R devel - Mar 2019 - as.data.frame.table() does not recognize default.stringsAsFactors()

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]]

I have no recollection of the original rationale for as.data.frame.table, but I
actually think it is fine as it is:

The classifying _factors_ of a crosstable should be factors unless very
specifically directed otherwise and that should not depend on the setting of an
option that controls the conversion of character data.

For as.data.frame.matrix, in contrast, it is the _content_ of the matrix that is
being converted, and it seems much more reasonable to follow the same path as
for other character data.

-pd
> On 12 Mar 2019, at 21:39 , