data.table
あまりにも簡単です...
library(data.table)
setorder(setDT(d), -x)[, head(.SD, 5), keyby = grp]
または
setorder(setDT(d), grp, -x)[, head(.SD, 5), by = grp]
または(.SD
各グループの呼び出しを回避するため、ビッグデータセットの方が高速です)
setorder(setDT(d), grp, -x)[, indx := seq_len(.N), by = grp][indx <= 5]
編集:これは(だれかに興味がある場合)dplyr
と比較する方法data.table
です
set.seed(123)
d <- data.frame(
x = runif(1e6),
grp = sample(1e4, 1e6, TRUE))
library(dplyr)
library(microbenchmark)
library(data.table)
dd <- copy(d)
microbenchmark(
top_n = {d %>%
group_by(grp) %>%
top_n(n = 5, wt = x)},
dohead = {d %>%
arrange_(~ desc(x)) %>%
group_by_(~ grp) %>%
do(head(., n = 5))},
slice = {d %>%
arrange_(~ desc(x)) %>%
group_by_(~ grp) %>%
slice(1:5)},
filter = {d %>%
arrange(desc(x)) %>%
group_by(grp) %>%
filter(row_number() <= 5L)},
data.table1 = setorder(setDT(dd), -x)[, head(.SD, 5L), keyby = grp],
data.table2 = setorder(setDT(dd), grp, -x)[, head(.SD, 5L), grp],
data.table3 = setorder(setDT(dd), grp, -x)[, indx := seq_len(.N), grp][indx <= 5L],
times = 10,
unit = "relative"
)
# expr min lq mean median uq max neval
# top_n 24.246401 24.492972 16.300391 24.441351 11.749050 7.644748 10
# dohead 122.891381 120.329722 77.763843 115.621635 54.996588 34.114738 10
# slice 27.365711 26.839443 17.714303 26.433924 12.628934 7.899619 10
# filter 27.755171 27.225461 17.936295 26.363739 12.935709 7.969806 10
# data.table1 13.753046 16.631143 10.775278 16.330942 8.359951 5.077140 10
# data.table2 12.047111 11.944557 7.862302 11.653385 5.509432 3.642733 10
# data.table3 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 10
わずかに速いdata.table
ソリューションを追加する:
set.seed(123L)
d <- data.frame(
x = runif(1e8),
grp = sample(1e4, 1e8, TRUE))
setDT(d)
setorder(d, grp, -x)
dd <- copy(d)
library(microbenchmark)
microbenchmark(
data.table3 = d[, indx := seq_len(.N), grp][indx <= 5L],
data.table4 = dd[dd[, .I[seq_len(.N) <= 5L], grp]$V1],
times = 10L
)
タイミング出力:
Unit: milliseconds
expr min lq mean median uq max neval
data.table3 826.2148 865.6334 950.1380 902.1689 1006.1237 1260.129 10
data.table4 729.3229 783.7000 859.2084 823.1635 966.8239 1014.397 10