Dear Tom,
as your grids are spatial grids, you may want to look into the web
service standards of the OGC (www.opengeospatial.org) for them, WCS (for
reading) and WCS-T (for writing) in particular. We're experimenting with
this currently, using the recently open sourced rasdaman software
(www
Massimo, I would at least include those on the Spatial task view, at
http://cran.r-project.org/web/views/Spatial.html and merge the full list
there with your list.
In your list, for instance, geoR and geoRglm are missing.
--
Edzer
Massimo Di Stefano wrote:
Hi,
i'm working on a live-dvd linux
Ingo Holz wrote:
> Hi,
>
> I have a SpatialGridDataFrame and want to plot it with spplot().
>
> Is it possible to plot only the grids that have a special value (eg. 312)?
>
fullgrid(x) = FALSE
spplot(x[x$value == 312,"value"]
Note that if fullgrid(x) is TRUE, x[rows,cols] would select on
row
Although not specifically related to r-sig-geo, I'll comment a bit -
I wouldn't delete part of the cells, but rather define the transparency
bit in the color. You can do that, e.g. by
> rgb(1,0,0,0.5)
[1] "#FF80"
you'll get half transparent red. Note that you need a device that
supports t
Sebastian P. Luque wrote:
> On Mon, 12 Nov 2007 23:29:59 +0100 (CET),
> Roger Bivand <[EMAIL PROTECTED]> wrote:
>
> [...]
>
>
>> Then the fallback is to write a GTiff, and use gdal_translate to convert
>> it (one of the gdal utilities that build with the GDAL shared
>> object). If the same probl
On linux, you should have the netCDF driver istalled; from gdalDrivers()
I see (on debian etch):
name long_name create copy
42netCDF Network Common Data Format FALSE TRUE
Then, reading the documentation of writeGDAL:
'create2GDAL' c
Ingo, that makes sense.
I committed a change to sp (in cvs), such that something like
spplot(meuse["zinc"],sp.layout=list("sp.text",coordinates(meuse),1:155))
works (although the plot of course does not make much sense)
It will be in the next release.
--
Edzer
Ingo Holz wrote:
> Hi,
>
> I am
... and I can't reproduce it under Linux, where "Ingo's title" happily
appears.
I guess r-help would be the right place to ask this question. Remove the
".../" before outfile.png, so it might run straight away.
--
Edzer
Ingo Holz wrote:
> Hi,
>
> it only happens using png(). It does not if I *.
> after saving this figures with png().
>
> Ingo
>
>
> Message: 3
> Date: Thu, 08 Nov 2007 15:00:42 +0100
> From: "Edzer J. Pebesma" <[EMAIL PROTECTED]>
> Subject: Re: [R-sig-Geo] spplot legends for each subplot
> To: [EMAIL PROTECTED]
> Cc: Ingo Ho
I fully agree with Roger's comment, but you may also want to check the
help of ?print.trellis (library lattice), especially its more=, split=
and position= arguments. It lets you combine trellis plots on a single page.
--
Edzer
Roger Bivand wrote:
> On Thu, 8 Nov 2007, Ingo Holz wrote:
>
>
>>
n:
>
> krige(formula=no2.ppb~traffic, mydata, newdata=mynewdata,model=vgmRaw)
>
> I'd like to get the WLS or GLS estimate of traffic.
>
> This back and forth is asking a lot of your time, I really appreciate
> your quick replies. Thanks!
>
> Zev
>
> Edzer J. Pebe
et=0.05, add.to=vgm(.05,"Err",0))
>
> fit.variogram(variogram(log(zinc)~1,meuse),model=myvgmA)
> model psillrange
> 1 Nug 0.000 0.
> 2 Exp 0.7186526 449.7581
>
>
> fit.variogram(variogram(log(zinc)~1,meuse),model=myvgmB)
> model psill range
Zev,
you can use the "Err" variogram model to denote micro variation as
opposed to nugget. The only effect it has is that for a new prediction
on an observation location the measurement error-free process is
predicted, and not the observation process itself. Semivariance of an
observation with
Dylan Beaudette wrote:
> On Friday 26 October 2007, Roger Bivand wrote:
>
>> On Fri, 26 Oct 2007, Dylan Beaudette wrote:
>>
>>> On Friday 26 October 2007, Roger Bivand wrote:
>>>
On Fri, 26 Oct 2007, Dylan Beaudette wrote:
> Hi,
>
> noticed that when I
I'm sorry I missed this talk Barry, but the slides were a pleasure to go
through!
