Pages: [1]
  Print  
Author Topic: which stopping criterion in dicretize by entropy  (Read 769 times)
pep
Newbie
*
Posts: 7


« on: May 15, 2011, 07:35:34 PM »

Hi
The specification of the discretize by entropy operator says: "The discretization is performed by selecting a bin boundary minimizing the entropy in the induced partitions. The method is then applied recursively for both new partitions until the stopping criterion is reached."
Which of the stopping criteria is used in this implementation (the one based on threshold of entropy? maximum number of bins?), and how can its parameter be set please? 
Cheers.
Logged
Sebastian Land
Administrator
Hero Member
*****
Posts: 2426


« Reply #1 on: May 17, 2011, 04:43:12 PM »

Hi,
actually I don't know myself, but the source code says, you should refer to

a) Multi-interval discretization of continued-values attributes for classification learning (Fayyad,Irani) and
b) Supervised and Unsupervised Discretization (Dougherty,Kohavi,Sahami).

Tell me if you know...

Greetings,
  Sebastian
Logged
Pages: [1]
  Print  
 
Jump to: