R help - Sep 2009 - How can I change characteristics of a cca biplot in R

Hi,

I?m doing cca for a community data set in R and I have made a biplot for my
data. Otherwise everything seems to be allright but the biplot is so messy I
can?t read it well enough or publish it. I would like to get the row numbers out
of the plot: I want the species position and the environmental variables in it
as vectors but not the station numbers. How do I get them out?

I have a raw species data set and a raw environmental data set and I don?t have
station names or numbers in the data set but R puts the row names in anyway. I
understand they are necessary but I just don?t want to show them in the biplot.

Thank you!

Yours sincerely 
Heta Rousi ( Finnish environment institute, Marine center)

On Mon, 2009-09-07 at 12:49 +0300, Rousi Heta wrote:
> 
> Hi,
> 
> I?m doing cca for a community data set in R and I have made a biplot
> for my data. Otherwise everything seems to be allright but the biplot
> is so messy I can?t read it well enough or publish it. I would like to
> get the row numbers out of the plot: I want the species position and
> the environmental variables in it as vectors but not the station
> numbers. How do I get them out? 
Is this in vegan? If so, if obj contains your fitted cca model, then

plot(obj, display = c("species","bp"))

(or, if you have centroids for factor variables as well)

plot(obj, display = c("species","bp","cn"))

If you only want to plot the points rather than the labels, add argument
'type' to the call setting it to "p", e.g.:

plot(obj, display = c("species","bp"), type = "p")
> 
> I have a raw species data set and a raw environmental data set and I
> don?t have station names or numbers in the data set but R puts the row
> names in anyway. I understand they are necessary but I just don?t want
> to show them in the biplot.
All of this (and more) is explained in ?plot.cca (if you are talking
about vegan::cca)

You might also like to look at ?orditkplot (which allows you to move the
labels around yourself to get a clear plot) and ?orditorp with which you
can set a priority for certain sites to be labelled with text whilst
points are used for those sites that would cause text labels to overlap.

HTH

G
> 
> Thank you!
> 
> Yours sincerely 
> Heta Rousi ( Finnish environment institute, Marine center)
> ______________________________________________
> R-help at 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.
-- 
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
 Dr. Gavin Simpson             [t] +44 (0)20 7679 0522
 ECRC, UCL Geography,          [f] +44 (0)20 7679 0565
 Pearson Building,             [e] gavin.simpsonATNOSPAMucl.ac.uk
 Gower Street, London          [w] http://www.ucl.ac.uk/~ucfagls/
 UK. WC1E 6BT.                 [w] http://www.freshwaters.org.uk
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%

Win7, R-2.9.1

Dear list,

I have a large (nxm) matrix which is the output of an analysis. Since it 
is so large, I would like to use output formatting to make it easier to 
find particular values and patterns in the matrix. In particular, I want 
to print the matrix as follows:
- cells with a value that is below a given threshold should be printed 
as empty (thus leaving out the low values from sight)
- cells with particular values should be printed in bold face or with a 
larger font size

Is this possible? How would one do such a thing?

thanks, Roger