What was the argument not to go with OpenEV with communication through
Rserve?
Thanks,
--
Edzer
Barry Rowlingson wrote:
> Agustin Lobo wrote:
>
>> Any way of getting the pdf of the talk? I'm interested
>> both
Brad, you might want to try to construct one spplot per column, having
the scale perhaps horizontally on the bottom, and combing them using the
print(..., more = T) on trellis objects (see ?print.trellis in package
lattice). An issue might be to get the maps at exactly the same scale,
as the pr
Dear Klaus,
there's broadly 2 approaches; one builds on the so-called model-based
geostatistics (MBG) approach by Diggle et al 1998 (and in the book by
Ribeiro and Diggle), the other uses Pearson residual variogram and
covariance matrices that use the variance function for the mean
dependent (
Mauricio, it's easier than you think; try
Zn.vgm1 <- variogram(Zn~1, jura.pred.xy, alpha=c(22.5, 67.5), cutoff=2,
boundaries=c(0.1, 0.2*(1:10)), tol.hor=22.5)
plot(Zn.vgm1) # with 2 panels
plot(Zn.vgm1, multipanel=FALSE) # in a single panel
the add=TRUE does not work as the plot methods for gs
Zev, package fields contains some optimization codes written by Eric
Gilleland. I think it's mainly about optimizing an existent network.
--
Edzer
Zev Ross wrote:
> Hi All,
>
> Just wondering if anyone knows of any good R scripts/methods for
> monitoring network design optimization. I'm interest
icular advice for setting up the kernel
> (or other things) for such a machine (i.e., the PAE kernel)?
>
> Agus
>
> Edzer J. Pebesma escribió:
>> I think R will never do it's own memory swapping, as that is a
>> typical OS task. There are however several developments (p
I think R will never do it's own memory swapping, as that is a typical
OS task. There are however several developments (provided in add-on
packages) that will not load all data in memory at start-up, but instead
call some data base whenever a data element is needed. You might search
r-help for
acing the zero with positive numbers up to 5, with no
> luck.
>
> Anyone have any other ideas?
>
> Keith
>
> -----Original Message-
> From: Edzer J. Pebesma [mailto:[EMAIL PROTECTED]
> Sent: Tuesday, September 11, 2007 2:30 PM
> To: Keith Dunnigan
> Cc: r-
Keith,
indeed kriging usually fails when one or more point pairs have zero
distance. One solution in terms of distances would be to shift these
points a bit, such that no zero distances occur anymore. In terms of the
covariances, the solution would be to lower the corresponding
off-diagonal en
Joshua,
My guess is that to estimate beta geoR uses generalized least squares
and lm and SAS ordinary least squares. If you use a pure nugget model,
or some other model with a range parameter sufficiently close to zero,
i.e. model the observations as independent, the estimates should be the
s
Sebastien, a possible way to get your data in R is through the readOGR
function in package rgdal that can read from a PostGIS data base. Not
being an expert, from your example below it seems that the polygon data
are in some PostGIS form, WKT or something like that. You'll find some
examples on
David, you may also notice that the map produced does not have a cell
centre or cell 'crossing' at (0,0). Of course you'd assume enough
cleverness that this would be enforced automatically, but too bad. Try
v <- variogram(Ni ~ 1, jura.pred, cutoff=1.8, width=0.18, map=T)
(making sure that the
As Roger mentioned, we did try to make the Spatial*DataFrame objects
behave like a data.frame but indeed not with respect to applying direct
arithmetric on them. I do agree with Tim that if a is a single-band
SpatialGridDataFrame, then
a = a + 1
is more straightforward than
a$band1 = a$band1
Michael,
The plot method for SpatialLinesDataFrame objects resides in package sp,
and questions regarding it are easier noticed on the r-sig-geo mailing
list.
The reason why they are plotted with aspect ratio 1 is that they are
assumed to be spatial (geographical) data, and assume that 1 m nor
ugh... :-P
>
> Have a nice evening!
