Split character column into several binary (0/1) columns

Another option is tstrsplit() from data.table:

library(data.table)
vapply(tstrsplit(a, ",", fixed = TRUE, fill = 0), ">", integer(length(a)), 0L)
#      [,1] [,2] [,3] [,4]
# [1,]    1    1    1    0
# [2,]    1    1    0    0
# [3,]    1    1    1    1

Another convoluted base-R solution:

x  <- strsplit(a,",")
xl <- unique(unlist(x))

t(sapply(x,function(z)table(factor(z,levels=xl))))

which gives

     a b c d
[1,] 1 1 1 0
[2,] 1 1 0 0
[3,] 1 1 1 1

A base R - but longer solution:

el = unique(unlist(strsplit(a, ',')))
do.call(rbind, lapply(a, function(u) setNames(el %in% strsplit(u,',')[[1]]+0L, el))
#     a b c d
#[1,] 1 1 1 0
#[2,] 1 1 0 0
#[3,] 1 1 1 1

You can try cSplit_e from my "splitstackshape" package:

library(splitstackshape)
a <- c("a,b,c", "a,b", "a,b,c,d")
cSplit_e(as.data.table(a), "a", ",", type = "character", fill = 0)
#          a a_a a_b a_c a_d
# 1:   a,b,c   1   1   1   0
# 2:     a,b   1   1   0   0
# 3: a,b,c,d   1   1   1   1
cSplit_e(as.data.table(a), "a", ",", type = "character", fill = 0, drop = TRUE)
#    a_a a_b a_c a_d
# 1:   1   1   1   0
# 2:   1   1   0   0
# 3:   1   1   1   1

There's also mtabulate from "qdapTools":

library(qdapTools)
mtabulate(strsplit(a, ","))
#   a b c d
# 1 1 1 1 0
# 2 1 1 0 0
# 3 1 1 1 1

A very direct base R approach is to use table along with stack and strsplit:

table(rev(stack(setNames(strsplit(a, ",", TRUE), seq_along(a)))))
#    values
# ind a b c d
#   1 1 1 1 0
#   2 1 1 0 0
#   3 1 1 1 1

Tags:

R