如何在 R 中的函数中计算两个数据集之间的差异时保留数据集的 ID

How to Keep the id of a dataset when calculating the difference between two datasets within a function in R

我有一个函数可以计算 2 个数据集中行之间的差异(基于相同的列)。我想在计算后保留 id,因为在与另一个 table 合并后我需要它。我实际上不知道如何执行此步骤。这是数据和函数。

# data frame for recipients
IDr= c(seq(1,4))
Blood_type_r=c("A","B","AB","O")
data_R=data.frame(IDr,Blood_type_r,A=rep(0,4),B=c(rep(0,3),1),C=c(rep(1,3),0),D=rep(1,4),E=c(rep(0,2),rep(1,1),0),stringsAsFactors=FALSE)

  data_R
  IDr Blood_type_r A B C D E
1   1            A 0 0 1 1 0
2   2            B 0 0 1 1 0
3   3           AB 0 0 1 1 1
4   4            O 0 1 0 1 0
# data frame for donors 
IDd= c(seq(1,8))
Blood_type_d= c(rep("A", each=2),rep("B", each=2),rep("AB", each=2),rep("O", each=2))
WD= c(rep(0.25, each=2),rep(0.125, each=2),rep(0.125, each=2),rep(0.5, each=2))
data_D=data.frame(IDd,Blood_type_d,A=c(rep(0,6),1,1),B=c(rep(0,6),1,1),C=c(rep(1,7),0),D=rep(1,8),E=c(rep(0,6),rep(1,1),0),WD,stringsAsFactors=FALSE)
  data_D
  IDd Blood_type_d A B C D E    WD
1   1            A 0 0 1 1 0 0.250
2   2            A 0 0 1 1 0 0.250
3   3            B 0 0 1 1 0 0.125
4   4            B 0 0 1 1 0 0.125
5   5           AB 0 0 1 1 0 0.125
6   6           AB 0 0 1 1 0 0.125
7   7            O 1 1 1 1 1 0.500
8   8            O 1 1 0 1 0 0.500

# function
soustraction.i=function(D,R,i,threshold){
  D=as.data.frame(D)
  R=as.data.frame(R)
  dif=map2_df(D, R[i,], `-`)
  dif[dif<0] = 0
  dif$mismatch=rowSums(dif)
  dif=dif[which(dif$mismatch <= threshold),]
  return(dif)
  
}

 soustraction.i(data_D[,3:7],data_R[,3:7],1,3)
# A tibble: 8 x 6
      A     B     C     D     E mismatch
  <dbl> <dbl> <dbl> <dbl> <dbl>    <dbl>
1     0     0     0     0     0        0
2     0     0     0     0     0        0
3     0     0     0     0     0        0
4     0     0     0     0     0        0
5     0     0     0     0     0        0
6     0     0     0     0     0        0
7     1     1     0     0     1        3
8     1     1     0     0     0        2

我想要这样的输出(为捐赠者保留 IDd),但我不知道该怎么做,因为当我将它作为参数传递时,我的 2 个数据集必须具有相同的列数。例如,如果我将阈值设置为 3,我应该拥有来自捐赠者的所有 IDd table。

    IDd    A     B     C     D     E mismatch

1   1      0     0     0     0     0        0
2   2      0     0     0     0     0        0
3   3      0     0     0     0     0        0
4   4      0     0     0     0     0        0
5   5      0     0     0     0     0        0
6   6      0     0     0     0     0        0
7   7      1     1     0     0     1        3
8   8      1     1     0     0     0        2

感谢任何帮助,谢谢。

您可以将 ID 作为参数传入:

IDr= c(seq(1,4))
Blood_type_r=c("A","B","AB","O")
data_R=data.frame(IDr,Blood_type_r,A=rep(0,4),B=c(rep(0,3),1),C=c(rep(1,3),0),D=rep(1,4),E=c(rep(0,2),rep(1,1),0),stringsAsFactors=FALSE)
IDd= c(seq(1,8))
Blood_type_d= c(rep("A", each=2),rep("B", each=2),rep("AB", each=2),rep("O", each=2))
WD= c(rep(0.25, each=2),rep(0.125, each=2),rep(0.125, each=2),rep(0.5, each=2))
data_D=data.frame(IDd,Blood_type_d,A=c(rep(0,6),1,1),B=c(rep(0,6),1,1),C=c(rep(1,7),0),D=rep(1,8),E=c(rep(0,6),rep(1,1),0),WD,stringsAsFactors=FALSE)

soustraction.i=function(D,R,i,threshold, id){
  if(nrow(D) != length(id))stop("Length of id has to be same as number of rows of D\n")
  D=as.data.frame(D)
  R=as.data.frame(R)
  dif=map2_df(D, R[i,], `-`)
  dif[dif<0] = 0
  dif$mismatch=rowSums(dif)
  dif=dif[which(dif$mismatch <= threshold),]
  col1 <- colnames(dif)[1]
  dif <- dif %>% 
    tibble::add_column(IDd = id, .before=col1)
  return(dif)
  
}

soustraction.i(data_D[,3:7],data_R[,3:7],1,3, id=IDd)
# # A tibble: 8 x 7
#    ID_d     A     B     C     D     E mismatch
#   <int> <dbl> <dbl> <dbl> <dbl> <dbl>    <dbl>
# 1     1     0     0     0     0     0        0
# 2     2     0     0     0     0     0        0
# 3     3     0     0     0     0     0        0
# 4     4     0     0     0     0     0        0
# 5     5     0     0     0     0     0        0
# 6     6     0     0     0     0     0        0
# 7     7     1     1     0     0     1        3
# 8     8     1     1     0     0     0        2


要在输出中包含 Id 列,您应该首先将其传递到输入中。试试这个功能:

soustraction.i=function(D,R,i,threshold){
  D=as.data.frame(D)
  R=as.data.frame(R)
  dif=purrr::map2_df(D[-1], R[i,], `-`)
  dif[dif<0] = 0
  dif$mismatch=rowSums(dif)
  dif= cbind(ID = D[1], dif)
  dif=dif[which(dif$mismatch <= threshold),]
  return(dif)
}

soustraction.i(data_D[,c(1, 3:7)],data_R[,3:7],1,3)

#  IDd A B C D E mismatch
#1   1 0 0 0 0 0        0
#2   2 0 0 0 0 0        0
#3   3 0 0 0 0 0        0
#4   4 0 0 0 0 0        0
#5   5 0 0 0 0 0        0
#6   6 0 0 0 0 0        0
#7   7 1 1 0 0 1        3
#8   8 1 1 0 0 0        2

soustraction.i(data_D[,c(1, 3:7)],data_R[,3:7],1,2)
#  IDd A B C D E mismatch
#1   1 0 0 0 0 0        0
#2   2 0 0 0 0 0        0
#3   3 0 0 0 0 0        0
#4   4 0 0 0 0 0        0
#5   5 0 0 0 0 0        0
#6   6 0 0 0 0 0        0
#8   8 1 1 0 0 0        2

请注意,我假设 Id 列是 data_D 中的第一列。