Association Rule Generation

[muharrem aker]

 am new in WEKA and association rule mining. I have the file in arrf fomat I can open the file with Weka no problem but I can not get any result it thinks and thinks and then generates out of memory error. I dont have too many attributes and all my atributes are nominal. It should not be a problem  guess. Should the attributes be nominal in order to generate association rule. The only setiing i change is , I set lowerbound to 0.01 since what I have told.I have attached the file could you guys see what is wrong with it. What is the meaning of lowerbound. I have many null values for attributes but each attribute has at least one value. Is there any way to ommit null values .

 

Thanks

_______________________________________________
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]

>  am new in WEKA and association rule mining. I have the file in arrf fomat I
> can open the file with Weka no problem but I can not get any result it
> thinks and thinks and then generates out of memory error.

How much memory do you allow for the heap?

> I dont have too
> many attributes and all my atributes are nominal. It should not be a
> problem  guess. Should the attributes be nominal in order to generate
> association rule.

Apriori handles *only* nominal attributes.

> The only setiing i change is , I set lowerbound to 0.01
> since what I have told.

Normally, if one doesn't get any results with the default settings,
the lowerBoundMinSupport should be slowly lowered, until one gets
results.

Mark also fixed a bug in Apriori today regarding an infinite loop if
the lower bound was too small. Just grab a snapshot from the Weka
homepage, if you want this bugfix.

> I have attached the file could you guys see what is
> wrong with it. What is the meaning of lowerbound.

Copy/paste from Javadoc:
"Iteratively reduces the minimum support until it finds the required
number of rules with the given minimum confidence."

The following three parameters are used for this (once again,
copy/paste from Javadoc):

 -D <delta for minimum support>
  The delta by which the minimum support is decreased in
  each iteration. (default = 0.05)

 -U <upper bound for minimum support>
  Upper bound for minimum support. (default = 1.0)

 -M <lower bound for minimum support>
  The lower bound for the minimum support. (default = 0.1)

> I have many null values
> for attributes but each attribute has at least one value. Is there any way
> to ommit null values .

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