我得到了一张表，我需要转换成另外两种形式。任何人都可以帮我找到一个系统的R-way来转换它而不需要一堆嵌套for循环？
这是表格的简化版本：
Status <- rep(c(paste0("B",seq(1,4)),"Total"),3)
FID <- c(rep("N123",10),rep("K541",5))
IID <- c(rep(123,5),rep(456,5),rep(789,5))
Value1.G1 <- c(rep(c(888,345,765,875,875,323),2),8039,830,849)
Value2.G1 <- c(rep(c(443,325,761),4),649,975,323)
Value1.G2 <- rep(c(446,345,765,875,323),3)
Value2.G2 <- c(rep(c(540,345,765),4),169,875,431)
dat <-data.frame(FID,IID,Status,Value1.G1,Value2.G1,Value1.G2,Value2.G2)
print(dat)
FID IID Status Value1.G1 Value2.G1 Value1.G2 Value2.G2
1 N123 123 B1 888 443 446 540
2 N123 123 B2 345 325 345 345
3 N123 123 B3 765 761 765 765
4 N123 123 B4 875 443 875 540
5 N123 123 Total 875 325 323 345
6 N123 456 B1 323 761 446 765
7 N123 456 B2 888 443 345 540
8 N123 456 B3 345 325 765 345
9 N123 456 B4 765 761 875 765
10 N123 456 Total 875 443 323 540
11 K541 789 B1 875 325 446 345
12 K541 789 B2 323 761 345 765
13 K541 789 B3 8039 649 765 169
14 K541 789 B4 830 975 875 875
15 K541 789 Total 849 323 323 431
简而言之，排除前三列，每个单元格中的数字是特定样本的特定值（在此示例中为Value1或Value2）123，{{ 1}}和456），在特定的凝胶（789和1）上，处于特定状态（2，B1，{{1 }，B2和B3）。前三列（B4，Total，FID）列出了有关示例（IID，Status）和状态（FID的信息）。
我需要创建的第一个表单将标题分解为组件部分。 （澄清点：＆＃34; Gel＆＃34;列是指＆＃34; G＆＃34;在列名称之后的前一个数值。）
IID我需要创建的第二种表单要求每个唯一的个人ID（Status）都包含一行，其中包含所有值的信息。在这种情况下，列名称表示关于值及其特定条件的所有信息（即哪个值，哪个凝胶和哪个状态）。使用此示例数据，这意味着有3行和22列。
FID IID Status Value1 Value2 Gel
1 N123 123 B1 888 443 1
2 N123 456 B1 323 761 1
3 K541 789 B1 875 325 1
4 N123 123 B1 446 540 2
5 N123 456 B1 446 765 2
6 K541 789 B1 446 345 2
7 N123 123 B2 345 325 1
8 N123 456 B2 888 443 1
9 K541 789 B2 323 761 1
10 N123 123 B2 345 345 2
11 N123 456 B2 345 540 2
12 K541 789 B2 345 765 2
13 N123 123 B3 765 761 1
14 N123 456 B3 345 325 1
15 K541 789 B3 8039 649 1
16 N123 123 B3 765 765 2
17 N123 456 B3 765 345 2
18 K541 789 B3 765 169 2
19 N123 123 B4 875 443 1
20 N123 456 B4 765 761 1
21 K541 789 B4 830 975 1
22 N123 123 B4 875 540 2
23 N123 456 B4 875 765 2
24 K541 789 B4 875 875 2
25 N123 123 Total 875 325 1
26 N123 456 Total 875 443 1
27 K541 789 Total 849 323 1
28 N123 123 Total 323 345 2
29 N123 456 Total 323 540 2
30 K541 789 Total 323 431 2
答案 0 :(得分：3)
使用?reshape
Status <- rep(c(paste0("B",seq(1,4)),"Total"),3)
FID <- c(rep("N123",10),rep("K541",5))
IID <- c(rep(123,5),rep(456,5),rep(789,5))
Value1.G1 <- c(rep(c(888,345,765,875,875,323),2),8039,830,849)
Value2.G1 <- c(rep(c(443,325,761),4),649,975,323)
Value1.G2 <- rep(c(446,345,765,875,323),3)
Value2.G2 <- c(rep(c(540,345,765),4),169,875,431)
dat <-data.frame(FID,IID,Status,Value1.G1,Value2.G1,Value1.G2,Value2.G2)
dat
用于长格式
l <- reshape(dat, direction = 'long', varying = list(c(4,6), c(5,7)),
v.names = c('Value1', 'Value2'), timevar = 'Gel')
l[order(l$Status), ]
