【发布时间】:2021-04-16 23:48:03
【问题描述】:
我有一个函数可以计算 2 个数据集中的行之间的差异(基于相同的列)。这是一个示例和函数
#################
## Sample ##
#################
# 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
我想要做的是当我将阈值设置为0 并且我的mismatch 大于0 时,我不想让这些患者失去,而是我想保留他们并分配一个@987654325 @值,例如,如果我将阈值设置为0,我会得到
soustraction.i(data_D[,3:7],data_R[,3:7],1,0)
# A tibble: 6 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
我失去了 2 名患者,我想分配一个 NA 值。所以输出将是
# Desired output
# 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 NA
8 1 1 0 0 0 NA
这是我迄今为止尝试过的,它给了我一个警告,但没有做正确的事情
soustraction.j=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$mismatch=rowSums(dif)
if(threshold==0){
if(dif$mismatch > 0){
dif$mismatch= NA
}
}else{
dif=dif[which(dif$mismatch <= threshold),]
}
return(dif)
}
soustraction.j(data_D[,3:7],data_R[,3:7],1,0)
# 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
#Warning message:
#In if (dif$mismatch > 0) { :
# the condition has length > 1 and only the first element will be used
提前感谢您的帮助
【问题讨论】:
标签: r if-statement na