>
> stefano
>
>
> Edzer J. Pebesma ha scritto:
>> Stefano,
>>
>> I thought cell declustering meant finding the size of the region of
>> influence for an observation and using that as weight in further
>>
Stefano,
I thought cell declustering meant finding the size of the region of
influence for an observation and using that as weight in further
analysis. An approach would be using voronoi diagrams (package deldir,
and read the list archives), another using the number of nearest cells
based on a
Debs,
what does gdalinfo sayl about the .tif map? I wouldn't trust Arcmap as
the ultimate referee to judge whether a geotiff is sound or not. It may
dislike your floating point values, for example.
--
Edzer
Debarchana Ghosh wrote:
> Hello,
>
> I'm using Windows with 2 GB ram.
>
> I have created
Agustin,
I didn't look at the cross overs, but spplot inside a loop needs an
explicit print(spplot(...)) around it to get the result printed
(actually plotted); this is a lattice FAQ, spplot wraps xyplot or
levelplot in lattice.
--
Edzer
Agustin Lobo wrote:
Dear
rsiggeos,
After importin
Agustin Lobo wrote:
> Dear sig-geos,
>
> is there any way of converting from vector
> (imported with rgdal from a shp) to raster
> within R?
>
> Thanks!
>
> Agus
>
>
Yes, using the classes and methods in sp -- you'd first have to create a
grid e.g. with spsample, sampling type regular or makegr
Cesar Martinez Izquierdo wrote:
> Hello list,
> we are trying to implement spatial interpolations (IDW and several types
> of Kriging) in our open source GIS application, which is written in Java.
>
> We plan to use JRI to connect with R from Java, and then use the
> features of "gstat" R-packag
Kitty Lee wrote:
> Hi Roger, I forgot to mention I did try tripack and did go through your
> previous post.
>
> But I'm doing a simulation and I have to repeat the process >1000 times.
>
>
> I feel using the voronoi method to divide up the study area may not be the
> most efficient way. I thoug
Roger Bivand wrote:
> On Mon, 25 Jun 2007, Agustin Lobo wrote:
>
>> I've tried (among other things):
>>> limit1 <- read.shape("limit_PNSN2000.shp")
>> Shapefile type: Polygon, (5), # of Shapes: 2
>>> limit1poly <- Map2poly(limit1)
>>> limit1owin <- as(limit1poly,"owin")
>> Error in .classEnv(thi
0
> NA's :119.0
>
> > Y <- SpatialPixels(X)
> > summary(Y)
> Object of class SpatialPixels
> Coordinates:
> min max
> x 410649.7 415399.7
> y 4607910.5 4610910.5
> Is projected: TRUE
> proj4string : [ +proj=utm +zone=31 +ellps=intl +uni
Roger Bivand wrote:
> It may also be worth asking on the PostGIS list whether you could upload
> your geometries to PostGIS and have GEOS do the measurement - if you have
> access to the software and experience with it. It may be that it can
> handle geographical coordinates.
>
I have to be
Not only to avoid NAs, but also to get approximately right sample size.
Stratified sampling does not take place based on strata defined by
attributes (map layers), but rather by dividing the area into square
blocks (strata) and randomly sample (n=1) from each block. That is why
the resulting sa
Is it possible to compute them experimentally, by computing the variance
of the back-transformed simulations for each prediction location?
--
Edzer
Paulo Justiniano Ribeiro Jr wrote:
> Dear Giovanna
>
> For certain values of the Box-Cox transformation it is not possible to
> compute kriging varia
If they're SpatialPoints* or SpatialPixels*, use rbind on them. If
they're in a SpatialGridDataFrame, first convert to pixels by
fullgrid(x) = FALSE
then rbind, then back with fullgrid(x) = TRUE
hth,
--
Edzer
Kitty Lee wrote:
> Thanks to Terry and Virgilio, I used both suggestions in creating
Thomas,
I have seen this error from package gstat before but find it hard to
guess what caused it without looking over your shoulder. Please send the
script that led to the error.
--
Edzer
Thomas Szegvary wrote:
> Hi there
>
> I have problems using krige(). I want to do ordinary kriging, but al
Jan, I have a clue why this happened. Indeed,
> image(input, col=rev(bpy.colors(10)), axes=T)
reproduces the example, but
> image(input, col=rev(bpy.colors(10)))
> axis(1)
> axis(2)
> box()
doesn't. It seems like the col argument is passed to axis, try
> axis(1, col = rev(bpy.colors(10))
Mike, my experience with linking R with PostGIS are documented here:
http://wiki.intamap.org/index.php/PostGIS
which I may have mentioned before on r-sig-geo.
