SLOW split() function

Using Josh's nice example, with data.table's built-in 'by' (optimised
grouping) yields a 6 times speedup (100 seconds down to 15 on
my netbook).

system.time(all.2b <- lapply(si, function(.indx) { coef(lm(y ~

+ x, data=d[.indx,])) }))
? user ?system elapsed
144.501 ? 0.300 145.525

system.time(all.2c <- lapply(si, function(.indx) { minimal.lm(y

+ = d[.indx, y], x = d[.indx, list(int, x)]) }))
? user ?system elapsed
100.819 ? 0.084 101.552

system.time(all.2d <- d[,minimal.lm2(y=y, x=cbind(int, x)),by=key])

? user ?system elapsed
?15.269 ? 0.012 ?15.323 ? # 6 times faster

head(all.2c)

$`1`
? ? ? ?coef ? ? ? ?se
x1 0.5152438 0.6277254
x2 0.5621320 0.5754560

$`2`
? ? ? ?coef ? ? ? se
x1 0.2228235 0.312918
x2 0.3312261 0.261529

$`3`
? ? ? ? coef ? ? ? ?se
x1 -0.1972439 0.4674000
x2 -0.1674313 0.4479957

$`4`
? ? ? ? ?coef ? ? ? ?se
x1 -0.13915746 0.2729158
x2 -0.03409833 0.2212416

$`5`
? ? ? ? ? coef ? ? ? ?se
x1 ?0.007969786 0.2389103
x2 -0.083776526 0.2046823

$`6`
? ? ? ? ?coef ? ? ? ?se
x1 -0.58576454 0.5677619
x2 -0.07249539 0.5009013

head(all.2d)

? ? key ? ? ? coef ? ? ? ?V2
[1,] ? 1 ?0.5152438 0.6277254
[2,] ? 1 ?0.5621320 0.5754560
[3,] ? 2 ?0.2228235 0.3129180
[4,] ? 2 ?0.3312261 0.2615290
[5,] ? 3 -0.1972439 0.4674000
[6,] ? 3 -0.1674313 0.4479957

minimal.lm2 ? # slightly modified version of Josh's

function(y, x) {
?obj <- lm.fit(x = x, y = y)
?resvar <- sum(obj$residuals^2)/obj$df.residual
?p <- obj$rank
?R <- .Call("La_chol2inv", x = obj$qr$qr[1L:p, 1L:p, drop = FALSE],
size = p, PACKAGE = "base")
?m <- min(dim(R))
?d <- c(R)[1L + 0L:(m - 1L) * (dim(R)[1L] + 1L)]
?se <- sqrt(d * resvar)
?list(coef = obj$coefficients, se)
}

--
View this message in context: http://r.789695.n4.nabble.com/SLOW-split-function-tp3892349p3900851.html
Sent from the R help mailing list archive at Nabble.com.