Reporting a possible inconsistency or bug in handling stringsAsFactors in
as.data.frame.table()
Here is a simple test
> options()$stringsAsFactors
[1] TRUE
> x<-c("a","b","c","a","b")
> d<-as.data.frame(table(x))
> d
x Freq
1 a 2
2 b 2
3 c 1
> class(d$x)
[1] "factor"
> d2<-as.data.frame(table(x),stringsAsFactors=F)
> class(d2$x)
[1] “character"
> options(stringsAsFactors=F)
> options()$stringsAsFactors
[1] FALSE
> d3<-as.data.frame(table(x))
> d3
x Freq
1 a 2
2 b 2
3 c 1
> class(d3$x)
[1] “factor"
> d4<-as.data.frame(table(x),stringsAsFactors=F)
> class(d4$x)
[1] “character"
# Display the code showing the different stringsAsFactors handling in table
and matrix:
> as.data.frame.table
function (x, row.names = NULL, ..., responseName = "Freq", stringsAsFactors =
TRUE,
sep = "", base = list(LETTERS))
{
ex <- quote(data.frame(do.call("expand.grid", c(dimnames(provideDimnames(x,
sep = sep, base = base)), KEEP.OUT.ATTRS = FALSE, stringsAsFactors =
stringsAsFactors)),
Freq = c(x), row.names = row.names))
names(ex)[3L] <- responseName
eval(ex)
}
<bytecode: 0x28769f8>
<environment: namespace:base>
> as.data.frame.matrix
function (x, row.names = NULL, optional = FALSE, make.names = TRUE,
..., stringsAsFactors = default.stringsAsFactors())
{
d <- dim(x)
nrows <- d[[1L]]
ncols <- d[[2L]]
ic <- seq_len(ncols)
dn <- dimnames(x)
if (is.null(row.names))
row.names <- dn[[1L]]
collabs <- dn[[2L]]
if (any(empty <- !nzchar(collabs)))
collabs[empty] <- paste0("V", ic)[empty]
value <- vector("list", ncols)
if (mode(x) == "character" && stringsAsFactors) {
for (i in ic) value[[i]] <- as.factor(x[, i])
}
else {
for (i in ic) value[[i]] <- as.vector(x[, i])
}
autoRN <- (is.null(row.names) || length(row.names) != nrows)
if (length(collabs) == ncols)
names(value) <- collabs
else if (!optional)
names(value) <- paste0("V", ic)
class(value) <- "data.frame"
if (autoRN)
attr(value, "row.names") <- .set_row_names(nrows)
else .rowNamesDF(value, make.names = make.names) <- row.names
value
}
<bytecode: 0x29995c0>
<environment: namespace:base>
> sessionInfo()
R version 3.5.2 (2018-12-20)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: CentOS Linux 7 (Core)
Matrix products: default
BLAS: /usr/lib64/libblas.so.3.4.2
LAPACK: /usr/lib64/liblapack.so.3.4.2
locale:
[1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
[3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
[5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
[7] LC_PAPER=en_US.UTF-8 LC_NAME=C
[9] LC_ADDRESS=C LC_TELEPHONE=C
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
attached base packages:
[1] stats graphics grDevices utils datasets methods base
loaded via a namespace (and not attached):
[1] compiler_3.5.2 tools_3.5.2
Thanks,
Joe
[[alternative HTML version deleted]]
______________________________________________
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel
