Re: [R] decision tree with weighted inputs

[Carlos Ortega]

Hi,

In the R-Help history there have been similar questions to yours. As a
starting point you can check this:

http://tolstoy.newcastle.edu.au/R/e2/help/07/01/9138.html

Regrads,
Carlos.

On Thu, Jul 22, 2010 at 6:37 PM, David Shin ds...@jumptrading.com wrote:

 I'd like to train a decision tree on a set of weighted data points.  I
 looked into the rpart package, which builds trees but doesn't seem to offer
 the capability of weighting inputs.  (There is a weights parameter, but it
 seems to correspond to output classes rather than to input points).

 I'm making do for now by preprocessing my input data by adding multiple
 instances of each data point corresponding to its weight before feeding to
 rpart.  But I worry this tricks the cross-validation phase of the rpart
 building process into thinking a model generalizes better than it really
 does.  This is because a heavily-weighted point can be included in both the
 training and testing set of a cross validation split.

 Is there a better way to achieve my goal?

 
 Note: This email is for the confidential use of the named addressee(s) only
 and may contain proprietary, confidential or privileged information. If you
 are not the intended recipient, you are hereby notified that any review,
 dissemination or copying of this email is strictly prohibited, and to please
 notify the sender immediately and destroy this email and any attachments.
 Email transmission cannot be guaranteed to be secure or error-free. Jump
 Trading, therefore, does not make any guarantees as to the completeness or
 accuracy of this email or any attachments. This email is for informational
 purposes only and does not constitute a recommendation, offer, request or
 solicitation of any kind to buy, sell, subscribe, redeem or perform any type
 of transaction of a financial product.

[[alternative HTML version deleted]]

 __
 R-help@r-project.org mailing list
 https://stat.ethz.ch/mailman/listinfo/r-help
 PLEASE do read the posting guide
 http://www.R-project.org/posting-guide.html
 and provide commented, minimal, self-contained, reproducible code.


[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] decision tree with weighted inputs

[David Shin]

I'd like to train a decision tree on a set of weighted data points.  I looked 
into the rpart package, which builds trees but doesn't seem to offer the 
capability of weighting inputs.  (There is a weights parameter, but it seems to 
correspond to output classes rather than to input points).

I'm making do for now by preprocessing my input data by adding multiple 
instances of each data point corresponding to its weight before feeding to 
rpart.  But I worry this tricks the cross-validation phase of the rpart 
building process into thinking a model generalizes better than it really does.  
This is because a heavily-weighted point can be included in both the training 
and testing set of a cross validation split.

Is there a better way to achieve my goal?


Note: This email is for the confidential use of the named addressee(s) only and 
may contain proprietary, confidential or privileged information. If you are not 
the intended recipient, you are hereby notified that any review, dissemination 
or copying of this email is strictly prohibited, and to please notify the 
sender immediately and destroy this email and any attachments. Email 
transmission cannot be guaranteed to be secure or error-free. Jump Trading, 
therefore, does not make any guarantees as to the completeness or accuracy of 
this email or any attachments. This email is for informational purposes only 
and does not constitute a recommendation, offer, request or solicitation of any 
kind to buy, sell, subscribe, redeem or perform any type of transaction of a 
financial product.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.