Added format specifier for yearqtr

NEWS.md

@@ -50,6 +50,8 @@
 
 9. `fread()` no longer replaces a literal header column name `"NA"` with an auto-generated `Vn` name when `na.strings` includes `"NA"`, [#5124](https://github.com/Rdatatable/data.table/issues/5124). Data rows still continue to parse `"NA"` as missing. Thanks @Mashin6 for the report and @shrektan for the fix.
 
+10. `yearqtr()` and `yearmon()` gain an optional `format` argument [#7694](https://github.com/Rdatatable/data.table/issues/7694). 'numeric' is the default and preserves the original behavior, while 'character' formats the date as YYYYQ# (e.g., 2025Q2) for `yearqtr()` and YYYYM# (e.g., 2025M4) for `yearmon()`. Thanks to @jan-swissre for the report and @LunaticSage218 for the implementation.
+
 ### Notes
 
 1. {data.table} now depends on R 3.5.0 (2018).

R/IDateTime.R

@@ -365,8 +365,30 @@ isoyear = function(x) as.integer(format(as.IDate(x), "%G"))
 month   = function(x) convertDate(as.IDate(x), "month")
 quarter = function(x) convertDate(as.IDate(x), "quarter")
 year    = function(x) convertDate(as.IDate(x), "year")
-yearmon = function(x) convertDate(as.IDate(x), "yearmon")
-yearqtr = function(x) convertDate(as.IDate(x), "yearqtr")
+yearmon = function(x, format=c("numeric", "character")) {
+  format = match.arg(format)
+  x_as_idate = as.IDate(x)
+  ymon = convertDate(x_as_idate, "yearmon")
+  if (format == "numeric") return(ymon)
+  ans = rep(NA_character_, length(x_as_idate))
+  ok = !is.na(x_as_idate)
+  yr = floor(ymon[ok])
+  mon = round((ymon[ok] - yr) * 12) + 1L
+  ans[ok] = paste0(yr, "M", mon)
+  ans
+}
+yearqtr = function(x, format=c("numeric", "character")) {
+  format = match.arg(format)
+  x_as_idate = as.IDate(x)
+  yqtr = convertDate(x_as_idate, "yearqtr")
+  if (format == "numeric") return(yqtr)
+  ans = rep(NA_character_, length(x_as_idate))
+  ok = !is.na(x_as_idate)
+  yr = floor(yqtr[ok])
+  qtr = round((yqtr[ok] - yr) * 4) + 1L
+  ans[ok] = paste0(yr, "Q", qtr)
+  ans
+}
 
 convertDate = function(x, type) {
   type = match.arg(type, c("yday", "wday", "mday", "week", "month", "quarter", "year", "yearmon", "yearqtr"))

inst/tests/tests.Rraw

@@ -21585,3 +21585,18 @@ close(con)
 file.create(f <- tempfile())
 test(2367.6, fread(file(f)), data.table(), warning="Connection has size 0.")
 unlink(f)
+
+# yearqtr() could optionally output 2025Q4 format #7694
+x = c("1111-11-11", "2019-01-01", "2019-02-28", "2019-03-01", "2019-12-31", "2020-02-29", "2020-03-01", "2020-12-31", "2040-01-01", "2040-12-31", "2100-03-01", NA)
+test(2368.1, yearqtr(x, format="numeric"), c(1111.75, 2019, 2019, 2019, 2019.75, 2020, 2020, 2020.75, 2040, 2040.75, 2100, NA))
+test(2368.2, yearqtr(x, format="numeric"), yearqtr(x))  # numeric is the default, preserves backwards compatibility
+test(2368.3, yearqtr(x, format="character"), c("1111Q4", "2019Q1", "2019Q1", "2019Q1", "2019Q4", "2020Q1", "2020Q1", "2020Q4", "2040Q1", "2040Q4", "2100Q1", NA_character_))
+test(2368.4, yearqtr("2016-08-03 01:02:03.45", format="character"), "2016Q3")
+test(2368.5, yearqtr(NA, format="character"), NA_character_)
+
+# yearmon() could optionally output 2025M4 format #7694
+test(2369.1, yearmon(x, format="numeric"), c(1111+10/12, 2019, 2019+1/12, 2019+2/12, 2019+11/12, 2020+1/12, 2020+2/12, 2020+11/12, 2040, 2040+11/12, 2100+2/12, NA))
+test(2369.2, yearmon(x, format="numeric"), yearmon(x))  # numeric is the default, preserves backwards compatibility
+test(2369.3, yearmon(x, format="character"), c("1111M11", "2019M1", "2019M2", "2019M3", "2019M12", "2020M2", "2020M3", "2020M12", "2040M1", "2040M12", "2100M3", NA_character_))
+test(2369.4, yearmon("2016-08-03 01:02:03.45", format="character"), "2016M8")
+test(2369.5, yearmon(NA, format="character"), NA_character_)

man/IDateTime.Rd

@@ -97,9 +97,8 @@ isoyear(x)
 month(x)
 quarter(x)
 year(x)
-yearmon(x)
-yearqtr(x)
-
+yearmon(x, format = c("numeric", "character"))
+yearqtr(x, format = c("numeric", "character"))
 }
 
 \arguments{
@@ -115,6 +114,7 @@ yearqtr(x)
   the S3 generic.}
   \item{units}{one of the units listed for truncating. May be abbreviated.}
   \item{ms}{ For \code{as.ITime} methods, what should be done with sub-second fractions of input? Valid values are \code{'truncate'} (floor), \code{'nearest'} (round), and \code{'ceil'} (ceiling). See Details. }
+  \item{format}{format is either \code{"numeric"} (default) or \code{"character"}. \code{"character"} formats the result as \code{"2025M4"} for \code{yearmon} and \code{"2025Q4"} for \code{yearqtr}.}
 }
 \details{
 \code{IDate} is a date class derived from \code{Date}. It has the same
@@ -209,7 +209,11 @@ Similarly, \code{isoyear()} returns the ISO 8601 year corresponding to the ISO w
    for second, minute, hour, day of year, day of week,
    day of month, week, month, quarter, and year, respectively.
    \code{yearmon} and \code{yearqtr} return double values representing
-   respectively \code{year + (month-1) / 12} and \code{year + (quarter-1) / 4}.
+   respectively \code{year + (month-1) / 12} and \code{year + (quarter-1) / 4}
+   when \code{format = "numeric"} (the default). When \code{format = "character"},
+   they return character vectors of the form \code{"YYYYMM"} (e.g. \code{"2025M4"})
+   and \code{"YYYYQN"} (e.g. \code{"2025Q4"}) respectively, with \code{NA} input
+   returned as \code{NA_character_}.
 
    \code{second}, \code{minute}, \code{hour} are taken directly from
    the \code{POSIXlt} representation.