Indeed, as Tim confirms, besides the (r)gdal link, (R)ODBC is another
working link for transferring table information. I doubt whether i
Andrew Niccolai wrote:
> Therefore, does anyone have any solutions for reading in an image
>that would work in theory like the following:
>
>setwd(anypathway)
>tif.image <- "VERY_LARGE_IMAGE.tif"
>Bounded.tif <- GDAL.open(tif.image, bbox=c(UpL.X, LwR.X, UpL.Y, LwR.Y))
>
>By the way, I am not set
Marta Rufino wrote:
> Dear list members,
>
>
> I have three doubts: :-)
>
> 1. How to colour the lines from a shape file (which has been inserted
> into a spplot, through sp.layout):
>
> #For example
> nc <- readShapeLines("costa.shp", proj4string=CRS("+proj=longlat
> +datum=WGS84"))
> spplot(gr
m W. Watt
> A statistical analysis, properly conducted, is a delicate dissection of
> uncertainties, a surgery of suppositions. ~M.J.Moroney
>
>
>
>
>> -Oorspronkelijk bericht-
>> Van: Edzer J. Pebesma [mailto:[EMAIL PROTECTED]
>> Verzonden
Thierry, you'll have to find out what the linear model of
regionalization or intrinsic correlation mean; they are legal models,
meaning that they lead to predictions with guaranteed non-negative
prediction variances. There's a way to override the check (meaning it
will not stop on error) but no
Andrew,
If you want to simulate particular random fields that are Gaussian or
binary, described by a second order properties (mean, variogram), then
you may want to look into the simulation capabilities of packages
RandomFields or gstat. If you want to simulate objects (circles,
ellipses, star
Michal,
I think (and hope for you) it is not necessary to search the solution at
the level of grid. The plot function for variograms in package gstat is
a rather (?) thin wrapper around xyplot, so if you carefully read how to
control the main and sub arguments of ?xyplot, then you're done:
lib
Please use the on-line documentation that comes with downloaded package;
the documentation you used may very well be out of sync with the package
fields. If you have questions about the docs in the package, you might
want to ask the package developer.
--
Edzer
Juan Du wrote:
> Dear R-helpers,
>
temiz wrote:
> hello
>
> when I create a directional variogram, it usually gives different
> shaped variograms according to its direction.
> (like this cvgm <- variogram(z ~1, data=el4 ,boundaries = seq(0,2000, by
> = 50), alpha=c(0,45,90,135,180,225,270)) )
>
> In these cases, which variog
temiz wrote:
> hello
>
> when I try universal kriging, it gives this error:
>
> > v.trend <- variogram(z~x+y,el4)
> > new.fit <- fit.variogram(v.trend, vgm(1,"Exp",300,1))
> > krige(el4$z~el4$x+el4$y,el4, model=new.fit, newdata=mask_SG)
> Error in gstat.formula.predict(d$formula, newdata, na.act
Yong Li wrote:
> require(maptools)
>
> #read in shape file
> pts <- readShapePoints(system.file("shapes/baltim.shp",
> package="maptools")[1])
>
> #define the dimension of grids
> x.min <- summary(pts)$bbox[1]
> y.min <- summary(pts)$bbox[2]
> x.max <- summary(pts)$bbox[3]
> y.max <- summary(pts)
You may want to use spsample, or, if you selected the points in the
polygon with overlay and want to sample from them, use function sample.
It is hard for us to see what you're trying and cannot get without
(reproducible) example code.
--
Edzer
Yong Li wrote:
> I want to overlay points with a p
perhaps use
spplot(OK_pred[1], ...)
which would be more or less short for
levelplot(var1.pred~x+y, as.data.frame(OK_pred), aspect = "iso", ...)
--
Edzer
temiz wrote:
>hello
>
>why does levelplot function give an error
>
>OK_pred <- krige(z~1,el4, newdata=mask_SG, model=efitted)
>levelplot(var
large memory footprint -- I moved the zerodist
code from R to C. (I needed it myself for a 30.000 point data set this
morning.)
--
Edzer
--- Begin Message ---
>>>>> Edzer J Pebesma writes:
> This new sp version has a better rbind CRS checking and re-implements
> zerodist in C.
it in parts.
--
Edzer
temiz wrote:
> Edzer J. Pebesma wrote:
>> temiz wrote:
>>> ...
