Janet
Reputation: 225
merging the outputs of functions within nested function in R
I have 2 functions that each gives a different output, i was trying to create a new function that merge the 2 outputs of theses functions, but keep getting an error saying the object is not found, i understand that once i am out of any of my functions (inside of the general function), the main function does not recognize these objects. I do not know how to make these outputs recognizable in the global environment for the main function. Here is the code
#############################################################################
#############################################################################
# 1. datasets
IDr= c(seq(1,5))
BTR=c("A","B","AB","O","O")
data_R=data.frame(IDr,BTR,A=c(0,1,rep(0,3)),B=c(0,rep(0,3),1),C=c(0,rep(1,3),0),D=c(0,rep(1,4)),E=c(1,1,0,rep(1,1),0),stringsAsFactors=FALSE)
data_R
IDr BTR A B C D E
1 1 A 0 0 0 0 1
2 2 B 1 0 1 1 1
3 3 AB 0 0 1 1 0
4 4 O 0 0 1 1 1
5 5 O 0 1 0 1 0
IDd= c(seq(1,8))
BTD= c("A","B","AB","O","AB","AB","O","O")
fg= c(rep(0.0025, each=2),rep(0.00125, each=2),rep(0.0011, each=2),rep(0.0015, each=2))
data_D=data.frame(IDd,BTD,A=c(rep(0,5),1,1,1),B=c(rep(0,6),1,1),C=c(rep(1,7),0),D=rep(1,8),E=c(rep(0,5),rep(1,2),0),fg,stringsAsFactors=FALSE)
data_D
IDd BTD A B C D E fg
1 1 A 0 0 1 1 0 0.00250
2 2 B 0 0 1 1 0 0.00250
3 3 AB 0 0 1 1 0 0.00125
4 4 O 0 0 1 1 0 0.00125
5 5 AB 0 0 1 1 0 0.00110
6 6 AB 1 0 1 1 1 0.00110
7 7 O 1 1 1 1 1 0.00150
8 8 O 1 1 0 1 0 0.00150
############################################################################
############################################################################
# fist function
# calulate the frequency of repeated set (A:E) using fg
freq<- function(df, Vars,col.interest){
col.interest=as.data.frame(col.interest)
resultat1= df %>%
group_by(across(all_of(Vars))) %>%
dplyr::summarise(count = n(), frequency.epi = sum(fg), .groups = 'drop')
res=merge(resultat1,col.interest,all=TRUE)
res_final=cbind(df[1:2],res)
return(res_final)
}
dfreq= freq(data_D,colnames(data_D)[3:7],data_D[3:7])
dfreq
IDd BTD A B C D E count frequency.epi
1 1 A 0 0 1 1 0 5 0.0086
2 2 B 0 0 1 1 0 5 0.0086
3 3 AB 0 0 1 1 0 5 0.0086
4 4 O 0 0 1 1 0 5 0.0086
5 5 AB 0 0 1 1 0 5 0.0086
6 6 AB 1 0 1 1 1 1 0.0011
7 7 O 1 1 0 1 0 1 0.0015
8 8 O 1 1 1 1 1 1 0.0015
###############################################################
# the second function that was corrected by @MrFlic
mis.test = function(D, R, threshold) {
D = as.data.frame(D)
R = as.data.frame(R)
mismatch.i = function(i) {
dif = purrr::map2_df(D[-1], R[i,-1], `-`)
dif[dif<0] = 0
dif$mismatch=rowSums(dif)
dif = cbind(ID = D[1],IDr=R[i,1], dif)
dif = dif[which(dif$mismatch <= threshold),]
return(list=dif[c(1,2,ncol(dif))])
}
diff.mat = do.call(rbind, lapply(1:nrow(R), function(x) mismatch.i(x)))
diff.mat = as.data.frame(diff.mat)
return(diff.mat)
}
# if i want mis.test for 1 person
mis_one=mis.test(data_D[,c(1,3:7)],data_R[1,c(1,3:7)],2)
mis_one
IDd IDr mismatch
1 1 1 2
2 2 1 2
3 3 1 2
4 4 1 2
5 5 1 2
# what i want to do in the main function is this step (for example using these exact outputs)
merge(mis_one,dfreq,by="IDd") # this was executed outside to show the expected output
# this is the output expected that i want if i run the main function
IDd IDr mismatch BTD A B C D E count frequency.epi
1 1 1 2 A 0 0 1 1 0 5 0.0086
2 2 1 2 B 0 0 1 1 0 5 0.0086
3 3 1 2 AB 0 0 1 1 0 5 0.0086
4 4 1 2 O 0 0 1 1 0 5 0.0086
5 5 1 2 AB 0 0 1 1 0 5 0.0086
Here is the main function, with many errors
test.merge=function(D,DF,R,threshold,Vars,col.interest){
R=as.data.frame(R)
D=as.data.frame(D)
DF=as.data.frame(DF)
col.interest=as.data.frame(col.interest)
# remark1: Here i know i repeated the same arguments because i did not know what to set in order to do the calculation
freq.epi<- function( Vars,col.interest){
resultat1= DF %>%
group_by(across(all_of(Vars))) %>%
dplyr::summarise(count = n(), frequency.epi = sum(fg), .groups = 'drop')
res=merge(resultat1,col.interest,all=TRUE)
res_final=cbind(DF[1:2],res)
return(res_final)
}
# same as remark1 for the arguments
mis.test = function(D, R, threshold) {
D = as.data.frame(D)
R = as.data.frame(R)
mismatch.i = function(i) {
dif = purrr::map2_df(D[-1], R[i,-1], `-`)
dif[dif<0] = 0
dif$mismatch=rowSums(dif)
dif = cbind(ID = D[1],IDr=R[i,1], dif)
dif = dif[which(dif$mismatch <= threshold),]
return(list=dif[c(1,2,ncol(dif))])
}
diff.mat = do.call(rbind, lapply(1:nrow(R), function(x) mismatch.i(x)))
diff.mat = as.data.frame(diff.mat)
return(diff.mat)
}
# i dont know how to make diff.mat and res_final visible for test.merge
# i am trying to merge the two outputs res_final and diff.mat by the IDd
tab=merge(diff.mat,res_final,by="IDd")
return(tab)
}
test.merge(data_D[,c(1,3:7)],data_D,data_R[1,c(1,3:7)],2,colnames(data_D)[3:7],data_D[3:7])
# Error in merge(diff.mat, res_final, by = "IDd") :
# object 'diff.mat' not found
I dont know if there is other ways to use the outputs of functions within the main function. Thank you in advance for your help
Upvotes: 1
Views: 344
Answers (1)
Ronak Shah
Reputation: 389055
Why do you want to mix all the functions into one? I would suggest to keep them separate and write test.merge to only merge data from 2 outputs.
