根据R中的四个条件用两列计算值
Calculate value with two columns based on four conditions in R
我在 r 中上传了一个大型数据集（简短版本见下文）：我想为每个 Cruiseid、Samplenr、Species 和 [= 计算一个值16=]（所以基于四个条件）：
Cruiseid Samplenr Species Age Length LK TNumStat TNumLK
197502 37 154 0 12,5 2 2,791666667 5,583333
197502 37 154 0 17,5 3 2,166666667 6,5
197502 37 154 2 172,5 34 11,54166667 392,4167
197502 37 154 2 177,5 35 12,0625 422,1875
197502 37 154 2 182,5 36 2,083333333 75
197502 35 154 0 112,5 22 11,85654008 260,8439
197502 35 154 2 197,5 39 2,109704641 82,27848
197502 35 154 2 217,5 43 2,109704641 90,7173
197502 35 154 2 232,5 46 2,109704641 97,04641
197502 36 154 0 12,5 2 4,685314685 9,370629
197502 36 154 2 182,5 36 3,496503497 125,8741
197502 41 154 0 17,5 3 2,260869565 6,782609
197502 41 154 2 202,5 40 4,347826087 173,913
197502 41 154 2 212,5 42 2,173913043 91,30435
197502 41 154 2 242,5 48 2,173913043 104,3478
197503 56 154 0 17,5 3 7,428571429 22,28571
197503 56 154 0 147,5 29 10,30952381 298,9762
197503 56 154 2 172,5 34 13,19047619 448,4762
197503 56 154 2 187,5 37 2,380952381 88,09524
197503 54 154 0 12,5 2 3,35 6,7
197503 54 154 0 157,5 31 12 372
197503 54 154 0 167,5 33 13,25 437,25
197503 54 154 2 172,5 34 13,85 470,9
197503 54 154 2 187,5 37 2,5 92,5
197503 54 154 2 217,5 43 2,5 107,5
197503 53 154 0 12,5 2 2,875536481 5,751073
197503 53 154 0 97,5 19 4,806866953 91,33047
197503 53 154 0 107,5 21 5,622317597 118,0687
197503 53 154 0 142,5 28 8,776824034 245,7511
我想计算：((TNumStat$TNumLK/TNumStat$TNumStat)*0.5+0.25)*10每个 Cruiseid、Samplenr、Species 和 Age。
我已经在循环构造中尝试过一些东西：
#######################
Cruise <- unique(TNumStat$Cruiseid)
Track <- unique(TNumStat$Samplenr)
#######################
AvrLengthCr <- c()
AvrLengthCr <- rep(NA, length(TNumStat$Species))
#######################
for(j in 1:length(Cruise)){
t1.ss <- which(TNumStat$Cruiseid == Cruise[j])
###
for(i in 1:length(Track)){
t2.ss <- which(TNumStat$Samplenr[t1.ss] == Track[i])
###
AvrLengthCr[t1.ss][t2.ss] <- ((TNumStat$TNumLK[t1.ss][t2.ss]/TNumStat$TNumStat[t1.ss][t2.ss])*0.5+0.25)*10
}}
但是好像不行。我也一直在看 dcast:
TNumStat2<-dcast(TNumStat,Cruiseid+Samplenr+Species+Age,formula = (((TNumStat$TNumLK/TNumStat$TNumStat*0.5+0.25)*10) )),na.rm=TRUE)
我试过的选项似乎都不起作用，我不知道如何解决这个问题。有人可以帮我吗？
谢谢
早上好，
我认为这个问题不是很清楚。但是你可以尝试类似的东西 (with dplyr)
sample <- sample %>%
mutate(calculate = ((TNumLK/TNumStat) * 0.5 + 0.25) * 10) %>%
group_by(Cruiseid, Samplenr, Species, Age)
summarisedDF <- sample %>%
summarise(avg.calculate = mean(calculate))
令我印象深刻的是您的列 "Length", "TNumStat", "TNumLK" 有 , 而不是 .，因此是字符格式，不能轻易转换为数字。
TNumStat[c("TNumStat", "TNumLK")] <-
lapply(TNumStat[c("TNumStat", "TNumLK")],
function(x) as.numeric(gsub(",", ".", x)))
这可能取决于您的系统区域设置，所以如果适合您，请忽略此步骤。
然后，您可以使用 by 来应用您的公式。
