How to find first element of a group that fulfill a condition

Question

structure(list(group = c(17L, 17L, 17L, 18L, 18L, 18L, 18L, 19L, 
19L, 19L, 20L, 20L, 20L, 21L, 21L, 22L, 23L, 24L, 25L, 25L, 25L, 
26L, 27L, 27L, 27L, 28L), var = c         


        

Answer 1

library(dplyr)

df$first = NULL

df %>%
  group_by(group) %>%
  mutate(first = as.numeric(row_number() == min(row_number()[var == 1]))) %>%
  ungroup()

# # A tibble: 26 x 3
#   group   var first
#     
# 1    17    74     0
# 2    17    49     0
# 3    17     1     1
# 4    18    74     0
# 5    18     1     1
# 6    18    49     0
# 7    18    61     0
# 8    19    49     0
# 9    19     1     1
# 10   19     5     0
# # ... with 16 more rows

The idea is to flag the minimum row number where var = 1, within each group.

This will return some warnings, because in some groups there are no var = 1 cases.

Another option would be this:

library(dplyr)

df$first = NULL

# create row id
df$id = seq_along(df$group)

df %>%
  filter(var == 1) %>%                         # keep cases where var = 1
  distinct(group, .keep_all = T) %>%           # keep distinct cases based on group
  mutate(first = 1) %>%                        # create first column
  right_join(df, by=c("id","group","var")) %>% # join back original dataset
  mutate(first = coalesce(first, 0)) %>%       # replace NAs with 0
  select(-id)                                  # remove row id

# # A tibble: 26 x 3
#   group   var first
#     
# 1    17    74     0
# 2    17    49     0
# 3    17     1     1
# 4    18    74     0
# 5    18     1     1
# 6    18    49     0
# 7    18    61     0
# 8    19    49     0
# 9    19     1     1
#10    19     5     0
# # ... with 16 more rows