Get the position number of the first instance of a thing in one column, and use that number to pick something from another column

find_index.R

library(data.table)
library(dplyr)
library(purrr)

# lots of dates
date = seq.Date(from = as.Date("1900-01-01"),
                to = as.Date("2900-12-31"),
                by = "day")

# lots of cases
cases = c(1:length(date)-1)

# make a dataframe
df <- data.frame(date = date, cases = cases)

# Get the position of the first instance of 10,000 in the cases col,
# and use that number to index the date col, returning the first date
# on which 10,000 cases occurred.
dt <- as.data.table(df) # convert to data.table first
dt[, date[which.max(cases >= 10000)]]
# this only works because 10000 is a vlaue that can be found in that column.

# HOWEVER

# which.max returns 1 when it fails, thus indexing
# our first date, which we do not want because there
# are no days with 400,000 or more cases. We expect NA.
dt[, date[which.max(cases >= 400000)]]

# Let's test many methods. Plus, we want to speed test them at the
# end, so I'm putting each method inside a function because it's easier
# to add them as functions in the speed test.

dt_which_max_method <- function() {
  dt <- as.data.table(df)
  dt[, date[which.max(cases >= 400000)]]
} 

# match(true, x) will return NA when it fails, which
# is what we want so that we don't get a date returned
# when there are no days with 400,000 or more cases
dt_match_true_method <- function() {
  dt <- as.data.table(df)
  dt[, date[match(TRUE, cases >= 100000)]]
} 

# test them all and return the first one, also returns NA
dt_which_first_method <- function() {
  dt <- as.data.table(df)
  dt[, date[which(cases >= 400000)[1L]]]  
}

# use base R's Position function, also returns NA
dt_position_method <- function() {
  dt <- as.data.table(df)
  dt[, date[Position(function(x) x >= 400000, cases)]]
}

#---- And now with a tibble and the purrr detect_index function

# returns 'Date of length 0'
tidyverse_method <- function() {
  tb <- tibble::as_tibble(df)
  tb %>%
    slice(purrr::detect_index(cases, ~.x >= 400000)) %>% 
    pull(date)
}

# tidyverse mixed with the base match function
tidyverse_base_method <- function() {
  tb <- tibble::as_tibble(df)
  tb %>%
    slice(match(TRUE, cases >= 100000)) %>% 
    pull(date)
}

#--- Speed test them each 500 times

microbenchmark::microbenchmark(
  dt_which_max_method(),
  dt_match_true_method(),
  dt_which_first_method(),
  dt_position_method(),
  tidyverse_method(),
  tidyverse_base_method(),
  times = 500L
)

Important clarification from Hadley on the use of purrr::detect_index()