I'm not entirely sure what you want, but maybe this does the trick?
data.frame.by <- function(data, variables, fun, ...) {
if (length(variables) == 0 ) {
df <- data.frame(results = 0)
df$results <- list(fun(data$value, ...))
return(df)
}
sorted <- sort.df(data, variables)[,c(variables), drop=FALSE]
duplicates <- duplicated(sorted[,variables, drop=FALSE])
index <- cumsum(!duplicates)
results <- by(data, index, fun, ...)
cols <- sorted[!duplicates,variables, drop=FALSE]
cols$results <- array(results)
cols
}
sort.df <- function(data, vars) {
data[do.call("order", data[,vars, drop=FALSE]), ,drop=FALSE]
}
dataset <- data.frame(gp1 = rep(1:2, c(4,4)), gp2 = rep(1:4,
c(2,2,2,2)), value = rnorm(8))
data.frame.by(dataset, c("gp1", "gp2"), function(data) mean(data$value))
data.frame.by(dataset, "gp1", function(data) tapply(data$value, data$gp2, mean))
data.frame.by(dataset, "gp1", function(data) lm(gp2 ~ value, data)) #
doesn't print, but everything is there ok
(note that the results column will be a list if necessary - this may
be a serious abuse of data frames, but I'm not sure and no one replied
when I queried the list)
Hadley
______________________________________________
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel
