Merge branch 'master' into DataCodeIntegration

Author: badasahog

.ci/atime/tests.R

@@ -277,5 +277,14 @@ test.list <- atime::atime_test_list(
     Slow = "73d79edf8ff8c55163e90631072192301056e336",   # Parent of the first commit in the PR (https://github.com/Rdatatable/data.table/commit/8397dc3c993b61a07a81c786ca68c22bc589befc)
     Fast = "8397dc3c993b61a07a81c786ca68c22bc589befc"),  # Commit in the PR (https://github.com/Rdatatable/data.table/pull/7019/commits) that removes inefficiency
 
+  "isoweek improved in #7144" = atime::atime_test(
+    setup = {
+      set.seed(349)
+      x = sample(Sys.Date() - 0:5000, N, replace=TRUE)
+    },
+    expr = data.table::isoweek(x),
+    Slow = "548410d23dd74b625e8ea9aeb1a5d2e9dddd2927",   # Parent of the first commit in the PR (https://github.com/Rdatatable/data.table/commit/548410d23dd74b625e8ea9aeb1a5d2e9dddd2927)
+    Fast = "c0b32a60466bed0e63420ec105bc75c34590865e"),  # Commit in the PR (https://github.com/Rdatatable/data.table/pull/7144/commits) that uses a much faster implementation
+
     tests=extra.test.list)
 # nolint end: undesirable_operator_linter.

NEWS.md

@@ -42,6 +42,10 @@
 
 8. `groupingsets()` gets a new argument `enclos` for use together with the `jj` argument in functions wrapping `groupingsets()`, including the existing wrappers `rollup()` and `cube()`, [#5560](https://github.com/Rdatatable/data.table/issues/5560). When forwarding a `j`-expression as `groupingsets(jj = substitute(j))`, make sure to pass `enclos = parent.frame()` as well, so that the `j`-expression will be evaluated in the right context. This makes it possible for `j` to refer to variables outside the `data.table`. Thanks @sindribaldur for the report and @aitap for the fix.
 
+9. `isoweek()` is much faster (e.g. 20x) by re-using an implementation from {base}, [#5111](https://github.com/Rdatatable/data.table/issues/5111). Thanks @MichaelChirico for the report and PR.
+
+10. `data.table()` and `as.data.table()` with `keep.rownames=TRUE` now extract row names from named vectors, matching `data.frame()` behavior. Names from the first named vector in the input are used to create the row names column (default name `"rn"` or custom name via `keep.rownames="column_name"`), [#1916](https://github.com/Rdatatable/data.table/issues/1916). Thanks to @richierocks for the feature request and @Mukulyadav2004 for the implementation.
+
 ### BUG FIXES
 
 1. Custom binary operators from the `lubridate` package now work with objects of class `IDate` as with a `Date` subclass, [#6839](https://github.com/Rdatatable/data.table/issues/6839). Thanks @emallickhossain for the report and @aitap for the fix.

R/IDateTime.R

@@ -342,19 +342,20 @@ yday    = function(x) convertDate(as.IDate(x), "yday")
 wday    = function(x) convertDate(as.IDate(x), "wday")
 mday    = function(x) convertDate(as.IDate(x), "mday")
 week    = function(x) convertDate(as.IDate(x), "week")
-isoweek = function(x) {
+# TODO(#3279): Investigate if improved as.IDate() makes our below implementation faster than this
+isoweek = function(x) as.integer(format(as.IDate(x), "%V"))
   # ISO 8601-conformant week, as described at
   #   https://en.wikipedia.org/wiki/ISO_week_date
   # Approach:
   # * Find nearest Thursday to each element of x
   # * Find the number of weeks having passed between
   #   January 1st of the year of the nearest Thursdays and x
 
-  x = as.IDate(x)   # number of days since 1 Jan 1970 (a Thurs)
-  nearest_thurs = as.IDate(7L * (as.integer(x + 3L) %/% 7L))
-  year_start = as.IDate(format(nearest_thurs, '%Y-01-01'))
-  1L + (nearest_thurs - year_start) %/% 7L
-}
+#  x = as.IDate(x)   # number of days since 1 Jan 1970 (a Thurs)
+#  nearest_thurs = as.IDate(7L * (as.integer(x + 3L) %/% 7L))
+#  year_start = as.IDate(format(nearest_thurs, '%Y-01-01'))
+#  1L + (nearest_thurs - year_start) %/% 7L
+
 
 month   = function(x) convertDate(as.IDate(x), "month")
 quarter = function(x) convertDate(as.IDate(x), "quarter")

