GeneralizaedSequentialPatterns

[Laura Lozano]

Hello,

I am starting with GeneralizaedSequentialPatterns algorithm. I`ve tried to use the algorithm with a test set(gsp.arff) that Peter provided in a previous mail. I load the data set in the explorer without problem. But when I go to the tab Associate to try GeneralizaedSequentialPatterns, it is not active, I mean, when I press the button Choose in Associator, GeneralizaedSequentialPatterns appears in ligth gray, so I cant use it. Is there anybody that has been worked with the algorithm without problem?

Also, is there a way to specify a min gap or taxonomical knowledge about
items such as described in the paper that the algorithm is based on?.

Thank you very much.

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

[asma ben zakour]

Hello,

If  you want to run GSP you can do it on the simple CLI  commande with this one :

 weka.associations.GeneralizedSequentialPatterns -t "c:\GSP.arff" -S 0.3 -I 0 -F -1

the S option specify the min support , I specify the rank of id sequence attrbute , anf F to indicate the attribute to ignore.
 but, in this implementaion there is no  times conttraints ( Ws, min gap and max gap)
you can use SPADE algo : in this link 
rpi.edu/~zaki/www-new/pmwiki.php/Software/Software#toc9

cheers
Asma

2009/11/4 Laura Lozano <laurloz83@...>

Hello,

I am starting with GeneralizaedSequentialPatterns algorithm. I`ve tried to use the algorithm with a test set(gsp.arff) that Peter provided in a previous mail. I load the data set in the explorer without problem. But when I go to the tab Associate to try GeneralizaedSequentialPatterns, it is not active, I mean, when I press the button Choose in Associator, GeneralizaedSequentialPatterns appears in ligth gray, so I cant use it. Is there anybody that has been worked with the algorithm without problem?

Also, is there a way to specify a min gap or taxonomical knowledge about
items such as described in the paper that the algorithm is based on?.

Thank you very much.

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

[Laura Lozano]

I have another question about GeneralizedSequentialPatterns, is there any implementation to generate the rules from the frequent sequences generated?

And what about SPADE, Asma? I have been looking the link, but I think you can only generate the frequent secuences, not rules.

Thank you very much.

2009/11/4 asma ben zakour <asma.b.zakour@...>

Hello,

If  you want to run GSP you can do it on the simple CLI  commande with this one :

 weka.associations.GeneralizedSequentialPatterns -t "c:\GSP.arff" -S 0.3 -I 0 -F -1

the S option specify the min support , I specify the rank of id sequence attrbute , anf F to indicate the attribute to ignore.
 but, in this implementaion there is no  times conttraints ( Ws, min gap and max gap)
you can use SPADE algo : in this link 
rpi.edu/~zaki/www-new/pmwiki.php/Software/Software#toc9

cheers
Asma

2009/11/4 Laura Lozano <laurloz83@...>

Hello,

I am starting with GeneralizaedSequentialPatterns algorithm. I`ve tried to use the algorithm with a test set(gsp.arff) that Peter provided in a previous mail. I load the data set in the explorer without problem. But when I go to the tab Associate to try GeneralizaedSequentialPatterns, it is not active, I mean, when I press the button Choose in Associator, GeneralizaedSequentialPatterns appears in ligth gray, so I cant use it. Is there anybody that has been worked with the algorithm without problem?

Also, is there a way to specify a min gap or taxonomical knowledge about
items such as described in the paper that the algorithm is based on?.

Thank you very much.

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

[asma ben zakour]

Sorry, I have no idea about  generating rules rom frequent sequences !!

2009/11/4 Laura Lozano <laurloz83@...>

I have another question about GeneralizedSequentialPatterns, is there any implementation to generate the rules from the frequent sequences generated?

And what about SPADE, Asma? I have been looking the link, but I think you can only generate the frequent secuences, not rules.

Thank you very much.

2009/11/4 asma ben zakour <asma.b.zakour@...>

Hello,

If  you want to run GSP you can do it on the simple CLI  commande with this one :

 weka.associations.GeneralizedSequentialPatterns -t "c:\GSP.arff" -S 0.3 -I 0 -F -1

the S option specify the min support , I specify the rank of id sequence attrbute , anf F to indicate the attribute to ignore.
 but, in this implementaion there is no  times conttraints ( Ws, min gap and max gap)
you can use SPADE algo : in this link 
rpi.edu/~zaki/www-new/pmwiki.php/Software/Software#toc9

cheers
Asma

2009/11/4 Laura Lozano <laurloz83@...>

Hello,

I am starting with GeneralizaedSequentialPatterns algorithm. I`ve tried to use the algorithm with a test set(gsp.arff) that Peter provided in a previous mail. I load the data set in the explorer without problem. But when I go to the tab Associate to try GeneralizaedSequentialPatterns, it is not active, I mean, when I press the button Choose in Associator, GeneralizaedSequentialPatterns appears in ligth gray, so I cant use it. Is there anybody that has been worked with the algorithm without problem?

Also, is there a way to specify a min gap or taxonomical knowledge about
items such as described in the paper that the algorithm is based on?.

Thank you very much.

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

[Peter Reutemann-3]

> I am starting with GeneralizaedSequentialPatterns algorithm. I`ve tried to
> use the algorithm with a test set(gsp.arff) that Peter provided in a
> previous mail. I load the data set in the explorer without problem. But when
> I go to the tab Associate to try GeneralizaedSequentialPatterns, it is not
> active, I mean, when I press the button Choose in Associator,
> GeneralizaedSequentialPatterns appears in ligth gray, so I cant use it. Is
> there anybody that has been worked with the algorithm without problem?

That's a bug in 3.6.1 and 3.7.0. Just update your version of Weka by
grabbing a snapshot of your version of Weka from the Weka homepage.

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
http://www.cs.waikato.ac.nz/~fracpete/           Ph. [phone]

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

[Peter Reutemann-3]

> I have another question about GeneralizedSequentialPatterns, is there any
> implementation to generate the rules from the frequent sequences generated?

No with the Weka version.

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
http://www.cs.waikato.ac.nz/~fracpete/           Ph. [phone]

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