Hello,
I am trying to draw the biplot of a PCA, but I would like to use another
variable of my initial data frame than my "row.names" to assign
labels to the points.
A part of my R file follows ; "m" is my initial data frame, which has
the variable "code" as row.names, and another variable
"name" that I'd
like to use as labels for the points.
> attach(m)
> t <- subset(m, comm == "59512",
select=c(pvviol,pcamb,pvvoit,pvroul,pinc,pdeg,ptot,pvp,pmin))
> library(mva)
> a <- princomp(na.omit(t),cor=TRUE)
I have tried some complicated things like
> biplot(a, cex=0.6, xlabs = subset(m, (comm == "59512") &
!(is.na(pvviol)), select = name))
(because I have two points who have missing values), but it doesn't work
(error message "length of dimnames[1] not equal to array extent").
Is there a simple way to do that ?
(I hope the explanations of my problem are clear enough)
Thanks a lot in advance.
--
Julien Barnier
Observatoire des Evolutions Sociales et Urbaines
Agence de d?veloppement et d'urbanisme de Lille M?tropole
2, place du Concert
59043 Lille Cedex
T?l. : 03.20.63.33.91
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