l <- by(TNumStat, TNumStat[c("Cruiseid", "Samplenr", "Species")],
function(x) cbind(unique(x[1:3]),
value=with(x, ((mean(TNumLK)/mean(TNumStat))*0.5+0.25)*10)))
这为您提供了一个列表，您 rbind 可以得到结果。
TNumStat.new <- do.call(rbind, l)
TNumStat.new
# Cruiseid Samplenr Species value
# 6 197502 35 154 148.46288
# 10 197502 36 154 85.14956
# 1 197502 37 154 149.61421
# 12 197502 41 154 174.24600
# 26 197503 53 154 106.86347
# 20 197503 54 154 159.17545
# 16 197503 56 154 131.26698
数据
TNumStat <- structure(list(Cruiseid = c(197502L, 197502L, 197502L, 197502L,
197502L, 197502L, 197502L, 197502L, 197502L, 197502L, 197502L,
197502L, 197502L, 197502L, 197502L, 197503L, 197503L, 197503L,
197503L, 197503L, 197503L, 197503L, 197503L, 197503L, 197503L,
197503L, 197503L, 197503L, 197503L), Samplenr = c(37L, 37L, 37L,
37L, 37L, 35L, 35L, 35L, 35L, 36L, 36L, 41L, 41L, 41L, 41L, 56L,
56L, 56L, 56L, 54L, 54L, 54L, 54L, 54L, 54L, 53L, 53L, 53L, 53L
), Species = c(154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L,
154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L,
154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L),
Age = c(0L, 0L, 2L, 2L, 2L, 0L, 2L, 2L, 2L, 0L, 2L, 0L, 2L,
2L, 2L, 0L, 0L, 2L, 2L, 0L, 0L, 0L, 2L, 2L, 2L, 0L, 0L, 0L,
0L), Length = structure(c(3L, 8L, 9L, 10L, 11L, 2L, 13L,
16L, 17L, 3L, 11L, 8L, 14L, 15L, 18L, 8L, 5L, 9L, 12L, 3L,
6L, 7L, 9L, 12L, 16L, 3L, 19L, 1L, 4L), .Label = c("107,5",
"112,5", "12,5", "142,5", "147,5", "157,5", "167,5", "17,5",
"172,5", "177,5", "182,5", "187,5", "197,5", "202,5", "212,5",
"217,5", "232,5", "242,5", "97,5"), class = "factor"), LK = c(2L,
3L, 34L, 35L, 36L, 22L, 39L, 43L, 46L, 2L, 36L, 3L, 40L,
42L, 48L, 3L, 29L, 34L, 37L, 2L, 31L, 33L, 34L, 37L, 43L,
2L, 19L, 21L, 28L), TNumStat = structure(c(16L, 11L, 2L,
5L, 9L, 3L, 10L, 10L, 10L, 21L, 19L, 13L, 20L, 12L, 12L,
24L, 1L, 6L, 14L, 18L, 4L, 7L, 8L, 15L, 15L, 17L, 22L, 23L,
25L), .Label = c("10,30952381", "11,54166667", "11,85654008",
"12", "12,0625", "13,19047619", "13,25", "13,85", "2,083333333",
"2,109704641", "2,166666667", "2,173913043", "2,260869565",
"2,380952381", "2,5", "2,791666667", "2,875536481", "3,35",
"3,496503497", "4,347826087", "4,685314685", "4,806866953",
"5,622317597", "7,428571429", "8,776824034"), class = "factor"),
TNumLK = structure(c(16L, 18L, 11L, 12L, 21L, 8L, 22L, 25L,
29L, 24L, 4L, 20L, 5L, 26L, 1L, 6L, 9L, 14L, 23L, 19L, 10L,
13L, 15L, 28L, 2L, 17L, 27L, 3L, 7L), .Label = c("104,3478",
"107,5", "118,0687", "125,8741", "173,913", "22,28571", "245,7511",
"260,8439", "298,9762", "372", "392,4167", "422,1875", "437,25",
"448,4762", "470,9", "5,583333", "5,751073", "6,5", "6,7",
"6,782609", "75", "82,27848", "88,09524", "9,370629", "90,7173",
"91,30435", "91,33047", "92,5", "97,04641"), class = "factor")), class = "data.frame", row.names = c(NA,
