The R Project SVN R

\name{aggregate}
\alias{aggregate}
\alias{aggregate.default}
\alias{aggregate.data.frame}
\alias{aggregate.ts}
\title{Compute Summary Statistics of Data Subsets}
\usage{
aggregate(x, \dots)

\method{aggregate}{default}(x, \dots)

\method{aggregate}{data.frame}(x, by, FUN, \dots)

\method{aggregate}{ts}(x, nfrequency = 1, FUN = sum, ndeltat = 1,
          ts.eps = getOption("ts.eps"), \dots)
}
\description{
  Splits the data into subsets, computes summary statistics for each,
  and returns the result in a convenient form.
}
\arguments{
  \item{x}{an R object.}
  \item{by}{a list of grouping elements, each as long as the variables
    in \code{x}.  Names for the grouping variables are provided if
    they are not given.  The elements of the list will be coerced to
    factors (if they are not already factors).}
  \item{FUN}{a scalar function to compute the summary statistics which
    can be applied to all data subsets.}
  \item{nfrequency}{new number of observations per unit of time; must
    be a divisor of the frequency of \code{x}.}
  \item{ndeltat}{new fraction of the sampling period between
    successive observations; must be a divisor of the sampling
    interval of \code{x}.}
  \item{ts.eps}{tolerance used to decide if \code{nfrequency} is a
    sub-multiple of the original frequency.}
  \item{\dots}{further arguments passed to or used by methods.}
}
\details{
  \code{aggregate} is a generic function with methods for data frames
  and time series.
  
  The default method \code{aggregate.default} uses the time series
  method if \code{x} is a time series, and otherwise coerces \code{x}
  to a data frame and calls the data frame method.

  \code{aggregate.data.frame} is the data frame method.  If \code{x}
  is not a data frame, it is coerced to one.  Then, each of the
  variables (columns) in \code{x} is split into subsets of cases
  (rows) of identical combinations of the components of \code{by}, and
  \code{FUN} is applied to each such subset with further arguments in
  \code{\dots} passed to it.
  (I.e., \code{tapply(VAR, by, FUN, \dots, simplify = FALSE)} is done
  for each variable \code{VAR} in \code{x}, conveniently wrapped into
  one call to \code{lapply()}.)
  Empty subsets are removed, and the result is reformatted into a data
  frame containing the variables in \code{by} and \code{x}.  The ones
  arising from \code{by} contain the unique combinations of grouping
  values used for determining the subsets, and the ones arising from
  \code{x} the corresponding summary statistics for the subset of the
  respective variables in \code{x}.
  
  \code{aggregate.ts} is the time series method.  If \code{x} is not a
  time series, it is coerced to one.  Then, the variables in \code{x}
  are split into appropriate blocks of length
  \code{frequency(x) / nfrequency}, and \code{FUN} is applied to each
  such block, with further (named) arguments in \code{\dots} passed to
  it.  The result returned is a time series with frequency
  \code{nfrequency} holding the aggregated values.
}
\author{Kurt Hornik}
\seealso{
  \code{\link{apply}}, \code{\link{lapply}}, \code{\link{tapply}}.
}
\references{
  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
  \emph{The New S Language}.
  Wadsworth \& Brooks/Cole.
}
\examples{
data(state)

## Compute the averages for the variables in 'state.x77', grouped
## according to the region (Northeast, South, North Central, West) that
## each state belongs to.
aggregate(state.x77, list(Region = state.region), mean)

## Compute the averages according to region and the occurrence of more
## than 130 days of frost.
aggregate(state.x77,
          list(Region = state.region,
               Cold = state.x77[,"Frost"] > 130),
          mean)
## (Note that no state in 'South' is THAT cold.)

data(presidents)
## Compute the average annual approval ratings for American presidents.
aggregate(presidents, nf = 1, FUN = mean)
## Give the summer less weight.
aggregate(presidents, nf = 1, FUN = weighted.mean, w = c(1, 1, 0.5, 1))
}
\keyword{category}
\keyword{array}