我注意到您要求最有效的方法——如果您正在考虑将其扩展到更大的集合,我强烈建议您使用 data.table。
library(data.table)
library(RcppRoll)
l[, .(sum = RcppRoll::roll_sum(y, n = 2L, fill = NA, align = "left"),
seq = seq_len(.N)),
keyby = .(x)][!is.na(sum)]
将此与使用具有 100,000 行和 10,000 组的 tidyverse 包的答案进行粗略的基准比较说明了显着差异。
(我使用 Psidom 的答案而不是 jazzurro 的答案,因为 jazzuro 不允许对任意数量的行求和。)
library(tibble)
library(dplyr)
library(RcppRoll)
library(stringi) ## Only included for ability to generate random strings
## Generate data with arbitrary number of groups and rows --------------
rowCount <- 100000
groupCount <- 10000
sumRows <- 2L
set.seed(1)
l <- tibble(x = sample(stri_rand_strings(groupCount,3),rowCount,rep=TRUE),
y = sample(0:10,rowCount,rep=TRUE))
## Using dplyr and tibble -----------------------------------------------
ptm <- proc.time() ## Start the clock
dplyr_result <- l %>%
group_by(x) %>%
do(
data.frame(
sum = roll_sum(.$y, sumRows),
seq = seq_len(length(.$y) - sumRows + 1)
)
)
|========================================================0% ~0 s remaining
dplyr_time <- proc.time() - ptm ## Stop the clock
## Using data.table instead ----------------------------------------------
library(data.table)
ptm <- proc.time() ## Start the clock
setDT(l) ## Convert l to a data.table
dt_result <- l[,.(sum = RcppRoll::roll_sum(y, n = sumRows, fill = NA, align = "left"),
seq = seq_len(.N)),
keyby = .(x)][!is.na(sum)]
data.table_time <- proc.time() - ptm ## Stop the clock
结果:
> dplyr_time
user system elapsed
10.28 0.04 10.36
> data.table_time
user system elapsed
0.35 0.02 0.36
> all.equal(dplyr_result,as.tibble(dt_result))
[1] TRUE