R - 如何在数据框中每行找到三个最小值？
R - How to find three smallest values per row in a data frame?
我有一个数据框，其中包含几个雨量计之间的距离，如下所示：
df <- structure(list(`1549` = c(NA, 490774.05, 290832.68, 87750.38,
138531.18, 103870.34, 112919.7, 19625.65, 398693.43, 73514.23,
129691.63, 64279.9, 141587.34, 43643.42, 122327.17, 223922.21,
159877.72, 259277.48, 397058.24, 162170.11), `1550` = c(490774.05,
NA, 346526.87, 575898.52, 437822.83, 576249.76, 568218.1, 509608.26,
123809.9, 562535.73, 564793.88, 550108.84, 407124.69, 484522.14,
438163.36, 266959.95, 426227.74, 288355.87, 118585.43, 451437.16
), `1551` = c(290832.68, 346526.87, NA, 344074.16, 162014.5,
322268.72, 302065.93, 308396.36, 222759.32, 336164.42, 285694.49,
351932.11, 149572.61, 256425.81, 174567.46, 207661.81, 140177.31,
83159.56, 228092.01, 154156.1), `1552` = c(87750.38, 575898.52,
344074.16, NA, 182091.17, 40867.26, 66590.75, 71839.53, 479119.61,
14460.63, 93261.62, 55663.25, 198493.52, 94903.03, 169984.4,
309812.1, 204134.81, 328832.15, 478194.47, 195100.02), `1553` = c(138531.18,
437822.83, 162014.5, 182091.17, NA, 161552.92, 143725.71, 153432.89,
325263.63, 174539.44, 132252.45, 194340.98, 31927.37, 98444.64,
16790.01, 198440.03, 22316.41, 159524.37, 326631.15, 29460.62
), `1554` = c(103870.34, 576249.76, 322268.72, 40867.26, 161552.92,
NA, 26830.77, 93867.72, 473756.48, 47917.78, 53473.37, 92965.23,
183147.09, 92489.91, 152245.46, 313474.9, 182522.18, 316347.16,
473608.16, 169315.19), `1555` = c(112919.7, 568218.1, 302065.93,
66590.75, 143725.71, 26830.77, NA, 107114.83, 462486.94, 71081.79,
26755.47, 114938.18, 168181.74, 90811.33, 136477.11, 308852.76,
163624.08, 301551.94, 462815.84, 148089.64), `1556` = c(19625.65,
509608.26, 308396.36, 71839.53, 153432.89, 93867.72, 107114.83,
NA, 418219.65, 57381.36, 127019.34, 44887.51, 158865.19, 55484.99,
137694.58, 242667.11, 175231.39, 278552.75, 416536.23, 175455.6
), `1557` = c(398693.43, 123809.9, 222759.32, 479119.61, 325263.63,
473756.48, 462486.94, 418219.65, NA, 466733.89, 455884.87, 461489.12,
296185.66, 384844.71, 327993.12, 185684.32, 311265.55, 169212.4,
9134.61, 335535.36), `1558` = c(73514.23, 562535.73, 336164.42,
14460.63, 174539.44, 47917.78, 71081.79, 57381.36, 466733.89,
NA, 96997.95, 45101.5, 189181.18, 83727.19, 161645.62, 296199.74,
196763.58, 318209.6, 465667.59, 189348.21), `1559` = c(129691.63,
564793.88, 285694.49, 93261.62, 132252.45, 53473.37, 26755.47,
127019.34, 455884.87, 96997.95, NA, 139876.37, 159753.19, 99985.18,
127897.21, 309991.97, 150269.39, 291728.65, 456729.45, 131782.96
), `1561` = c(64279.9, 550108.84, 351932.11, 55663.25, 194340.98,
92965.23, 114938.18, 44887.51, 461489.12, 45101.5, 139876.37,
NA, 202394.04, 96114.27, 179318.52, 283357.46, 216503.97, 323440.15,
459552.78, 214003.26), `1562` = c(141587.34, 407124.69, 149572.61,
198493.52, 31927.37, 183147.09, 168181.74, 158865.19, 296185.66,
189181.18, 159753.19, 202394.04, NA, 107341.48, 31911.1, 166860.76,
33107.97, 133450.41, 297181.53, 55912.87), `1563` = c(43643.42,