# FID IID Status Gel Value1 Value2 id
# 1.1 N123 123 B1 1 888 443 1
# 6.1 N123 456 B1 1 323 761 6
# 11.1 K541 789 B1 1 875 325 11
# 1.2 N123 123 B1 2 446 540 1
# 6.2 N123 456 B1 2 446 765 6
# 11.2 K541 789 B1 2 446 345 11
# 2.1 N123 123 B2 1 345 325 2
# 7.1 N123 456 B2 1 888 443 7
# 12.1 K541 789 B2 1 323 761 12
# 2.2 N123 123 B2 2 345 345 2
# 7.2 N123 456 B2 2 345 540 7
# 12.2 K541 789 B2 2 345 765 12
# 3.1 N123 123 B3 1 765 761 3
# 8.1 N123 456 B3 1 345 325 8
# 13.1 K541 789 B3 1 8039 649 13
# 3.2 N123 123 B3 2 765 765 3
# 8.2 N123 456 B3 2 765 345 8
# 13.2 K541 789 B3 2 765 169 13
# 4.1 N123 123 B4 1 875 443 4
# 9.1 N123 456 B4 1 765 761 9
# 14.1 K541 789 B4 1 830 975 14
# 4.2 N123 123 B4 2 875 540 4
# 9.2 N123 456 B4 2 875 765 9
# 14.2 K541 789 B4 2 875 875 14
# 5.1 N123 123 Total 1 875 325 5
# 10.1 N123 456 Total 1 875 443 10
# 15.1 K541 789 Total 1 849 323 15
# 5.2 N123 123 Total 2 323 345 5
# 10.2 N123 456 Total 2 323 540 10
# 15.2 K541 789 Total 2 323 431 15
和广泛
reshape(dat, direction = 'wide', timevar = 'Status', idvar = names(dat)[1:2])
# FID IID Value1.G1.B1 Value2.G1.B1 Value1.G2.B1 Value2.G2.B1 Value1.G1.B2
# 1 N123 123 888 443 446 540 345
# 6 N123 456 323 761 446 765 888
# 11 K541 789 875 325 446 345 323
# Value2.G1.B2 Value1.G2.B2 Value2.G2.B2 Value1.G1.B3 Value2.G1.B3 Value1.G2.B3
# 1 325 345 345 765 761 765
# 6 443 345 540 345 325 765
# 11 761 345 765 8039 649 765
# Value2.G2.B3 Value1.G1.B4 Value2.G1.B4 Value1.G2.B4 Value2.G2.B4 Value1.G1.Total
# 1 765 875 443 875 540 875
# 6 345 765 761 875 765 875
# 11 169 830 975 875 875 849
# Value2.G1.Total Value1.G2.Total Value2.G2.Total
# 1 325 323 345
# 6 443 323 540
# 11 323 323 431
答案 1 :(得分：2)
您可以在melt的开发版本中尝试dcast，data.table，即v1.9.5，它可以使用多个值列。它可以从here
转换为＆＃39; wide＆＃39;要在＆＃39; data＆＃39;上使用melt，请使用数据表。 （setDT(dat) - 将＆quot; data.frame＆＃39;转换为＆＃39; data.table＆＃39;）并指定＆＃39; Value1＆＃39;和＆＃39; Value2＆的索引＃39;作为一个＆＃39;列表＆＃39;在measure.vars
library(data.table)#v1.9.5+
dM <- melt(setDT(dat), measure.vars=list(c(4,6), c(5,7)), variable.name='Gel')
dM[order(Status)]
# FID IID Status Gel value1 value2
# 1: N123 123 B1 1 888 443
# 2: N123 456 B1 1 323 761
# 3: K541 789 B1 1 875 325
# 4: N123 123 B1 2 446 540
# 5: N123 456 B1 2 446 765
# 6: K541 789 B1 2 446 345
# 7: N123 123 B2 1 345 325
# 8: N123 456 B2 1 888 443
# 9: K541 789 B2 1 323 761
#10: N123 123 B2 2 345 345
#11: N123 456 B2 2 345 540
#12: K541 789 B2 2 345 765
#13: N123 123 B3 1 765 761
#14: N123 456 B3 1 345 325
#15: K541 789 B3 1 8039 649
#16: N123 123 B3 2 765 765
#17: N123 456 B3 2 765 345
#18: K541 789 B3 2 765 169
#19: N123 123 B4 1 875 443
#20: N123 456 B4 1 765 761
#21: K541 789 B4 1 830 975
#22: N123 123 B4 2 875 540
#23: N123 456 B4 2 875 765
#24: K541 789 B4 2 875 875
#25: N123 123 Total 1 875 325
#26: N123 456 Total 1 875 443
