Re: [R] identify high dimension data point

From: Greg Snow <Greg.Snow_at_intermountainmail.org>
Date: Thu 11 May 2006 - 04:15:34 EST


The tkBrush function in the TeachingDemos package may help. If you just want to see where a selected point apears in each of the pairwise plots based on selecting it in 1 plot then this function will do that for you
(note it depends on having installed the tcltk package as well).

If you need the index of a selected point then you can do something like:

out1 <- tkBrush(mydata)  

# now select the point of interest, click to make the change persistent.

which(out1$col != 'black') # this gives the observation (row) number

Hope this helps,

-- 
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow@intermountainmail.org

(801) 408-8111
-----Original Message----- From: r-help-bounces@stat.math.ethz.ch [mailto:r-help-bounces@stat.math.ethz.ch] On Behalf Of Tong Wang Sent: Wednesday, May 10, 2006 5:05 AM To: R help Subject: [R] identify high dimension data point Hi there, I am having some trouble with the Identify() function, it looks that the identify() function only works on the plot of 2-dimension data set. In high-dimension case , if I use pairs() + identify() in hope to observe all the components of the data point I selected, I get error message. Is there anyway to get around this ? Plus, I also need it to actually compare all the components of the picked data point with "mydataset" to choose the closest one. Thanks million in advance. best tong ______________________________________________ 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 ______________________________________________ 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
Received on Thu May 11 04:30:15 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Thu 11 May 2006 - 06:10:04 EST.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.