>>> I regarded some modifications in
>>> http://grass.gdf-hannover.de/wiki/GRASS_6_Tutorial#GRASS_and_R_kriging_interpolation
>>>
>>>
>>>
>>&
May I suggest you take a look at the Spatial Task View?
r-project.org -> CRAN -> Select Mirror -> Task Views -> Spatial.
--
Edzer
Linda Smith wrote:
> Could you please let me know more details about rgval package? I have never
> used it before. I only tried image.plot() where if you have regular
temiz wrote:
> ...
> I regarded some modifications in
> http://grass.gdf-hannover.de/wiki/GRASS_6_Tutorial#GRASS_and_R_kriging_interpolation
>
> I encountered a new problem :
> > OK_pred <- krige(z ~ 1, el3, newdata=mask_SG, model=efitted)
> [using ordinary kriging]
>
> "memory.c", line 57: can't
Tim Keitt wrote:
>>spplot(beta, "1")
>>
>>
>Error in `[.data.frame`(as(obj, "data.frame"), zcol) :
>undefined columns selected
>
>I can't seem to fix this. Version: 0.9-10
>
>
>
Thought I fixed this -- how about sp 0.9-11 current CRAN version?
--
Edzer
temiz wrote:
> following the topic GRASS and R kriging interpolation from grass6 tutorial
>
> I came here without problems
>
> But here:
>
> zz <- krige(z ~ 1, locations = el1 , newdata = mask_SG , model = efitted)
> Error in predict.gstat(g, newdata = newdata, block = block, nsim = nsim, :
>
el1 is already a SpatialPointsDataFrame, so omit the locations argument.
You may try something as simple as
zz <- krige(log(z) ~ 1, el1, mask_SG, efitted)
--
Edzer
temiz wrote:
> when does this error occur ?
>
> > zz <- krige(formula = log(el1$z) ~ 1, locations = ~x+y , data = el1
> ,newdata
temiz wrote:
> hello
>
> when I followed the steps of ORDINARY KRIGING IN R WITH GRASS6 DATA in
> GRASS 6 Tutorial.
>
> I encountered this error:
>
> > mask_SG <-
> SpatialGridDataFrame(grd,data=list(k=rep(1,G$cols3*G$rows3)),proj4string=CRS(G$proj4))
> Error in validObject(.Object) : invalid c
Dear list members,
I've been exploring a bit the possibilities of PostGIS, and accessing
its functionality (the GEOS geometry library really) from R. I used
writeOGR and readOGR from rgdal to move sp objects in and out the data
base, and used sqlQuery from RODBC to do a spatial query on the dat
Raffaele, try
spplot(x, ..., main=list(label="title",cex=3))
I found this by
library(lattice)
?xyplot # search for argument main
--
Edzer
Raffaele Morelli wrote:
> Hi you all,
>
> probably this is a silly question (I mean I apologize for that in advance :)
> )
>
> I am using spplot in order to
Patrick,
the problem is that if you reproject points on a grid, the result is not
on a grid anymore, so I think it is correct that spTransform does return
a SpatialPointsDataFrame rather than a SpatialGridDataFrame. You would
have to shift points to centers on the new grid. The creator function
Although I'm interested many of the issues below, and also feel the
attraction of the develop-it-ourself, my personal agenda is a bit more
modest. Once we start with GEOS support (an idea mentioned every 6
months on this list), the next thing we need for dealing with huge or
massive data sets i
I would try the alternative,
bubble(Error,maxsize=1.5)
bubble(Error,maxsize=1.5, key.entries=-10:10)
Doing what you want with spplot, you're basically thrown back at xyplot
with asp="iso"; look at how key is formed there; with
spplot(Error, pch = ifelse(Error$error < 0, 95, 3), key.space = "rig
Hi,
Is there an R package/function that, given a set of polygons (say
country boundaries) finds the line set of lines that defines the
boundary for each pair of neighbouring countries?
--
Edzer
___
R-sig-Geo mailing list
R-sig-Geo@stat.math.ethz.ch
ht
Paul, that is hard to see from here. Perhaps you could make the points
available? Is the grid aligned with x and y? Did something happen with
(re)projection inbetween?
--
Edzer
Paul Magdon wrote:
>First of all thank you very much for this comments.
