Pages: [1]
  Print  
Author Topic: Missing W-Apriori Algorith  (Read 617 times)
monamahfouz
Newbie
*
Posts: 4


« on: July 06, 2014, 09:39:53 PM »

Hi everyone,

I am trying to look for the W-Apriori operator to use while doing a homework assignment. I can't find it anywhere when looking for it, even on the filter text box on the left hand side. I can find the FP-growth one alright. Worth noting I just accepted updates to Rapidminer 5.

Is that a known issue / do I need to install anything to get to use this operator?

Thanks a lot for helping out!
Mona
Logged
awchisholm
Sr. Member
****
Posts: 444


WWW
« Reply #1 on: July 06, 2014, 11:34:31 PM »

Hello Mona

You need to install the Weka extension. Go to Help->Updates and Extensions (Marketplace) then search for Weka. Follow the instructions to install this.

regards

Andrew
Logged

monamahfouz
Newbie
*
Posts: 4


« Reply #2 on: July 07, 2014, 05:29:57 PM »

This worked - thank you SO much!
Logged
monamahfouz
Newbie
*
Posts: 4


« Reply #3 on: July 07, 2014, 05:43:07 PM »

I was able to download the extension and can see the operator now, but the output is missing the actual itemsets! I left all default values as is, this is the output:

W-Apriori
Apriori
=======

Minimum support: 0.1 (3 instances)
Minimum metric <confidence>: 0.9
Number of cycles performed: 18

Generated sets of large itemsets:

Size of set of large itemsets L(1): 12

Size of set of large itemsets L(2): 3

Best rules found:


It doesn't list the actual itemsets. I am using Rapidminer 6.0.006 - any ideas?
Logged
Marco Boeck
Administrator
Hero Member
*****
Posts: 1258


WWW
« Reply #4 on: July 08, 2014, 08:13:53 AM »

Hi,

the apriori algorithm is about generating association rules - which are delivered by the operator. The frequent item sets are only an intermediate result.
If you actually want frequent item sets, you can use FP-Growth to get them.

Regards,
Marco
Logged

Are you from a scientific background and want to use RapidMiner Studio 6? Check out our new RapidMiner Academia program!
Pages: [1]
  Print  
 
Jump to: