by.im.Rd
\name{by.im}
\alias{by.im}
\title{Apply Function to Image Broken Down by Factor}
\description{
Splits a pixel image into sub-images and applies a function to each
sub-image.
}
\usage{
\method{by}{im}(data, INDICES, FUN, ...)
}
\arguments{
\item{data}{A pixel image (object of class \code{"im"}).}
\item{INDICES}{Grouping variable.
Either a tessellation (object of class \code{"tess"}) or
a factor-valued pixel image.
}
\item{FUN}{Function to be applied to each sub-image of \code{data}.}
\item{\dots}{Extra arguments passed to \code{FUN}.}
}
\details{
This is a method for the generic function \code{\link{by}} for
pixel images (class \code{"im"}).
The pixel image \code{data} is first divided into sub-images according
to \code{INDICES}. Then the function \code{FUN} is applied to each subset.
The results of each computation are returned in a list.
The grouping variable \code{INDICES} may be either
\itemize{
\item a tessellation (object of class \code{"tess"}). Each tile of
the tessellation delineates a subset of the spatial domain.
\item a pixel image (object of class \code{"im"}) with factor
values. The levels of the factor determine subsets of the spatial
domain.
}
}
\value{
A list containing the results of each evaluation of \code{FUN}.
}
\seealso{
\code{\link{split.im}},
\code{\link{tess}},
\code{\link{im}}
}
\examples{
W <- square(1)
X <- as.im(function(x,y){sqrt(x^2+y^2)}, W)
Y <- dirichlet(runifpoint(12, W))
# mean pixel value in each subset
unlist(by(X, Y, mean))
# trimmed mean
unlist(by(X, Y, mean, trim=0.05))
}
\author{Adrian Baddeley
\email{adrian@maths.uwa.edu.au}
\url{http://www.maths.uwa.edu.au/~adrian/}
and Rolf Turner
\email{r.turner@auckland.ac.nz}
}
\keyword{spatial}
\keyword{methods}
\keyword{manip}