Merge pull request #1325 from MichaelChirico/setDF

Closes #1320; setDF gains the rownames argument

R/data.table.R

@@ -2428,35 +2428,55 @@ address <- function(x) .Call(Caddress, eval(substitute(x), parent.frame()))
 
 ":=" <- function(...) stop('Check that is.data.table(DT) == TRUE. Otherwise, := and `:=`(...) are defined for use in j, once only and in particular ways. See help(":=").')
 
-setDF <- function(x) {
-    if (!is.list(x)) stop("setDF only accepts data.table, data.frame or list of equal length as input")
-    if (is.data.table(x)) {
-        # copied from as.data.frame.data.table
-        setattr(x, "row.names", .set_row_names(nrow(x)))
-        setattr(x, "class", "data.frame")
-        setattr(x, "sorted", NULL)
-        setattr(x, ".internal.selfref", NULL)
-    } else if (is.data.frame(x)) {
-        x
+setDF <- function(x, rownames=NULL) {
+  if (!is.list(x)) stop("setDF only accepts data.table, data.frame or list of equal length as input")
+  if (any(duplicated(rownames))) stop("rownames contains duplicates")
+  if (is.data.table(x)) {
+    # copied from as.data.frame.data.table
+    if (is.null(rownames)) {
+      rn <- .set_row_names(nrow(x))
+    }   else {
+      if (length(rownames) != nrow(x))
+        stop("rownames incorrect length; expected ", nrow(x), " names, got ", length(rownames))
+      rn <- rownames
+    }
+    setattr(x, "row.names", rn)
+    setattr(x, "class", "data.frame")
+    setattr(x, "sorted", NULL)
+    setattr(x, ".internal.selfref", NULL)
+  } else if (is.data.frame(x)) {
+    if (!is.null(rownames)){
+      if (length(rownames) != nrow(x)) 
+        stop("rownames incorrect length; expected ", nrow(x), " names, got ", length(rownames))
+      setattr(x, "row.names", rownames)
+    }
+    x
+  } else {
+    n = vapply(x, length, 0L)
+    mn = max(n)
+    if (any(n<mn))
+      stop("All elements in argument 'x' to 'setDF' must be of same length")
+    xn = names(x)
+    if (is.null(xn)) {
+      setattr(x, "names", paste("V",seq_len(length(x)),sep=""))
     } else {
-        n = vapply(x, length, 0L)
-        mn = max(n)
-        if (any(n<mn))
-            stop("All elements in argument 'x' to 'setDF' must be of same length")
-        xn = names(x)
-        if (is.null(xn)) {
-            setattr(x, "names", paste("V",seq_len(length(x)),sep=""))
-        } else {
-            idx = xn %chin% ""
-            if (any(idx)) {
-                xn[idx] = paste("V", seq_along(which(idx)), sep="")
-                setattr(x, "names", xn)
-            }
-        }
-        setattr(x,"row.names",.set_row_names(max(n)))
-        setattr(x,"class","data.frame")
+      idx = xn %chin% ""
+      if (any(idx)) {
+        xn[idx] = paste("V", seq_along(which(idx)), sep="")
+        setattr(x, "names", xn)
+      }
     }
-    invisible(x)
+    if (is.null(rownames)) {
+      rn <- .set_row_names(mn)
+    } else {
+      if (length(rownames) != mn)
+        stop("rownames incorrect length; expected ", mn, " names, got ", length(rownames))
+      rn <- rownames
+    }
+    setattr(x,"row.names", rn)
+    setattr(x,"class","data.frame")
+  }
+  invisible(x)
 }
 
 setDT <- function(x, keep.rownames=FALSE, key=NULL) {

README.md

@@ -78,6 +78,8 @@
 
   28. `fread()` gains `quote` argument with default value `"\""`. Setting `quote=""` disables (could be useful in reading columns with uneven quotes). Closes [#568](https://github.com/Rdatatable/data.table/issues/568). Also addresses/closes [#1256](https://github.com/Rdatatable/data.table/issues/1256), [#1077](https://github.com/Rdatatable/data.table/issues/1077), [#1079](https://github.com/Rdatatable/data.table/issues/1079) and [#1095](https://github.com/Rdatatable/data.table/issues/1095). Thanks to @Synergist, @daroczig, @geotheory and @rsaporta for the reports.
 
+  29. `setDF()` gains `rownames` argument for ready conversion to a `data.frame` with user-specified rows. Closes [#1320](https://github.com/Rdatatable/data.table/issues/1320). Thanks to @MichaelChirico for the FR and PR.
+
 #### BUG FIXES
 
   1. `if (TRUE) DT[,LHS:=RHS]` no longer prints, [#869](https://github.com/Rdatatable/data.table/issues/869) and [#1122](https://github.com/Rdatatable/data.table/issues/1122). Tests added. To get this to work we've had to live with one downside: if a `:=` is used inside a function with no `DT[]` before the end of the function, then the next time `DT` or `print(DT)` is typed at the prompt, nothing will be printed. A repeated `DT` or `print(DT)` will print. To avoid this: include a `DT[]` after the last `:=` in your function. If that is not possible (e.g., it's not a function you can change) then `DT[]` at the prompt is guaranteed to print. As before, adding an extra `[]` on the end of a `:=` query is a recommended idiom to update and then print; e.g. `> DT[,foo:=3L][]`. Thanks to Jureiss and Jan Gorecki for reporting.

inst/tests/tests.Rraw

@@ -4759,6 +4759,24 @@ df <- list(1:5, 6:10)
 test(1305.4, setDF(as.data.table(df)), setDF(df))
 test(1305.5, setDF(1:5), error="setDF only accepts")
 test(1305.6, setDF(list(1, 2:3)), error="All elements in argument")
+# Tests .7 - .13 for FR #1320: setDF accepts rownames argument
+dt  <- data.table(a=1:5, b=6:10)
+df  <- data.frame(a=1:5, b=6:10)
+lst <- list(a=1:5, b=6:10)
+df2 <- data.frame(a=1:5, b=6:10)
+rownames(df2) <- LETTERS[1:5]
+test(1305.7, setDF(dt, rownames=LETTERS[1:5]), df2)
+test(1305.8, setDF(df, rownames=LETTERS[1:5]), df2)
+test(1305.9, setDF(lst,rownames=LETTERS[1:5]), df2)
+# setDF returns an error for each type if rownames incorrect length
+dt  <- data.table(a=1:5, b=6:10)
+df  <- data.frame(a=1:5, b=6:10)
+lst <- list(a=1:5, b=6:10)
+test(1305.10, setDF(dt, rownames="a"), error='rownames incorrect length')
+test(1305.11, setDF(df, rownames="a"), error='rownames incorrect length')
+test(1305.12, setDF(lst,rownames="a"), error='rownames incorrect length')
+# setDF returns an error when rownames contains duplicates
+test(1305.13, setDF(dt, rownames=rep("a",5)), error='rownames contains duplicates')
 
 # .SD retains as much of head(key) as appropriate.
 #  by= always keeps data appearance order, so it's which columns are grouped and selected that drive how much of key is retained

man/setDF.Rd

@@ -7,14 +7,17 @@
   A helper function to convert a \code{data.table} or \code{list} of equal length to \code{data.frame} by reference.
 }
 \usage{
-setDF(x)
+setDF(x, rownames=NULL)
 }
 \arguments{
   \item{x}{ A \code{data.table}, \code{data.frame} or \code{list} of equal length. }
+  \item{rownames}{ A \code{character} vector to assign as the row names of \code{x}. }
 }
 
 \details{
   This feature request came up on the data.table mailing list: \url{http://bit.ly/1xkokNQ}. All \code{data.table} attributes including any keys of the input data.table are stripped off.
+
+  When using \code{rownames}, recall that the row names of a \code{data.frame} must be unique. By default, the assigned set of row names is simply the sequence 1, ..., \code{nrow(x)} (or \code{length(x)} for \code{list}s).
 }
 
 \value{
@@ -28,9 +31,12 @@ X = data.table(x=1:5, y=6:10)
 ## convert 'X' to data.frame, without any copy.
 setDF(X)
 
+X = data.table(x=1:5, y=6:10)
+## idem, assigning row names
+setDF(X, rownames = LETTERS[1:5])
+
 X = list(x=1:5, y=6:10)
 # X is converted to a data.frame without any copy.
 setDF(X)
 }
-\keyword{ data }
-
+\keyword{ data }