-29L))
我在 r 中上传了一个大型数据集（简短版本见下文）：我想为每个 Cruiseid、Samplenr、Species 和 [= 计算一个值16=]（所以基于四个条件）：
Cruiseid Samplenr Species Age Length LK TNumStat TNumLK
197502 37 154 0 12,5 2 2,791666667 5,583333
197502 37 154 0 17,5 3 2,166666667 6,5
197502 37 154 2 172,5 34 11,54166667 392,4167
197502 37 154 2 177,5 35 12,0625 422,1875
197502 37 154 2 182,5 36 2,083333333 75
197502 35 154 0 112,5 22 11,85654008 260,8439
197502 35 154 2 197,5 39 2,109704641 82,27848
197502 35 154 2 217,5 43 2,109704641 90,7173
197502 35 154 2 232,5 46 2,109704641 97,04641
197502 36 154 0 12,5 2 4,685314685 9,370629
197502 36 154 2 182,5 36 3,496503497 125,8741
197502 41 154 0 17,5 3 2,260869565 6,782609
197502 41 154 2 202,5 40 4,347826087 173,913
197502 41 154 2 212,5 42 2,173913043 91,30435
197502 41 154 2 242,5 48 2,173913043 104,3478
197503 56 154 0 17,5 3 7,428571429 22,28571
197503 56 154 0 147,5 29 10,30952381 298,9762
197503 56 154 2 172,5 34 13,19047619 448,4762
197503 56 154 2 187,5 37 2,380952381 88,09524
197503 54 154 0 12,5 2 3,35 6,7
197503 54 154 0 157,5 31 12 372
197503 54 154 0 167,5 33 13,25 437,25
197503 54 154 2 172,5 34 13,85 470,9
197503 54 154 2 187,5 37 2,5 92,5
197503 54 154 2 217,5 43 2,5 107,5
197503 53 154 0 12,5 2 2,875536481 5,751073
197503 53 154 0 97,5 19 4,806866953 91,33047
197503 53 154 0 107,5 21 5,622317597 118,0687
197503 53 154 0 142,5 28 8,776824034 245,7511
我想计算：((TNumStat$TNumLK/TNumStat$TNumStat)*0.5+0.25)*10每个 Cruiseid、Samplenr、Species 和 Age。
我已经在循环构造中尝试过一些东西：
#######################
Cruise <- unique(TNumStat$Cruiseid)
Track <- unique(TNumStat$Samplenr)
#######################
AvrLengthCr <- c()
AvrLengthCr <- rep(NA, length(TNumStat$Species))
#######################
for(j in 1:length(Cruise)){
t1.ss <- which(TNumStat$Cruiseid == Cruise[j])
###
for(i in 1:length(Track)){
t2.ss <- which(TNumStat$Samplenr[t1.ss] == Track[i])
###
AvrLengthCr[t1.ss][t2.ss] <- ((TNumStat$TNumLK[t1.ss][t2.ss]/TNumStat$TNumStat[t1.ss][t2.ss])*0.5+0.25)*10
}}
但是好像不行。我也一直在看 dcast:
TNumStat2<-dcast(TNumStat,Cruiseid+Samplenr+Species+Age,formula = (((TNumStat$TNumLK/TNumStat$TNumStat*0.5+0.25)*10) )),na.rm=TRUE)
我试过的选项似乎都不起作用，我不知道如何解决这个问题。有人可以帮我吗？
谢谢
早上好，
我认为这个问题不是很清楚。但是你可以尝试类似的东西 (with dplyr)
sample <- sample %>%
mutate(calculate = ((TNumLK/TNumStat) * 0.5 + 0.25) * 10) %>%
group_by(Cruiseid, Samplenr, Species, Age)
summarisedDF <- sample %>%
summarise(avg.calculate = mean(calculate))
令我印象深刻的是您的列 "Length", "TNumStat", "TNumLK" 有 , 而不是 .，因此是字符格式，不能轻易转换为数字。
TNumStat[c("TNumStat", "TNumLK")] <-
lapply(TNumStat[c("TNumStat", "TNumLK")],
function(x) as.numeric(gsub(",", ".", x)))
这可能取决于您的系统区域设置，所以如果适合您，请忽略此步骤。
然后，您可以使用 by 来应用您的公式。
l <- by(TNumStat, TNumStat[c("Cruiseid", "Samplenr", "Species")],
