lundi 11 janvier 2021

Assign an NA value to a numeric variable using IF statement in R

I have a function that calculates the difference between rows (based on the same columns) in 2 datasets. Here is a sample and function

#################
##   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

What i want to do is when i set my threshold to 0 and my mismatch is greater than 0, i do not want to loose theses patients, instead i want to keep them and assign an NA value, for example if i set the threshold at 0 i would get

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

I am loosing 2 patients which i would want to assign an NA value. So the output would be

# 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

Here is what i tried so far and it gives me a warning and not doing the right thing

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

Thank you in advance for your help

Aucun commentaire:

Enregistrer un commentaire