484522.14, 256425.81, 94903.03, 98444.64, 92489.91, 90811.33,
55484.99, 384844.71, 83727.19, 99985.18, 96114.27, 107341.48,
NA, 83210.44, 220988.12, 120496.54, 234506.15, 384171.99, 119976.68
), `1564` = c(122327.17, 438163.36, 174567.46, 169984.4, 16790.01,
152245.46, 136477.11, 137694.58, 327993.12, 161645.62, 127897.21,
179318.52, 31911.1, 83210.44, NA, 192483.7, 37576.32, 165076.25,
328900.73, 45164.38), `1565` = c(223922.21, 266959.95, 207661.81,
309812.1, 198440.03, 313474.9, 308852.76, 242667.11, 185684.32,
296199.74, 309991.97, 283357.46, 166860.76, 220988.12, 192483.7,
NA, 196022.38, 126522.76, 181932.96, 221505.05), `1566` = c(159877.72,
426227.74, 140177.31, 204134.81, 22316.41, 182522.18, 163624.08,
175231.39, 311265.55, 196763.58, 150269.39, 216503.97, 33107.97,
120496.54, 37576.32, 196022.38, NA, 143436.02, 313128.42, 26013.61
), `1567` = c(259277.48, 288355.87, 83159.56, 328832.15, 159524.37,
316347.16, 301551.94, 278552.75, 169212.4, 318209.6, 291728.65,
323440.15, 133450.41, 234506.15, 165076.25, 126522.76, 143436.02,
NA, 171940.61, 166888.68), `1568` = c(397058.24, 118585.43, 228092.01,
478194.47, 326631.15, 473608.16, 462815.84, 416536.23, 9134.61,
465667.59, 456729.45, 459552.78, 297181.53, 384171.99, 328900.73,
181932.96, 313128.42, 171940.61, NA, 337646.57), `1569` = c(162170.11,
451437.16, 154156.1, 195100.02, 29460.62, 169315.19, 148089.64,
175455.6, 335535.36, 189348.21, 131782.96, 214003.26, 55912.87,
119976.68, 45164.38, 221505.05, 26013.61, 166888.68, 337646.57,
NA)), row.names = c(1549L, 1550L, 1551L, 1552L, 1553L, 1554L,
1555L, 1556L, 1557L, 1558L, 1559L, 1561L, 1562L, 1563L, 1564L,
1565L, 1566L, 1567L, 1568L, 1569L), class = "data.frame")
行名和列名是每个仪表的 ID。仪表到自身的距离为 0，所以我用 NA 替换了 0。
对于每一行，我试图找到三个最近的仪表并将它们连同它们的 ID 一起保存。预期的输出将是这样的：
id nearest distance
1549 1556 19625.65
1549 1563 43643.42
1549 1561 64279.90
1550 1568 118585.43
1550 1557 123809.90
1550 1565 266959.95
等等。我可以用代码 t(apply(df, 1, sort)[ 1:3, ]) 找到最近的三个点，但我很难获得它们的 ID 并组装最终数据框...
我的实际数据集更大 (6289 x 6289)，那么达到预期结果的最快方法是什么？
我建议将您的数据转换为如下所示的长格式。然后，您可以按 ID 对它们进行分组，并找到每个 ID 的最小值：
library(tidyr)
library(dplyr)
df %>%
mutate(ID1=rownames(.)) %>%
gather('ID2','dist',-ID1) %>%
filter(!is.na(dist)) %>%
group_by(ID1) %>%
summarise(mindist=min(dist),nearest=ID2[which.min(dist)])
编辑：对于至少 n 个距离，您可以只对 aftergrouping 和 select 前 n:
进行排序
df %>%
mutate(ID1=rownames(.)) %>%
gather('ID2','dist',-ID1) %>%
filter(!is.na(dist)) %>%
group_by(ID1) %>%
arrange(dist) %>%
slice(1:3) %>%
mutate(dist_rank=1:3)
一种选择是使用 pivot_longer() 和 top_n()。
library(dplyr)
library(tidyr)
library(tibble)
df %>%
rownames_to_column() %>%
pivot_longer(cols = -rowname) %>%
group_by(rowname) %>%
top_n(-3, wt = value) %>%
arrange(rowname, value)
# A tibble: 60 x 3
# Groups: rowname [20]
rowname name value
<chr> <chr> <dbl>
1 1549 1556 19626.
2 1549 1563 43643.
3 1549 1561 64280.
4 1550 1568 118585.
5 1550 1557 123810.
6 1550 1565 266960.
7 1551 1567 83160.
8 1551 1566 140177.
9 1551 1562 149573.
10 1552 1558 14461.
