1. Paul Hiemstra
  2. automap


Paul Hiemstra  committed ef062a0

Verbose argument is now also passed on to krige.cv

  • Participants
  • Parent commits 137fd7e
  • Branches automap

Comments (0)

Files changed (2)


View file
 Package: automap
 Version: 1.0-9
-Date: 2010/12/12
+Date: 2010/14/12
 Title: Automatic interpolation package
 Author: Paul Hiemstra <p.hiemstra@geo.uu.nl>
 Maintainer: Paul Hiemstra <p.hiemstra@geo.uu.nl>
 Description: This package performs an automatic interpolation by automatically estimating the variogram and then calling gstat.
 Depends: R (>= 2.10.0), methods, sp (>= 0.9-55), gstat (>= 0.9-65)
 Imports: lattice
+Suggests: ggplot2,maptools,gpclib
 License: GPL

File man/compare.cv.rd

View file
 	   reference = 1, 
 	   plot.diff = FALSE,
-       digits = 4) 
+       digits = 4,
+       ggplot = FALSE,
+       addPoly = NULL) 
 	\item{...}{\code{\link{autoKrige.cv}} objects that are compared to each other. Also accepts the output form krige.cv, these objects are transformed to \code{\link{autoKrige.cv}} objects.}
             worse than the reference, vice-versa for green. This is very useful to see where the differences between the results are spatially and if 
             there is a pattern.}    
      \item{digits}{The number of significant digits in the resulting data.frame.}
+     \item{ggplot}{logical, determines if spplot or ggplot2 is used to make the spatial plot of the cross-validation residuals. 
+            Note that the \code{plot.diff} and \code{reference} arguments are obsolete when \code{ggplot} equals TRUE.}
+     \item{addPoly}{if this object contains a \code{SpatialPolygons*} object, it is added to the plot as layout. Note that this only works
+           when \code{ggplot} equals TRUE.}
 \value{A data.frame with for each cross-validation result a number of diagnostics:
 % \describe{
 compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv, 
            bubbleplots = TRUE, col.names = c("OK","UK1","UK2"), 
            plot.diff = TRUE)
+# I recently added a new bubble plot that uses ggplot
+# I find it preferable, note that it requires ggplot2.
+compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv, 
+           bubbleplots = TRUE, col.names = c("OK","UK1","UK2"), 
+           ggplot = TRUE)