>
>As you already stated the points have to be
Roger Bivand wrote:
> On Wed, 7 Mar 2007, Schmitt Thierry wrote:
>
>
>> I am struggling to overlay spatialLinesDataFrame and
>> SpatialGridDataFrame. The overlay method doesn't allow me to do so.
>>
>>
>
> There is no overlay method, you would need to write one, or interpolate
> points alo
Gabor, sp provides a contour method for objects of class
SpatialGridDataFrame. I don't know how you should create a grid such
that contours are circles -- simplest to generate distances from
specific points. I don't know if there is easy way to do this right now;
a rather indirect way is to use
Using the classes and methods for spatial data in package sp, typically
the dem would be stored in a grid (SpatialGridDataFrame) and the vector
data in a SpatialPointsDataFrame. Then you can use the overlay method to
retrieve the dem values at point locations, to look at their relationship.
--
E
All of the partners in the intamap project (http://www.intamap.org/) do,
for example.
--
Edzer
Gabor Grothendieck wrote:
> Not sure if this will become an issue but in case I need
> it to justify my toolset does anyone have a list of
> recognizable organizations that use R for geographic
> proces
Gabor,
package rgdal provides an interface to the PROJ.4 library for projection
of geographical data. Look for the function (or rather method)
spTransform. It takes any of the spatial classes provided by package sp,
and afaik any of the known projection systems, including UTM and
ellipsoids (L
Dagmar,
this is hard to tell from here without having something that I can
reproduce; my first suggestion would be NA's in the values or
coordinates, but you say it is not. Also hard to read your code: is
crossvalid a global logical? How can you pass the character vector
location.xvalid to the
Trevor, a few notes in addition to Roger's answer:
Trevor Doerksen wrote:
> I have two specific questions:
> 1) ...
> Also, I don't know
> how to mask a specific area (like the nice grid in the meuse data set)
> of interest within that grid.
Depends on where you start. Suppose you have a Spati
Matthew, try
library(gstat)
demo(gstat3D)
It doesn't use the sp classes, and in the next version it will be like this:
# $Id: gstat3D.R,v 1.4 2006-02-10 19:05:02 edzer Exp $
# simple demo of 3D interpolation of 50 points with random normal values,
# randomly located in the unit cube
n <- 50
dat
Hi Thierry,
I think spatstat covers point pattern analysis, which is mostly not
covered by gslib. I have seen either no or small differences between
gstat and gslib, but never differences that I could not explain. They
may for instance relate to how you integrate covariances over a block;
ther
I'm not a 100% sure, but it might be that you are using c(sub.cb.poly,
i) which creates a list when the arguments are complicated structures.
You may wish to use rbind on two (or more!) SpatialPolygonsDataFrame
objects instead. Provided you have the latest sp from CRAN...
Hth,
--
Edzer
Andrew
Roger Bivand wrote:
> Would it be sensible to include ProportionalSymbolMap() in maptools? In
> fact, it is the legend that is the tough problem, so in fact using the
> bubble-plot method in sp may be an easier way forward:
>
> SPDF <- SpatialPointsDataFrame(coordinates(ill), data=data.frame(x=x)
Perhaps try
> [EMAIL PROTECTED]@att[[1]]
etc.
--
Edzer
Horacio Samaniego wrote:
> I first need to apologize as I have made a mistake, I know that I
> should have read the Breaking News before (http://www.sal.uiuc.edu/
> tools/tools-sum/rgeo/r-spatial-projects)
>
> Now I am trying to step ba
David Forrest wrote:
>On Wed, 17 Jan 2007, Roger Bivand wrote:
>...
>
>
>>>What do I need to to do turn the key off for spplot(SpatialPointsData) ?
>>>
>>>
>>I can't see it, I thought it might be auto.ket=FALSE, but it doesn't seem
>>to be that. To be honest, I would feel more comfortable
David Forrest wrote:
> Hi All,
>
> Does the install.packages('sp') on my R V2.1.0 (Debian Stable) report:
>
> no package 'sp' at the repositories in: download.packages(pkgs, destdir
> = tmpd, available = available
>
> ... because sp from CRAN depends on "R (>= 2.4.0), methods" ?
>
> The mac
Jeff, you may want to have a look at function spsample in package sp.
--
Edzer
Jeffrey Stratford wrote:
> Hi, is there a way to sample an ESRI grid using random sample points?
> In the past I used ESRI's spatial analyst but I would like to switch all
> my analyses to R if possible. The grid is
Patrick, I can see this is confusing.
