?
>
>
>    Thanks a lot in advance!
>
>
>    ignacio
>
>
>
>    --
>    Ignacio Arganda-Carreras, Ph.D.
>    Ikerbasque Research Fellow
>    Departamento de Ciencia de la Computacion e Inteligencia Artificial
>    Facultad de Informatica, Universidad del Pais Vasco
>    Paseo de Manuel Lardizabal, 1
>    20018 Donostia-San Sebastian
>    Guipuzcoa, Spain
>
>    Phone : +34 943 01 73 25
>    Website: http://sites.google.com/site/iargandacarreras/ <http://biocomp.cnb.csic.es/%7Eiarganda/index_EN.html>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>    _______________________________________________
>    Wekalist mailing list
>    Send posts to: [hidden email]
>    List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
>    List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
>
>
> ------------------------------
>
> Message: 4
> Date: Tue, 13 Jun 2017 19:52:27 +0100
> From: Alexander Osherenko <[hidden email]>
> To: "Weka machine learning workbench list."
> <[hidden email]>
> Subject: Re: [Wekalist] Explanation of misclassification
> Message-ID:
> <[hidden email]>
> Content-Type: text/plain; charset="utf-8"
>
> I read a couple of good books on machine learning, but they were not about the question I am interested in. Maybe, you can recommmend something?
>
> Best, Alexander
>
> 2017-06-13 14:54 GMT+01:00 Mark Hall <[hidden email]>:
>
>> Your best bet would be to read a good book on machine learning.
>> Strengths, weaknesses and representational power of algorithms will be
>> discussed, along with data characteristics that each is best suited to handle.
>>
>> Cheers,
>> Mark.
>>
>> On 13/06/17, 3:34 AM, "Alexander Osherenko" <wekalist-bounces@list.
>> waikato.ac.nz on behalf of [hidden email]> wrote:
>>
>>    I wonder: are there some articles that aim at the ?error explanation??
>> of
>>    classification results that consider ?the chosen classifier, the
>> data or
>>    some other aspects and explain the probable reason of
>> misclassification? For
>>    example, a typical answer of this question would be "a classifier
>> works not
>>    good with sparse data" or "a classifier works not good because of data
>>    overfitting".
>>
>>    Best, Alexander
>>
>>
>>
>>    --
>>    View this message in context: http://weka.8497.n7.nabble.
>> com/Explanation-of-misclassification-tp40936.html
>>    Sent from the WEKA mailing list archive at Nabble.com.
>>    _______________________________________________
>>    Wekalist mailing list
>>    Send posts to: [hidden email]
>>    List info and subscription status: https://list.waikato.ac.nz/ 
>> mailman/listinfo/wekalist
>>    List etiquette: http://www.cs.waikato.ac.nz/~
>> ml/weka/mailinglist_etiquette.html
>>
>>
>>
>> _______________________________________________
>> Wekalist mailing list
>> Send posts to: [hidden email] List info and subscription
>> status: https://list.waikato.ac.nz/ mailman/listinfo/wekalist List
>> etiquette: http://www.cs.waikato.ac.nz/~
>> ml/weka/mailinglist_etiquette.html
>>
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://list.waikato.ac.nz/pipermail/wekalist/attachments/20170613/751093d1/attachment-0001.html>
>
> ------------------------------
>
> Message: 5
> Date: Wed, 14 Jun 2017 11:41:42 +1200
> From: Eibe Frank <[hidden email]>
> To: "Weka machine learning workbench list."
> <[hidden email]>
> Subject: Re: [Wekalist] Grouping similar labels
> Message-ID: <[hidden email]>
> Content-Type: text/plain; charset=utf-8
>
> In the Explorer, you can sort by column value in the dataset editor (click ?Edit?? in the Preprocess panel).
>
> In the KnowledgeFlow, there is the ?Sorter? component, under ?Tools?.
>
> A (hacky) way that works in all user interfaces is to use the supervised version of the Resample filter. A command-line example:
>
>  java weka.Run .supervised.instance.Resample -no-replacement -c last < ~/datasets/UCI/optdigits.arff
>
> Cheers,
> Eibe
>
>> On 14/06/2017, at 1:39 AM, Pierre DEMAJ <[hidden email]> wrote:
>>
>> Dear Weka experts,
>>
>> I am using a .arff that looks like this:
>>
>> 0.562,-0.90659,4.717,Class.1
>> 1.762,-0.69157,3.022,Class.1
>> 0.222,-0.2993,2.147,Class.1
>> -1.435,-1.15904,3.751,Class.2
>> -2.029,-0.22442,3.424,Class.2
>> -0.331,0.65621,6.292,Class.2
>> -2.242,-0.12325,3.294,Class.3
>> -3.57,0.12794,5.052,Class.3
>> -2.263,0.14772,3.362,Class.3
>> -4.604,-0.71211,1.574,Class.3
>> -1.722,-0.71604,5.424,Class.1
>> -6.149,-0.43472,-1.944,Class.1
>> -6.197,-0.22146,-2.302,Class.1
>> -2.231,-1.1015,0.839,Class.2
>> -3.172,-0.36353,1.795,Class.2
>> -1.799,-0.93137,0.663,Class.2
>>
>> I would like to group vectors of same classes without random permutation, so that the output arff looks like this:
>>
>> 0.562,-0.90659,4.717,Class.1
>> 1.762,-0.69157,3.022,Class.1
>> 0.222,-0.2993,2.147,Class.1
>> -1.722,-0.71604,5.424,Class.1
>> -6.149,-0.43472,-1.944,Class.1
>> -6.197,-0.22146,-2.302,Class.1
>> -1.435,-1.15904,3.751,Class.2
>> -2.029,-0.22442,3.424,Class.2
>> -0.331,0.65621,6.292,Class.2
>> -2.231,-1.1015,0.839,Class.2
>> -3.172,-0.36353,1.795,Class.2
>> -1.799,-0.93137,0.663,Class.2
>> -2.242,-0.12325,3.294,Class.3
>> -3.57,0.12794,5.052,Class.3
>> -2.263,0.14772,3.362,Class.3
>> -4.604,-0.71211,1.574,Class.3
>>
>> Is there any Weka function that implement this ?
>>
>> Thanks in advance for your help.
>> Pierre
>> _______________________________________________
>> Wekalist mailing list
>> Send posts to: [hidden email] List info and subscription
>> status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
>> List etiquette:
>> http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
> ------------------------------
>
> _______________________________________________
> Wekalist mailing list
> [hidden email]
> https://list.waikato.ac.nz/mailman/listinfo/wekalist
>
>
> End of Wekalist Digest, Vol 172, Issue 48
> *****************************************
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Loading...