The package has a doc/ subdirectory (in the pre-compiled package, or
inst/doc in the source package), which contains yaImputePaper.pdf. Page
9 of that document may be of some help to you. This is the first time
I've seen this package, so can't help you much there. It looks like the
package authors would like me to add some feature to the randomForest
package (which I maintain). I'll look into that.
Andy
________________________________
From: Ricky Jacob [mailto:[EMAIL PROTECTED]
Sent: Wednesday, April 11, 2007 7:11 AM
To: Liaw, Andy
Cc: r-help@stat.math.ethz.ch
Subject: Re: [R] Random Forest Imputations [Broadcast]
[Broadcast]
I am currently using R 2.4.1 version.
Am using the yaImpute package for k-NN imputation..
http://forest.moscowfsl.wsu.edu/gems/yaImpute.pdf
In yaImpute, i am using the yai function which uses randomForest
as a method for finding out the k-Nearest Neighbours..
http://cran.r-project.org/doc/packages/yaImpute.pdf
With the help iof the example given I was able to use the other
methods available.
from the document, and the MoscowMtStJoe exampe, is similar to
the work i am trying to do.
But the y variable needs to be entered in the form of a factor
for random forest.
what can be done here?!
On 4/11/07, Liaw, Andy <[EMAIL PROTECTED]> wrote:
Please provide the information the posting guide asks
(version of R, packages used, version of package used, etc). There are
no yaImpute() or yai() functions in the randomForest package.
Andy
________________________________
From: [EMAIL PROTECTED] on behalf of
Ricky Jacob
Sent: Wed 4/11/2007 5:55 AM
To: r-help@stat.math.ethz.ch
Subject: [R] Random Forest Imputations [Broadcast]
Dear All,
I am not able to run the random forest with my dataset..
X<- 280 records with satellite data(28 columns) - B1min,
b1max, b1std etc..
y<- 280 records with 3 columns - TotBasal Area, Stem
density and Volume
yref <- y[1:230,] #Keeping 1st 230 records as reference
records
want to set 0 to y values for records 231 to 280..
yimp <- y[231:280,] #records for which we want to impute
the basal area,
stem density and volume
mal1 <- yai(x=x, y=yref, method="mahalanobis", k=1,
noRefs = TRUE) # This
works fine for mahalanobis, msn, gnn, raw and Euclidean
Want to do a similar thing with random forest where the
1st 230 records
alone should be used for calculating Nearest Neighbours
for the records with
number 231 to 280..
What needs to be done.. Went through the yaImpute
document.. but all i
could do without any error message was to have NN
generated using the yai()
where all 280 records have been used for finding nearest
neighbour.
Regards
Ricky
[[alternative HTML version deleted]]
______________________________________________
R-help@stat.math.ethz.ch 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.
------------------------------------------------------------------------
------
Notice: This e-mail message, together with any
attachments, contains
information of Merck & Co., Inc. (One Merck Drive,
Whitehouse Station,
New Jersey, USA 08889), and/or its affiliates (which may
be known
outside the United States as Merck Frosst, Merck Sharp &
Dohme or MSD
and in Japan, as Banyu - direct contact information for
affiliates is
available at http://www.merck.com/contact/contacts.html)
that may be
confidential, proprietary copyrighted and/or legally
privileged. It is
intended solely for the use of the individual or entity
named on this
message. If you are not the intended recipient, and have
received this
message in error, please notify us immediately by reply
e-mail and then
delete it from your system.
------------------------------------------------------------------------
------
------------------------------------------------------------------------------
Notice: This e-mail message, together with any attachments,...{{dropped}}
______________________________________________
R-help@stat.math.ethz.ch 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.