# ... with 50 more rows
在基础 R 中，使用行名称创建所需的变量。
res <- do.call(rbind, lapply(1:nrow(df), function(i) {
r <- t(sort(df[i, ])[1:3])
data.frame(id=rownames(df[i, ]), nearest=rownames(r), distance=unname(r),
stringsAsFactors=FALSE)
}))
head(res)
# id nearest distance
# 1 1549 1556 19625.65
# 2 1549 1563 43643.42
# 3 1549 1561 64279.90
# 4 1550 1568 118585.43
# 5 1550 1557 123809.90
我有一个数据框，其中包含几个雨量计之间的距离，如下所示：
df <- structure(list(`1549` = c(NA, 490774.05, 290832.68, 87750.38,
138531.18, 103870.34, 112919.7, 19625.65, 398693.43, 73514.23,
129691.63, 64279.9, 141587.34, 43643.42, 122327.17, 223922.21,
159877.72, 259277.48, 397058.24, 162170.11), `1550` = c(490774.05,
NA, 346526.87, 575898.52, 437822.83, 576249.76, 568218.1, 509608.26,
123809.9, 562535.73, 564793.88, 550108.84, 407124.69, 484522.14,
438163.36, 266959.95, 426227.74, 288355.87, 118585.43, 451437.16
), `1551` = c(290832.68, 346526.87, NA, 344074.16, 162014.5,
322268.72, 302065.93, 308396.36, 222759.32, 336164.42, 285694.49,
351932.11, 149572.61, 256425.81, 174567.46, 207661.81, 140177.31,
83159.56, 228092.01, 154156.1), `1552` = c(87750.38, 575898.52,
344074.16, NA, 182091.17, 40867.26, 66590.75, 71839.53, 479119.61,
14460.63, 93261.62, 55663.25, 198493.52, 94903.03, 169984.4,
309812.1, 204134.81, 328832.15, 478194.47, 195100.02), `1553` = c(138531.18,
437822.83, 162014.5, 182091.17, NA, 161552.92, 143725.71, 153432.89,
325263.63, 174539.44, 132252.45, 194340.98, 31927.37, 98444.64,
16790.01, 198440.03, 22316.41, 159524.37, 326631.15, 29460.62
), `1554` = c(103870.34, 576249.76, 322268.72, 40867.26, 161552.92,
NA, 26830.77, 93867.72, 473756.48, 47917.78, 53473.37, 92965.23,
183147.09, 92489.91, 152245.46, 313474.9, 182522.18, 316347.16,
473608.16, 169315.19), `1555` = c(112919.7, 568218.1, 302065.93,
66590.75, 143725.71, 26830.77, NA, 107114.83, 462486.94, 71081.79,
26755.47, 114938.18, 168181.74, 90811.33, 136477.11, 308852.76,
163624.08, 301551.94, 462815.84, 148089.64), `1556` = c(19625.65,
509608.26, 308396.36, 71839.53, 153432.89, 93867.72, 107114.83,
NA, 418219.65, 57381.36, 127019.34, 44887.51, 158865.19, 55484.99,
137694.58, 242667.11, 175231.39, 278552.75, 416536.23, 175455.6
), `1557` = c(398693.43, 123809.9, 222759.32, 479119.61, 325263.63,
473756.48, 462486.94, 418219.65, NA, 466733.89, 455884.87, 461489.12,
296185.66, 384844.71, 327993.12, 185684.32, 311265.55, 169212.4,
9134.61, 335535.36), `1558` = c(73514.23, 562535.73, 336164.42,
14460.63, 174539.44, 47917.78, 71081.79, 57381.36, 466733.89,
NA, 96997.95, 45101.5, 189181.18, 83727.19, 161645.62, 296199.74,
196763.58, 318209.6, 465667.59, 189348.21), `1559` = c(129691.63,
564793.88, 285694.49, 93261.62, 132252.45, 53473.37, 26755.47,
127019.34, 455884.87, 96997.95, NA, 139876.37, 159753.19, 99985.18,
127897.21, 309991.97, 150269.39, 291728.65, 456729.45, 131782.96
), `1561` = c(64279.9, 550108.84, 351932.11, 55663.25, 194340.98,
92965.23, 114938.18, 44887.51, 461489.12, 45101.5, 139876.37,
NA, 202394.04, 96114.27, 179318.52, 283357.46, 216503.97, 323440.15,
459552.78, 214003.26), `1562` = c(141587.34, 407124.69, 149572.61,
198493.52, 31927.37, 183147.09, 168181.74, 158865.19, 296185.66,
189181.18, 159753.19, 202394.04, NA, 107341.48, 31911.1, 166860.76,
33107.97, 133450.41, 297181.53, 55912.87), `1563` = c(43643.42,
484522.14, 256425.81, 94903.03, 98444.64, 92489.91, 90811.33,
