Selecting the first positive event

Question

I'm struggling on how can I create a subsample of a dataframe using just the first positive test basing on the date. I'll show a toy example. Suppose I have the folowing;

df = data.frame(guy = c("A", "B", "A", 'B', "C", "C"),
  test1 = c(1, 1, 0, 0, 1, 0),
                test2 = c(0, 1, 0, 1, 0, 0),
                test3 = c(0, 0, 1, 0, 0, 1),
                date = as.Date(c('1999-10-20', '1999-10-21', '1999-10-22', '1999-10-23', '1999-10-24', '1999-10-25')));df
   #guy test1 test2 test3       date
#1   A     1     0     0 1999-10-20
#2   B     1     1     0 1999-10-21
#3   A     0     0     1 1999-10-22
#4   B     0     1     0 1999-10-23
#5   C     1     0     0 1999-10-24
#6   C     0     0     1 1999-10-25

Now, I want to filter, selecting just the first positive test, (i.e test1|test2|test3 = 1) based on the oldest date. In my example I'd get the following:

   #guy test1 test2 test3       date
#1   A     1     0     0 1999-10-20
#2   B     1     1     0 1999-10-21
#3   C     1     0     0 1999-10-24

Data frame:

df = data.frame(guy = c("A", "B", "A", 'B', "C", "C"),
  test1 = c(1, 1, 0, 0, 1, 0),
                test2 = c(0, 1, 0, 1, 0, 0),
                test3 = c(0, 0, 1, 0, 0, 1),
                date = as.Date(c('1999-10-20', '1999-10-21', '1999-10-22', '1999-10-23', '1999-10-24', '1999-10-25')));df

Any hint on how can I do that?

Answer 1

And using dplyr::top_n another option would be:

df = data.frame(guy = c("A", "B", "A", 'B', "C", "C"),
                test1 = c(1, 1, 0, 0, 1, 0),
                test2 = c(0, 1, 0, 1, 0, 0),
                test3 = c(0, 0, 1, 0, 0, 1),
                date = as.Date(c('1999-10-20', '1999-10-21', '1999-10-22', '1999-10-23', '1999-10-24', '1999-10-25')))

library(dplyr)

df %>% 
  filter(test1 | test2 | test3) %>% 
  group_by(guy) %>% 
  top_n(-1, date)
#> # A tibble: 3 x 5
#> # Groups:   guy [3]
#>   guy   test1 test2 test3 date      
#>   <chr> <dbl> <dbl> <dbl> <date>    
#> 1 A         1     0     0 1999-10-20
#> 2 B         1     1     0 1999-10-21
#> 3 C         1     0     0 1999-10-24

Answer 2

A base R option using subset + ave + max.col

subset(
  df,
  as.logical(
    ave(
      max.col(df[grepl("test\\d+", names(df))], "first"),
      guy,
      FUN = function(x) x == min(x)
    )
  ) & (test1|test2|test3)
)

which gives

  guy test1 test2 test3       date
1   A     1     0     0 1999-10-20
2   B     1     1     0 1999-10-21
5   C     1     0     0 1999-10-24