Benchmarking the difference between the old implementation of `decimal_date()` (making more use of `difftime`) and the new implementation

decimal_date_bench::mark

# decimal_date_strptime is:
register_binding("decimal_date_strptime", function(date) {
     # browser()
     y <- build_expr("year", date)
     # timezone <- call_binding("tz", date)
     start <- call_binding("make_datetime", year = y, tz = "UTC")
     end <- call_binding("make_datetime", year = y + 1L, tz = "UTC")
     # maybe use yday here
     sofar <- call_binding("difftime", date, start, units = "secs")
     total <- call_binding("difftime", end, start, units = "secs")
     y + sofar$cast(int64()) / total$cast(int64())
   })

# and decimal_date is: 
register_binding("decimal_date", function(date) {
    y <- build_expr("year", date)
    start <- call_binding("make_datetime", year = y, tz = "UTC")
    sofar <- call_binding("difftime", date, start, units = "secs")
    total <- call_binding(
      "if_else",
      build_expr("is_leap_year", date),
      Expression$scalar(31622400L), # number of seconds in a leap year (366 days)
      Expression$scalar(31536000L)  # number of seconds in a regular year (365 days)
      )
    y + sofar$cast(int64()) / total
  })


test_df <- tibble(
  a = c(2007.38998954347, 1970.77732069883, 2020.96061799722,
        2009.43465948477, 1975.71251467871, NA),
  b = as.POSIXct(
    c("2007-05-23 08:18:30", "1970-10-11 17:19:45", "2020-12-17 14:04:06",
      "2009-06-08 15:37:01", "1975-09-18 01:37:42", NA)
  ),
  c = as.Date(
    c("2007-05-23", "1970-10-11", "2020-12-17", "2009-06-08", "1975-09-18", NA)
  )
)

test1 <- bench::mark(
  new_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_POSIXct = decimal_date(b)
    ) %>%
    collect(),
  old_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_POSIXct = decimal_date_strptime(b)
    ) %>%
    collect(),
  min_iterations = 100
)
ggplot2::autoplot(test1)

test2 <- bench::mark(
  new_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_r_POSIXct_obj = decimal_date(as.POSIXct("2022-03-25 15:37:01"))
    ) %>%
    collect(),
  old_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_r_POSIXct_obj = decimal_date_strptime(as.POSIXct("2022-03-25 15:37:01"))
    ) %>%
    collect(),
  min_iterations = 100
)
ggplot2::autoplot(test2)

test3 <- bench::mark(
  new_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_r_date_obj = decimal_date(ymd("2022-03-25"))
    ) %>%
    collect(),
  old_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_r_date_obj = decimal_date_strptime(ymd("2022-03-25")),
    ) %>%
    collect(),
  min_iterations = 100
)
ggplot2::autoplot(test3)


test4 <- bench::mark(
  new_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_date = decimal_date(c)
    ) %>%
    collect(),
  old_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_date = decimal_date_strptime(c),
    ) %>%
    collect(),
  min_iterations = 100
)
ggplot2::autoplot(test4)

test5 <- bench::mark(
  new_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_POSIXct = decimal_date(b),
      decimal_date_from_r_POSIXct_obj = decimal_date(as.POSIXct("2022-03-25 15:37:01")),
      decimal_date_from_r_date_obj = decimal_date(ymd("2022-03-25")),
      decimal_date_from_date = decimal_date(c),
      date_from_decimal = date_decimal(a),
      date_from_decimal_r_obj = date_decimal(2022.178)
    ) %>%
    collect(),
  old_implementation = test_df %>%
    arrow_table() %>% 
    mutate(
      decimal_date_from_POSIXct = decimal_date_strptime(b),
      decimal_date_from_r_POSIXct_obj = decimal_date_strptime(as.POSIXct("2022-03-25 15:37:01")),
      decimal_date_from_r_date_obj = decimal_date_strptime(ymd("2022-03-25")),
      decimal_date_from_date = decimal_date_strptime(c),
      date_from_decimal = date_decimal(a),
      date_from_decimal_r_obj = date_decimal(2022.178)
    ) %>%
    collect(),
  min_iterations = 100
)
ggplot2::autoplot(test5) +
  hrbrthemes::theme_ipsum_rc() +
  hrbrthemes::scale_color_ipsum()

ggplot2::autoplot(test1) +
  hrbrthemes::theme_ipsum_rc() +
  hrbrthemes::scale_color_ipsum() +
  ggplot2::ggtitle("Test1 = decimal_date from POSIXct column")
ggplot2::autoplot(test2)
ggplot2::autoplot(test3)
ggplot2::autoplot(test4)
ggplot2::autoplot(test5)