freq<- function(df, Vars,col.interest){
col.interest=as.data.frame(col.interest)
resultat1= df %>%
group_by(across(all_of(Vars))) %>%
dplyr::summarise(count = n(), frequency.epi = sum(fg), .groups = 'drop')
res=merge(resultat1,col.interest,all=TRUE)
res_final=cbind(df[1:2],res)
return(res_final)
}
mis.test = function(D, R, threshold) {
D = as.data.frame(D)
R = as.data.frame(R)
mismatch.i = function(i) {
dif = purrr::map2_df(D[-1], R[i,-1], `-`)
dif[dif<0] = 0
dif$mismatch=rowSums(dif)
dif = cbind(ID = D[1],IDr=R[i,1], dif)
dif = dif[which(dif$mismatch <= threshold),]
return(list=dif[c(1,2,ncol(dif))])
}
diff.mat = do.call(rbind, lapply(1:nrow(R), function(x) mismatch.i(x)))
diff.mat = as.data.frame(diff.mat)
return(diff.mat)
}
test.merge = function(x, y) {
merge(x,y,by="IDd")
}
test.merge(mis.test(data_D[,c(1,3:7)],data_R[1,c(1,3:7)],2),
freq(data_D,colnames(data_D)[3:7],data_D[3:7]))
# IDd IDr mismatch BTD A B C D E count frequency.epi
#1 1 1 2 A 0 0 1 1 0 5 0.0086
#2 2 1 2 B 0 0 1 1 0 5 0.0086
#3 3 1 2 AB 0 0 1 1 0 5 0.0086
#4 4 1 2 O 0 0 1 1 0 5 0.0086
#5 5 1 2 AB 0 0 1 1 0 5 0.0086
And here is the fix to your original code.
test.merge=function(D,R,threshold,DF, Vars,col.interest){
R=as.data.frame(R)
D=as.data.frame(D)
DF=as.data.frame(DF)
col.interest=as.data.frame(col.interest)
freq.epi<- function(DF, Vars,col.interest){
resultat1= DF %>%
group_by(across(all_of(Vars))) %>%
dplyr::summarise(count = n(), frequency.epi = sum(fg), .groups = 'drop')
res=merge(resultat1,col.interest,all=TRUE)
res_final=cbind(DF[1:2],res)
return(res_final)
}
# same as remark1 for the arguments
mis.test = function(D, R, threshold) {
D = as.data.frame(D)
R = as.data.frame(R)
mismatch.i = function(i) {
dif = purrr::map2_df(D[-1], R[i,-1], `-`)
dif[dif<0] = 0
dif$mismatch=rowSums(dif)
dif = cbind(ID = D[1],IDr=R[i,1], dif)
dif = dif[which(dif$mismatch <= threshold),]
return(list=dif[c(1,2,ncol(dif))])
}
diff.mat = do.call(rbind, lapply(1:nrow(R), function(x) mismatch.i(x)))
diff.mat = as.data.frame(diff.mat)
return(diff.mat)
}
tab=merge(mis.test(D, R, threshold),freq.epi(DF, Vars, col.interest),by="IDd")
return(tab)
}
test.merge(data_D[,c(1,3:7)],data_R[1,c(1,3:7)],2,data_D, colnames(data_D)[3:7],data_D[3:7])
I am sure this could be optimised and written in a better way (as suggested in 1st part) but since I don't know the bigger picture here I'll leave this to OP.
Upvotes: 2
Related Questions
- combining 2 functions into one in R
- R nested functions
- Combine dataframes as function output in a single dataframe in R
- Combining 3 functions into one function
- Combining functions in R
- Return arguments of nested function in R
- Nested function in R
- in R: nest two lists of functions and return combined functions in a list
- Merge Function in R
- How to repeat performing a function in R multiple times