Pages: [1]
  Print  
Author Topic: order rules by support value (APRIORI algorithm)  (Read 1259 times)
GC
Guest
« on: March 19, 2009, 03:49:57 PM »

Hi,

when using the APRIORI algorithm for itemset extraction, rules are by default ranked by confidence.
How can I rank the rules by support value? By changing the T parameter? Which value should T have?

Many thanks in advance.
Geert
Logged
Sebastian Land
Administrator
Hero Member
*****
Posts: 2426


« Reply #1 on: March 20, 2009, 04:40:46 PM »

Hi Geert,
 
as far as I can see, you are using a WEKA operator. Unfortunately we cannot give support for their operators, mainly because we don't know them either. I would suggest using the FPGrowth implementation of rapid miner. If you have enough memory, this algorithm is a much faster alternative to apriori and the results are shown in a much more userfriendly way. You can apply the association rule generator afterwards and you will be able to sort the table in one click after any of the measures.
 

Greetings,
  Sebastian
Logged
GC
Guest
« Reply #2 on: March 27, 2009, 08:52:19 AM »

Hi,

and how can I rank the rules by support value? Only confidence,lift, conviction, ps, gain and laplace can be selected in my gui window?

Thanks a lot,
Geert
Logged
Ingo Mierswa
Administrator
Hero Member
*****
Posts: 1226



WWW
« Reply #3 on: March 31, 2009, 11:17:07 AM »

Hi,

simply click on the column header "Support" in the table should sort the itemsets or rules according to the selected column. This is true for almost all tables presented in RapidMiner.

Cheers,
Ingo
Logged

Did you try our new Marketplace? Upload or download new Extensions, add comments, and organize your operators. Have a look at  http://marketplace.rapid-i.com
Pages: [1]
  Print  
 
Jump to: