I have the following input
#mydata
ID  variable1  variable2
1    a,b,c,d      c,a 
2    g,f,h        h
3    p,l,m,n,c    c,l
I wish to subtract the strings of varible2 from variable1 and I'd like to have the following output?
#Output
ID  Output 
1    b,d      
2    g,f        
3    p,m,n    
#dput
structure(list(ID = 1:3, variable1 = structure(1:3, .Label = c("a,b,c,d", 
"g,f,h", "p,l,m,n,c"), class = "factor"), variable2 = structure(c(1L, 
 3L, 2L), .Label = c("c,a", "c,l", "h"), class = "factor")), .Names =    c("ID", 
 "variable1", "variable2"), class = "data.frame", row.names = c(NA, 
-3L))
                You can try,
Map(setdiff, strsplit(as.character(df$variable1), ',')), strsplit(as.character(df$variable2), ','))
                        We can use Map after splitting each of the columns by , get the setdiff, paste them together, set the names of the list output with 'ID' column, stack it to 'data.frame' and set the names to 'ID' and 'Output' for the columns.
setNames(stack(setNames(Map(function(x,y) toString(setdiff(x,y)), 
         strsplit(as.character(df1$variable1), ","), 
         strsplit(as.character(df1$variable2), ",")),
              df1$ID))[2:1], c("ID", "Output"))
 #  ID  Output
 #1  1    b, d
 #2  2    g, f
 #3  3 p, m, n
Or a compact option would be
library(splitstackshape)
cSplit(df1, 2:3, ",", "long")[, .(Output = toString(setdiff(variable1, variable2))) , ID]
#   ID  Output
#1:  1    b, d
#2:  2    g, f
#3:  3 p, m, n
                        If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With