Super fast group by, code from: http://stackoverflow.com/questions/3685492/r-speeding-up-group-by-operations. Especially, the `id()` function could prove very useful in building indices.

README.md

Super fast group by, code from: http://stackoverflow.com/questions/3685492/r-speeding-up-group-by-operations.
Especially, the id() function could prove very useful in building indices.

super_fast_group_by.R

# Set up some example data
year <-    sample(1970:2008, 1e6, rep=T)
state <-   sample(1:50, 1e6, rep=T)
group1 <-  sample(1:6, 1e6, rep=T)
group2 <-  sample(1:3, 1e6, rep=T)
myFact <-  rnorm(100, 15, 1e6)
weights <- rnorm(1e6)
myDF <- data.frame(year, state, group1, group2, myFact, weights)


library(plyr)
system.time({
  ids <- id(myDF[c("year", "state", "group1", "group2")], drop = TRUE)
  data <- as.matrix(myDF[c("myFact", "weights")])
  indices <- plyr:::split_indices(seq_len(nrow(data)), ids, n = attr(ids, "n"))

  fun <- function(rows) {
    weighted.mean(data[rows, 1], data[rows, 2])
  }
  values <- vapply(indices, fun, numeric(1))

  labels <- myDF[match(seq_len(attr(ids, "n")), ids), 
    c("year", "state", "group1", "group2")]
  aggregateDF <- cbind(labels, values)})