Besides methods(plot), try after library(sp) a
showMethods(plot)
to get an overview of the S4-style plot methods; methods(plot) only
shows the S3-style plot methods. Then,
class?SpatialPolygons
gives methods available for this class, among which plot, and
Christoph Hofer wrote:
> Hello Kenneth
>
> In the sp package you find the function "point.in.polygon".
>
Yes, and a convenient wrapper method, called "overlay" which basically
overlays a polygon coverage (SpatialPolygonsDataFrame) with a point
coverage (SpatialPointsDataFrame). Try
> library
Ken,
The indicator kriging idea does not stop at a single binary variable.
The "standard" (or "Stanford"?) way of getting non-negative predictions,
and possibly predictions that sum to one is rather pragmatic--simply
postprocessing predictions. There is a cleaner solution, called
compositional
statistical analyst
> CSIRO, Sustainable Ecosystems
> Davies Laboratory,
> University Drive, Douglas, QLD 4814
> Private Mail Bag, Aitkenvale, QLD 4814
>
> Phone/www
> (07) 4753 8510; 4753 8650(fax)
> Home: http://herry.ausbats.org.au
> Webadmin ABS: http://ausbats.or
0.9-4"
> "0.8-17"
> spatial
> "7.2-29"
>
>
> Thanks
> Herry
>
>
> Dr Alexander Herr
> Spatial and statistical analyst
> CSIRO, Sustainable Ecosystems
> Davies Laboratory,
> University Drive, Douglas, QLD 4814
> Private Mail Bag, Aitkenvale, QLD 4814
>
> Phone/www
>
>
> Phone/www
> (07) 4753 8510; 4753 8650(fax)
> Home: http://herry.ausbats.org.au
> Webadmin ABS: http://ausbats.org.au
> Sustainable Ecosystems: http://www.cse.csiro.au/
> ------------
>
>
> -Original Message-
> From: Edzer J. Pebesma
plotting variograms in gstat is done through xyplot in lattice; you'll
find where it gets it's defaults by
library(lattice)
trellis.par.get()
?trellis.par.set
--
Edzer
[EMAIL PROTECTED] wrote:
>
> Dear list,
>
> I am having troubles increasing the fontize when plotting a
> variogram{gstat} and
Herry, in
k1<-krige(z ~ x+y, ~x+y, data=shp1, newdata=a1000, model=m2, nmax=40)
shpl is alread a SpatialPointsDataFrame object, so you shouldn't specify
it's coordinates, ~x+y. Rather, use
k1<-krige(z ~ x+y, shp1, a1000, model=m2, nmax=40)
I must admit that a more helpful error message would
Paul, please note that at least 5 R packages calculate variograms, and
not everyone can see from your email address which one you are using
(gstat).
plot is a generic method; to find which instance is called try
class(plot(rad_data_vgm,rad_data_mod$sph))
[1] "trellis"
so the plot returns is ac
Dear spplot users,
When spplot is used with the names.attr argument for label placement in
the strips, and the names of the variables in zcol are not in alphabetic
order, strips will receive the wrong name. I found out only now because
apparently I tend to use names in alphabetic order, or just
Roger,
install.packages("gstat") with 2.4 over a 2.3 library gives me the
following:
...
ufctr.o sprow.o spswap.o stat.o submat.o userio.o utils.o vario.o
vario_fn.o vario_io.o vecop.o version.o writecmd.o xvalid.o
-L/usr/lib/R/lib -lR
** R
** data
** demo
** inst
** preparing package for la
Wouter,
you could resort to simulation, i.e. generate conditional
simulations, compute the catchment aggregated value and obtain
their distribution experimentally. If you're after the catchment mean,
you better use block kriging for irregular blocks (the catchment).
R package gstat provides this.
Bertrand,
Several causes can lead to a singular covariance matrix; the most common is
that you have duplicate observations (i.e. two or more observations on the
same location). Use zerodist to find out.
--
Edzer
bertrand toupin wrote:
> Hi everyone, another obstacle towards the achievement :)
>
>
Jacques,
the projection functions are now in package rgdal which is on CRAN so
should have Mac binaries. Look for the function spTransform.
Also, an email I sent to you last night answering a question related to
sp bounced; please resend the question to this list.
--
Edzer
pir2.jv wrote:
> I t
1 - 100 of 167 matches
Mail list logo