function(x) cbind(unique(x[1:3]),
value=with(x, ((mean(TNumLK)/mean(TNumStat))*0.5+0.25)*10)))
这为您提供了一个列表，您 rbind 可以得到结果。
TNumStat.new <- do.call(rbind, l)
TNumStat.new
# Cruiseid Samplenr Species value
# 6 197502 35 154 148.46288
# 10 197502 36 154 85.14956
# 1 197502 37 154 149.61421
# 12 197502 41 154 174.24600
# 26 197503 53 154 106.86347
# 20 197503 54 154 159.17545
# 16 197503 56 154 131.26698
数据
TNumStat <- structure(list(Cruiseid = c(197502L, 197502L, 197502L, 197502L,
197502L, 197502L, 197502L, 197502L, 197502L, 197502L, 197502L,
197502L, 197502L, 197502L, 197502L, 197503L, 197503L, 197503L,
197503L, 197503L, 197503L, 197503L, 197503L, 197503L, 197503L,
197503L, 197503L, 197503L, 197503L), Samplenr = c(37L, 37L, 37L,
37L, 37L, 35L, 35L, 35L, 35L, 36L, 36L, 41L, 41L, 41L, 41L, 56L,
56L, 56L, 56L, 54L, 54L, 54L, 54L, 54L, 54L, 53L, 53L, 53L, 53L
), Species = c(154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L,
154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L,
154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L, 154L),
Age = c(0L, 0L, 2L, 2L, 2L, 0L, 2L, 2L, 2L, 0L, 2L, 0L, 2L,
2L, 2L, 0L, 0L, 2L, 2L, 0L, 0L, 0L, 2L, 2L, 2L, 0L, 0L, 0L,
0L), Length = structure(c(3L, 8L, 9L, 10L, 11L, 2L, 13L,
16L, 17L, 3L, 11L, 8L, 14L, 15L, 18L, 8L, 5L, 9L, 12L, 3L,
6L, 7L, 9L, 12L, 16L, 3L, 19L, 1L, 4L), .Label = c("107,5",
"112,5", "12,5", "142,5", "147,5", "157,5", "167,5", "17,5",
"172,5", "177,5", "182,5", "187,5", "197,5", "202,5", "212,5",
"217,5", "232,5", "242,5", "97,5"), class = "factor"), LK = c(2L,
3L, 34L, 35L, 36L, 22L, 39L, 43L, 46L, 2L, 36L, 3L, 40L,
42L, 48L, 3L, 29L, 34L, 37L, 2L, 31L, 33L, 34L, 37L, 43L,
2L, 19L, 21L, 28L), TNumStat = structure(c(16L, 11L, 2L,
5L, 9L, 3L, 10L, 10L, 10L, 21L, 19L, 13L, 20L, 12L, 12L,
24L, 1L, 6L, 14L, 18L, 4L, 7L, 8L, 15L, 15L, 17L, 22L, 23L,
25L), .Label = c("10,30952381", "11,54166667", "11,85654008",
"12", "12,0625", "13,19047619", "13,25", "13,85", "2,083333333",
"2,109704641", "2,166666667", "2,173913043", "2,260869565",
"2,380952381", "2,5", "2,791666667", "2,875536481", "3,35",
"3,496503497", "4,347826087", "4,685314685", "4,806866953",
"5,622317597", "7,428571429", "8,776824034"), class = "factor"),
TNumLK = structure(c(16L, 18L, 11L, 12L, 21L, 8L, 22L, 25L,
29L, 24L, 4L, 20L, 5L, 26L, 1L, 6L, 9L, 14L, 23L, 19L, 10L,
13L, 15L, 28L, 2L, 17L, 27L, 3L, 7L), .Label = c("104,3478",
"107,5", "118,0687", "125,8741", "173,913", "22,28571", "245,7511",
"260,8439", "298,9762", "372", "392,4167", "422,1875", "437,25",
"448,4762", "470,9", "5,583333", "5,751073", "6,5", "6,7",
"6,782609", "75", "82,27848", "88,09524", "9,370629", "90,7173",
"91,30435", "91,33047", "92,5", "97,04641"), class = "factor")), class = "data.frame", row.names = c(NA,
-29L))