On Wed, 12 Dec 2007, Jian Zhang wrote:
Now I have the forest plot data with x, y locations, and I measured the DBH for
every indivicuals.
The data looks like that:
x=runif(100,0,100)
y=runif(100,0,100)
dbh=runif(100,1,100)
rdata=data.frame(x,y,dbh)
rdata[1:5,]
x y dbh
1 99.5354145 1.412844 34.10112
2 0.8259361 87.737036 39.12914
3 6.5678613 65.699032 22.55990
4 67.2987881 72.053877 45.83978
5 2.2491372 23.622898 68.77065
My question is: How can I plot the grid (25¡Á25,5¡Á5,...) figure by DBH?
Can you introduce a simply method to do it by R language? I know that it
can be done very easy by the software ArcGis.
Yes, but these are vector data, a DBH value at each point. To plot a grid
(25 by 25, ...), you must assign the values to a grid, and there are lots
of ways of doing that. Continuing the answer by Thierry Onkelinx:
set.seed(1)
x=runif(100,0,100)
y=runif(100,0,100)
dbh=runif(100,1,100)
rdata=data.frame(x,y,dbh)
library(sp)
coordinates(rdata) <- ~ x + y
grd <- GridTopology(c(2,2), c(4,4), c(25,25))
SP <- as(SpatialGrid(grd), "SpatialPixels")
whre <- overlay(SP, rdata)
SP_rdata <- SpatialPixelsDataFrame(SP, data=data.frame(dbh=rep(NA,
25*25)))
SP_rdata$dbh[whre] <- rdata$dbh
# this takes the last dbh value is more than one falls in each grid cell
# so a bit more work is needed here
pts <- list("sp.points", rdata)
spplot(SP_rdata, "dbh", sp.layout=list(pts))
Or interpolate, and mask out empty cells:
library(gstat)
SP_rdata2 <- idw(dbh ~ 1, rdata, newdata=SP, idp=2.0, nmax=4)
is.na(SP_rdata2$var1.pred) <- !(1:625 %in% whre)
spplot(SP_rdata2, "var1.pred", sp.layout=list(pts))
for example.
Roger
¡¡¡¡¡¡¡¡
¡¡¡¡¡¡¡¡
¡¡¡¡¡¡¡¡
¡¡¡¡¡¡¡¡
Thanks very much.
[[alternative HTML version deleted]]
--
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: [EMAIL PROTECTED]______________________________________________
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.