#27: K541 789 Total 1 849 323
#28: N123 123 Total 2 323 345
#29: N123 456 Total 2 323 540
#30: K541 789 Total 2 323 431
我们可以转换长期＆＃39;格式为＆＃39;宽＆＃39;与dcast。在这里，我们在value.var
dC <- dcast(dM, FID+IID~Gel+Status, value.var=c('value1', 'value2'))
dC
# FID IID 1_B1_value1 1_B2_value1 1_B3_value1 1_B4_value1 1_Total_value1
#1: K541 789 875 323 8039 830 849
#2: N123 123 888 345 765 875 875
#3: N123 456 323 888 345 765 875
# 2_B1_value1 2_B2_value1 2_B3_value1 2_B4_value1 2_Total_value1 1_B1_value2
#1: 446 345 765 875 323 325
#2: 446 345 765 875 323 443
#3: 446 345 765 875 323 761
# 1_B2_value2 1_B3_value2 1_B4_value2 1_Total_value2 2_B1_value2 2_B2_value2
#1: 761 649 975 323 345 765
#2: 325 761 443 325 540 345
#3: 443 325 761 443 765 540
# 2_B3_value2 2_B4_value2 2_Total_value2
#1: 169 875 431
#2: 765 540 345
#3: 345 765 540
我们还可以从原始数据集中获取宽格式
dcast(setDT(dat), FID+IID~Status, value.var=names(dat)[4:7])
# FID IID B1_Value1.G1 B2_Value1.G1 B3_Value1.G1 B4_Value1.G1 Total_Value1.G1
#1: K541 789 875 323 8039 830 849
#2: N123 123 888 345 765 875 875
#3: N123 456 323 888 345 765 875
# B1_Value2.G1 B2_Value2.G1 B3_Value2.G1 B4_Value2.G1 Total_Value2.G1
#1: 325 761 649 975 323
#2: 443 325 761 443 325
#3: 761 443 325 761 443
# B1_Value1.G2 B2_Value1.G2 B3_Value1.G2 B4_Value1.G2 Total_Value1.G2
#1: 446 345 765 875 323
#2: 446 345 765 875 323
#3: 446 345 765 875 323
# B1_Value2.G2 B2_Value2.G2 B3_Value2.G2 B4_Value2.G2 Total_Value2.G2
#1: 345 765 169 875 431
#2: 540 345 765 540 345
#3: 765 540 345 765 540
只需仔细检查OP的预期输出（＆＃39; form1＆＃39;）
merge(dM,form1,by=c("FID","IID","Gel","Status"),suffixes=c("akrun","real"))
# FID IID Status Gel value1 value2 Value1 Value2
# 1: K541 789 B1 1 875 325 875 325
# 2: K541 789 B2 1 323 761 323 761
# 3: K541 789 B3 1 8039 649 8039 649
# 4: K541 789 B4 1 830 975 830 975
# 5: K541 789 Total 1 849 323 849 323
# 6: K541 789 B1 2 446 345 446 345
# 7: K541 789 B2 2 345 765 345 765
# 8: K541 789 B3 2 765 169 765 169
# 9: K541 789 B4 2 875 875 875 875
# 10: K541 789 Total 2 323 431 323 431
# 11: N123 123 B1 1 888 443 888 443
# 12: N123 123 B2 1 345 325 345 325
# 13: N123 123 B3 1 765 761 765 761
# 14: N123 123 B4 1 875 443 875 443
# 15: N123 123 Total 1 875 325 875 325
# 16: N123 123 B1 2 446 540 446 540
# 17: N123 123 B2 2 345 345 345 345
# 18: N123 123 B3 2 765 765 765 765
# 19: N123 123 B4 2 875 540 875 540
# 20: N123 123 Total 2 323 345 323 345
# 21: N123 456 B1 1 323 761 323 761
# 22: N123 456 B2 1 888 443 888 443
# 23: N123 456 B3 1 345 325 345 325
# 24: N123 456 B4 1 765 761 765 761
# 25: N123 456 Total 1 875 443 875 443
# 26: N123 456 B1 2 446 765 446 765
# 27: N123 456 B2 2 345 540 345 540
# 28: N123 456 B3 2 765 345 765 345
# 29: N123 456 B4 2 875 765 875 765
# 30: N123 456 Total 2 323 540 323 540