Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
weighted event in decision tree

Subject: weighted event in decision tree

From: bembi prima

Date: 6 Nov, 2008 01:26:02

Message: 1 of 3

I want to implement boosted decision tree in matlab, that requires a weighted event used in decision trees. But, up to now, I desperately can't find how to weight an event used in classregtree() or treefit().
Is there a parameter that I can use in order to do that, or should I modify the data value, or should I even buiild a whole new decision tree algortihm?

Best regards,
Bembi

Subject: weighted event in decision tree

From: Ilya Narsky

Date: 7 Nov, 2008 16:20:37

Message: 2 of 3

Bembi,

the current implementation of classregtree does not weight observations.
You'd have to modify treefit code to do that.

If you have Computational Statistics Handbook with Matlab by the two
Martinezes, there are pointers to boosting code in the Supervised Learning
section. In particular, there is some code for boosting decision stumps
(trees with two leaves).

If you are interested in bagging decision trees and the algorithms described
by Breiman in his 2001 paper, feel free to get in touch with me privately.

-Ilya

"Bembi Prima" <puzzloholic@gmail.com> wrote in message
news:geth3a$la5$1@fred.mathworks.com...
>I want to implement boosted decision tree in matlab, that requires a
>weighted event used in decision trees. But, up to now, I desperately can't
>find how to weight an event used in classregtree() or treefit().
> Is there a parameter that I can use in order to do that, or should I
> modify the data value, or should I even buiild a whole new decision tree
> algortihm?
>
> Best regards,
> Bembi

Subject: weighted event in decision tree

From: Shiguo

Date: 14 Sep, 2011 01:50:28

Message: 3 of 3

"Bembi Prima" wrote in message <geth3a$la5$1@fred.mathworks.com>...
> I want to implement boosted decision tree in matlab, that requires a weighted event used in decision trees. But, up to now, I desperately can't find how to weight an event used in classregtree() or treefit().
> Is there a parameter that I can use in order to do that, or should I modify the data value, or should I even buiild a whole new decision tree algortihm?
>
> Best regards,
> Bembi

The 2011a version has boosted decision tree function now. see
http://www.mathworks.com/help/toolbox/stats/bsvjye9.html#bsvjyi5

Tags for this Thread

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us