GSIF (version 0.5-3)

spc: Derive Spatial Predictive Components

Description

Derives Spatial Predictive Components for a given set of covariates. It wraps the stats::prcomp method and predicts a list principal components for an object of type "SpatialPixelsDataFrame".

Usage

"spc"(obj, formulaString, scale. = TRUE,  silent = FALSE, ...)
"spc"(obj, formulaString, scale. = TRUE,  silent = FALSE, ...)

Arguments

obj

object of class "SpatialPixelsDataFrame" (must contain at least two grids) or a list of objects of type "SpatialPixelsDataFrame"

formulaString

object of class "formula" or a list of formulas

scale.

object of class "logical"; specifies whether covariates need to be scaled

silent

object of class "logical"; specifies whether to print the progress

...

additional arguments that can be passed to stats::prcomp

Value

returns an object of type "SpatialComponents". This is a list of grids with generic names PC1,...,PCp, where p is the total number of input grids.

See Also

stats::prcomp, SpatialComponents-class

Examples

# load data:
library(plotKML)
library(sp)

pal = rev(rainbow(65)[1:48])
data(eberg_grid)
gridded(eberg_grid) <- ~x+y
proj4string(eberg_grid) <- CRS("+init=epsg:31467")
formulaString <- ~ PRMGEO6+DEMSRT6+TWISRT6+TIRAST6
eberg_spc <- spc(eberg_grid, formulaString)
names(eberg_spc@predicted) # 11 components on the end;
## Not run: # plot maps:
# rd = range(eberg_spc@predicted@data[,1], na.rm=TRUE)
# sq = seq(rd[1], rd[2], length.out=48)
# spplot(eberg_spc@predicted[1:4], at=sq, col.regions=pal)
# ## End(Not run)