R/as.data.table.R

@@ -136,9 +136,26 @@ as.data.table.list = function(x,
   missing.check.names = missing(check.names)
   origListNames = if (missing(.named)) names(x) else NULL  # as.data.table called directly, not from inside data.table() which provides .named, #3854
   empty_atomic = FALSE
+
+  # Handle keep.rownames for vectors (mimicking data.frame behavior)
+  rownames_ = NULL
+  check_rownames = !isFALSE(keep.rownames)
+
   for (i in seq_len(n)) {
     xi = x[[i]]
     if (is.null(xi)) next    # eachncol already initialized to 0 by integer() above
+    if (check_rownames && is.null(rownames_)) {
+      if (is.null(dim(xi))) {
+        if (!is.null(nm <- names(xi))) {
+          rownames_ = nm
+          x[[i]] = unname(xi)
+        }
+      } else {
+        if (!is.null(nm <- rownames(xi))) {
+          rownames_ = nm
+        }
+      }
+    }
     if (!is.null(dim(xi)) && missing.check.names) check.names=TRUE
     if ("POSIXlt" %chin% class(xi)) {
       warningf("POSIXlt column type detected and converted to POSIXct. We do not recommend use of POSIXlt at all because it uses 40 bytes to store one date.")
@@ -203,6 +220,18 @@ as.data.table.list = function(x,
   }
   if (any(vnames==".SD")) stopf("A column may not be called .SD. That has special meaning.")
   if (check.names) vnames = make.names(vnames, unique=TRUE)
+
+  # Add rownames column when vector names were found
+  if (!is.null(rownames_)) {
+    rn_name = if (is.character(keep.rownames)) keep.rownames[1L] else "rn"
+    if (!is.na(idx <- chmatch(rn_name, vnames)[1L])) {
+      ans = c(list(ans[[idx]]), ans[-idx])
+      vnames = c(vnames[idx], vnames[-idx])
+    } else {
+      ans = c(list(recycle(rownames_, nrow)), ans)
+      vnames = c(rn_name, vnames)
+    }
+  }
   setattr(ans, "names", vnames)
   setDT(ans, key=key) # copy ensured above; also, setDT handles naming
   if (length(origListNames)==length(ans)) setattr(ans, "names", origListNames)  # PR 3854 and tests 2058.15-17

inst/tests/tests.Rraw

@@ -21406,3 +21406,23 @@ dt = data.table(x = 123456, y = "wide_string")
 test(2329.2, print(dt, col.names = "none"), output = "1: 123456 wide_string\n")
 dt = data.table(a = NA_integer_, b = NaN)
 test(2329.3, print(dt, col.names = "none"), output = "1: NA NaN\n")
+
+# Row name extraction from multiple vectors, #7136
+x <- 1:3 
+y <- setNames(4:6, c("A", "B", "C"))  
+test(2330.1, as.data.table(list(x, y), keep.rownames=TRUE), data.table(rn=c("A", "B", "C"), V1=1:3, V2=4:6))
+test(2330.2, as.data.table(list(x, y), keep.rownames="custom"), data.table(custom=c("A", "B", "C"), V1=1:3, V2=4:6))
+test(2330.3, as.data.table(list(y, x), keep.rownames=TRUE), data.table(rn=c("A", "B", "C"), V1=4:6, V2=1:3)) 
+
+# Behavior under data.frame()
+test(2330.4, as.data.table(data.frame(x, y), keep.rownames=TRUE), data.table(rn=c("A", "B", "C"), x=1:3, y=4:6))
+test(2330.5, as.data.table(data.frame(y, x), keep.rownames=TRUE), data.table(rn=c("A", "B", "C"), y=4:6, x=1:3))
+
+DF <- data.frame(row.names = letters[1:6], V = 1:6)     # Test data.frame with explicit rownames
+test(2330.6, as.data.table(list(a = 6:1, DF), keep.rownames=TRUE), data.table(rn=letters[1:6], a=6:1, V=1:6))
+
+z <- setNames(1:3, rep("", 3))  # vector with all-empty names     # behaviour with all-empty row names
+test(2330.7, as.data.table(list(z), keep.rownames=TRUE), data.table(rn=rep("", 3), V1=1:3))
+
+M <- matrix(1:6, nrow=3, dimnames=list(rep("", 3), c("V1", "V2")))   #  test of list(M) for empty-rowname'd matrix input
+test(2330.8, as.data.table(list(M), keep.rownames=TRUE), data.table(rn=rep("", 3), V1=1:3, V2=4:6))

man/as.data.table.Rd

@@ -31,7 +31,7 @@ is.data.table(x)
 }
 \arguments{
   \item{x}{An R object.}
-  \item{keep.rownames}{Default is \code{FALSE}. If \code{TRUE}, adds the input object's names as a separate column named \code{"rn"}. \code{keep.rownames = "id"} names the column \code{"id"} instead.}
+  \item{keep.rownames}{Default is \code{FALSE}. If \code{TRUE}, adds the input object's names as a separate column named \code{"rn"}. \code{keep.rownames = "id"} names the column \code{"id"} instead. For lists and when calling \code{data.table()}, names from the first named vector are extracted and used as row names, similar to \code{data.frame()} behavior.}
   \item{key}{ Character vector of one or more column names which is passed to \code{\link{setkeyv}}. }
   \item{sorted}{logical used in \emph{array} method, default \code{TRUE} is overridden when \code{key} is provided. }
   \item{value.name}{character scalar used in \emph{array} method, default \code{"value"}.}