这是一个示例数据框:
d <- data.frame(
x = runif(90),
grp = gl(3, 30)
)
我希望d
的子集包含x
的每个值的前5个值grp
的行。
使用base-R,我的方法类似于:
ordered <- d[order(d$x, decreasing = TRUE), ]
splits <- split(ordered, ordered$grp)
heads <- lapply(splits, head)
do.call(rbind, heads)
## x grp
## 1.19 0.8879631 1
## 1.4 0.8844818 1
## 1.12 0.8596197 1
## 1.26 0.8481809 1
## 1.18 0.8461516 1
## 1.29 0.8317092 1
## 2.31 0.9751049 2
## 2.34 0.9269764 2
## 2.57 0.8964114 2
## 2.58 0.8896466 2
## 2.45 0.8888834 2
## 2.35 0.8706823 2
## 3.74 0.9884852 3
## 3.73 0.9837653 3
## 3.83 0.9375398 3
## 3.64 0.9229036 3
## 3.69 0.8021373 3
## 3.86 0.7418946 3
使用dplyr
,我希望这可行:
d %>%
arrange_(~ desc(x)) %>%
group_by_(~ grp) %>%
head(n = 5)
但它只返回前5行。
为top_n
换取head
会返回整个d
。
d %>%
arrange_(~ desc(x)) %>%
group_by_(~ grp) %>%
top_n(n = 5)
如何获得正确的子集?
答案 0 :(得分:95)
来自?top_n
,关于wt
参数:
用于排序[...] 的变量默认为tbl&#34;中的最后一个变量。
数据集中的最后一个变量是&#34; grp&#34;,这不是您想要排名的变量,这就是您top_n
尝试&#34;返回整个d&的原因#34 ;.因此,如果你想按&#34; x&#34;在您的数据集中,您需要指定wt = x
。
set.seed(123)
d <- data.frame(
x = runif(90),
grp = gl(3, 30))
d %>%
group_by(grp) %>%
top_n(n = 5, wt = x)
# x grp
# 1 0.9404673 1
# 2 0.9568333 1
# 3 0.8998250 1
# 4 0.9545036 1
# 5 0.9942698 1
# 6 0.9630242 2
# 7 0.9022990 2
# 8 0.8578277 2
# 9 0.7989248 2
# 10 0.8950454 2
# 11 0.8146400 3
# 12 0.8123895 3
# 13 0.9849570 3
# 14 0.8930511 3
# 15 0.8864691 3
答案 1 :(得分:33)
data.table
也很容易......
library(data.table)
setorder(setDT(d), -x)[, head(.SD, 5), keyby = grp]
或者
setorder(setDT(d), grp, -x)[, head(.SD, 5), by = grp]
或者(对于大数据集应该更快,因为避免为每个组调用.SD
)
setorder(setDT(d), grp, -x)[, indx := seq_len(.N), by = grp][indx <= 5]
修改:dplyr
与data.table
的比较(如果有人感兴趣的话)
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
添加速度稍慢的data.table
解决方案:
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]$V1],
times = 10L
)
时序输出:
Unit: milliseconds
expr min lq mean median uq max neval
data.table3 826.2148 865.6334 950.1380 902.1689 1006.1237 1260.129 10
data.table4 729.3229 783.7000 859.2084 823.1635 966.8239 1014.397 10
答案 2 :(得分:24)
您需要将head
打包到do
。在以下代码中,.
代表当前组(请参阅...
帮助页面中do
的说明)。
d %>%
arrange_(~ desc(x)) %>%
group_by_(~ grp) %>%
do(head(., n = 5))
如akrun所述,slice
是另一种选择。
d %>%
arrange_(~ desc(x)) %>%
group_by_(~ grp) %>%
slice(1:5)
答案 3 :(得分:14)
我在基地R的方法是:
ordered <- d[order(d$x, decreasing = TRUE), ]
ordered[ave(d$x, d$grp, FUN = seq_along) <= 5L,]
使用dplyr,使用slice
的方法可能最快,但您也可以使用filter
,这可能比使用do(head(., 5))
更快:
d %>%
arrange(desc(x)) %>%
group_by(grp) %>%
filter(row_number() <= 5L)
set.seed(123)
d <- data.frame(
x = runif(1e6),
grp = sample(1e4, 1e6, TRUE))
library(microbenchmark)
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)},
times = 10,
unit = "relative"
)
Unit: relative
expr min lq median uq max neval
top_n 1.042735 1.075366 1.082113 1.085072 1.000846 10
dohead 18.663825 19.342854 19.511495 19.840377 17.433518 10
slice 1.000000 1.000000 1.000000 1.000000 1.000000 10
filter 1.048556 1.044113 1.042184 1.180474 1.053378 10
答案 4 :(得分:1)
top_n(n = 1)仍会为每个组返回多行。为了精确选择每个组的一个出现次数,请为每一行添加一个唯一变量:
set.seed(123)
d <- data.frame(
x = runif(90),
grp = gl(3, 30))
d %>%
mutate(rn = row_number()) %>%
group_by(grp) %>%
top_n(n = 1, wt = rn)
答案 5 :(得分:0)
另一个data.table
解决方案以突出其简洁的语法:
setDT(d)
d[order(-x), .SD[1:5], grp]