RandomFields (version 3.0.5)

RFspatialGridDataFrame-class: Class "RFspatialGridDataFrame"

Description

Class for spatial attributes that have spatial or spatio-temporal locations (at least of dimension 2) on a (full) regular grid. Direct extension of class SpatialGridDataFrame from the sp-package.

Creating Objects

Objects can be created by using the functions RFspatialGridDataFrame or conventional2RFspDataFrame or by calls of the form as(x, "RFspatialGridDataFrame"), where x is of class RFspatialPointsDataFrame.

Extends

Class "SpatialGridDataFrame", directly. Class "SpatialGrid", by class "SpatialGridDataFrame". Class "Spatial", by class "SpatialGrid".

Details

Note that in the data-slot, each colums is ordered according to the ordering of coordinates(grid), the first dimension runs fastest and for all BUT the second dimension, coordinate values are in ascending order. In the second dimension, coordinate values run from high to low. Hence, when converting to conventional formats using RFspDataFrame2conventional or RFspDataFrame2dataArray, the data array is re-ordered such that all dimensions are in ascending order. as.matrix does not perform re-ordering.

Methods summary, dimensions and isGridded are defined for the parent-class RFsp.

See Also

RFspatialPointsDataFrame-class, which is for point locations that are not on a grid, RFgridDataFrame-class which is for one-dimensional locations, RFsp

Examples

set.seed(0)
n <- 3

x <- GridTopology(cellcentre.offset=c(0, 0),
 cellsize=c(1, 0.2),
 cells.dim=c(10, 30))
f <- RFsimulate(model=RMexp(), x=x, n=n)

str(f)
str(RFspDataFrame2conventional(f))
str(RFspDataFrame2dataArray(f))
coordinates(f)[1:25,]
str(f[2]) ## selects second column of data-slot
all.equal(f, cbind(f,f)[1:3]) ## TRUE
str(as(f, "RFspatialPointsDataFrame"))

plot(f, nmax=2)

steps <- if (interactive()) c(10, 1, 10, 10) else c(2, 1, 2, 2)
x2 <- rbind(c(0, 0, 0, 0),
 c(1, 0.2, 2, 5),
 steps)
scale <- if (interactive()) 10 else 1
f2 <- RFsimulate(model=RMwhittle(nu=1.2, scale=scale), x=x2, grid=TRUE, n=n)
plot(f2, MARGIN=c(3,4), MARGIN.slices=1, n.slices=6, nmax=2)

set.seed(123)
f.sp <- RFsimulate(model=RMexp(), x=x, n=n)
set.seed(123)
f.old <- RFsimulate(model=RMexp(), x=x, n=n, spConform=FALSE)
all.equal(RFspDataFrame2conventional(f.sp)$data, f.old) ## TRUE