Transform each column factors in a column containing just `0` or `1`

Question

I'm trying to transform each of my column factors in a column containing just 0 or 1. Probably there is a function for that, or someone else already asked, but I couldn't found it. Here is a simple example to try to show what I need:

test = data.frame(my_groups = c("A", "A", "A", "B", "B", "C", "C", "C", "C"),
                  measure1 = c(1:9))

#as result:
#     group_A   group_B  group_C   measure1
# 1         1        0         0          1
# 1         1        0         0          2
# 1         1        0         0          3
# 1         0        1         0          4
# 1         0        1         0          5
# 1         0        0         1          6
# 1         0        0         1          7
# 1         0        0         1          8
# 1         0        0         1          9

Any hint on how can I do that?

Answer 1

We may use dummy_cols from fastDummies

library(fastDummies)
library(dplyr)
test %>% 
    rename(group = 'my_groups') %>%
    dummy_cols('group', remove_selected_columns = TRUE) %>%    
    select(starts_with('group'), measure1)

-output

 group_A group_B group_C measure1
1       1       0       0        1
2       1       0       0        2
3       1       0       0        3
4       0       1       0        4
5       0       1       0        5
6       0       0       1        6
7       0       0       1        7
8       0       0       1        8
9       0       0       1        9

Answer 2

Fortunately, there's a one-function Base R solution.

This type of problem happens a lot, and model.matrix() is built exactly for this.

# the "+ 0" is to avoid adding a column for the intercept.

model.matrix(~ my_groups + measure1 + 0, data=test)

Output:

  my_groupsA my_groupsB my_groupsC measure1
1          1          0          0        1
2          1          0          0        2
3          1          0          0        3
4          0          1          0        4
5          0          1          0        5
6          0          0          1        6
7          0          0          1        7
8          0          0          1        8
9          0          0          1        9

Answer 3

Here's a base R solution, constructing the matrix using expand.grid, then adding the required names.

res <- data.frame( t( unique( matrix( as.numeric( do.call("==", expand.grid(
   test$my_groups, test$my_groups) ) ), dim(test)[1] ) ) ), test$measure1 )

colnames(res) <- c( paste0( "group_", unique(test$my_groups) ), colnames(test)[2] )

res
  group_A group_B group_C measure1
1       1       0       0        1
2       1       0       0        2
3       1       0       0        3
4       0       1       0        4
5       0       1       0        5
6       0       0       1        6
7       0       0       1        7
8       0       0       1        8
9       0       0       1        9

Answer 4

We can try this using dplyr or purrr.

library(tidyverse)

test = data.frame(my_groups = c("A", "A", "A", "B", "B", "C", "C", "C", "C"),
                  measure1 = c(1:9))

dummyfy <- 
as_mapper(~{
  len_row <- vector('numeric', nrow(test))
  len_row[.] <- c(1)
  len_row}
)

data <- pivot_wider(test, names_from =  my_groups, values_from = measure1)
#> Warning: Values are not uniquely identified; output will contain list-cols.
#> * Use `values_fn = list` to suppress this warning.
#> * Use `values_fn = length` to identify where the duplicates arise
#> * Use `values_fn = {summary_fun}` to summarise duplicates

map(data, ~reduce(., c)) %>%
  map_dfr(dummyfy) %>% 
  bind_cols(test[-1])
#> # A tibble: 9 × 4
#>       A     B     C measure1
#>   <dbl> <dbl> <dbl>    <int>
#> 1     1     0     0        1
#> 2     1     0     0        2
#> 3     1     0     0        3
#> 4     0     1     0        4
#> 5     0     1     0        5
#> 6     0     0     1        6
#> 7     0     0     1        7
#> 8     0     0     1        8
#> 9     0     0     1        9

#equivalent using across:

data %>% summarise(across(everything(), ~reduce(., c) %>% dummyfy)) %>% bind_cols(test[-1])
#> # A tibble: 9 × 4
#>       A     B     C measure1
#>   <dbl> <dbl> <dbl>    <int>
#> 1     1     0     0        1
#> 2     1     0     0        2
#> 3     1     0     0        3
#> 4     0     1     0        4
#> 5     0     1     0        5
#> 6     0     0     1        6
#> 7     0     0     1        7
#> 8     0     0     1        8
#> 9     0     0     1        9

^{Created on 2021-12-03 by the reprex package (v2.0.1)}