55484.99, 384844.71, 83727.19, 99985.18, 96114.27, 107341.48,
NA, 83210.44, 220988.12, 120496.54, 234506.15, 384171.99, 119976.68
), `1564` = c(122327.17, 438163.36, 174567.46, 169984.4, 16790.01,
152245.46, 136477.11, 137694.58, 327993.12, 161645.62, 127897.21,
179318.52, 31911.1, 83210.44, NA, 192483.7, 37576.32, 165076.25,
328900.73, 45164.38), `1565` = c(223922.21, 266959.95, 207661.81,
309812.1, 198440.03, 313474.9, 308852.76, 242667.11, 185684.32,
296199.74, 309991.97, 283357.46, 166860.76, 220988.12, 192483.7,
NA, 196022.38, 126522.76, 181932.96, 221505.05), `1566` = c(159877.72,
426227.74, 140177.31, 204134.81, 22316.41, 182522.18, 163624.08,
175231.39, 311265.55, 196763.58, 150269.39, 216503.97, 33107.97,
120496.54, 37576.32, 196022.38, NA, 143436.02, 313128.42, 26013.61
), `1567` = c(259277.48, 288355.87, 83159.56, 328832.15, 159524.37,
316347.16, 301551.94, 278552.75, 169212.4, 318209.6, 291728.65,
323440.15, 133450.41, 234506.15, 165076.25, 126522.76, 143436.02,
NA, 171940.61, 166888.68), `1568` = c(397058.24, 118585.43, 228092.01,
478194.47, 326631.15, 473608.16, 462815.84, 416536.23, 9134.61,
465667.59, 456729.45, 459552.78, 297181.53, 384171.99, 328900.73,
181932.96, 313128.42, 171940.61, NA, 337646.57), `1569` = c(162170.11,
451437.16, 154156.1, 195100.02, 29460.62, 169315.19, 148089.64,
175455.6, 335535.36, 189348.21, 131782.96, 214003.26, 55912.87,
119976.68, 45164.38, 221505.05, 26013.61, 166888.68, 337646.57,
NA)), row.names = c(1549L, 1550L, 1551L, 1552L, 1553L, 1554L,
1555L, 1556L, 1557L, 1558L, 1559L, 1561L, 1562L, 1563L, 1564L,
1565L, 1566L, 1567L, 1568L, 1569L), class = "data.frame")
行名和列名是每个仪表的 ID。仪表到自身的距离为 0，所以我用 NA 替换了 0。
对于每一行，我试图找到三个最近的仪表并将它们连同它们的 ID 一起保存。预期的输出将是这样的：
id nearest distance
1549 1556 19625.65
1549 1563 43643.42
1549 1561 64279.90
1550 1568 118585.43
1550 1557 123809.90
1550 1565 266959.95
等等。我可以用代码 t(apply(df, 1, sort)[ 1:3, ]) 找到最近的三个点，但我很难获得它们的 ID 并组装最终数据框...
我的实际数据集更大 (6289 x 6289)，那么达到预期结果的最快方法是什么？
我建议将您的数据转换为如下所示的长格式。然后，您可以按 ID 对它们进行分组，并找到每个 ID 的最小值：
library(tidyr)
library(dplyr)
df %>%
mutate(ID1=rownames(.)) %>%
gather('ID2','dist',-ID1) %>%
filter(!is.na(dist)) %>%
group_by(ID1) %>%
summarise(mindist=min(dist),nearest=ID2[which.min(dist)])
编辑：对于至少 n 个距离，您可以只对 aftergrouping 和 select 前 n:
进行排序df %>%
mutate(ID1=rownames(.)) %>%
gather('ID2','dist',-ID1) %>%
filter(!is.na(dist)) %>%
group_by(ID1) %>%
arrange(dist) %>%
slice(1:3) %>%
mutate(dist_rank=1:3)
一种选择是使用 pivot_longer() 和 top_n()。
library(dplyr)
library(tidyr)
library(tibble)
df %>%
rownames_to_column() %>%
pivot_longer(cols = -rowname) %>%
group_by(rowname) %>%
top_n(-3, wt = value) %>%
arrange(rowname, value)
# A tibble: 60 x 3
# Groups: rowname [20]
rowname name value
<chr> <chr> <dbl>
1 1549 1556 19626.
2 1549 1563 43643.
3 1549 1561 64280.
4 1550 1568 118585.
5 1550 1557 123810.
6 1550 1565 266960.
7 1551 1567 83160.
8 1551 1566 140177.
9 1551 1562 149573.
10 1552 1558 14461.
# ... with 50 more rows
在基础 R 中，使用行名称创建所需的变量。
res <- do.call(rbind, lapply(1:nrow(df), function(i) {
r <- t(sort(df[i, ])[1:3])
data.frame(id=rownames(df[i, ]), nearest=rownames(r), distance=unname(r),
stringsAsFactors=FALSE)
}))
head(res)
# id nearest distance
# 1 1549 1556 19625.65
# 2 1549 1563 43643.42
# 3 1549 1561 64279.90
# 4 1550 1568 118585.43
# 5 1550 1557 123809.90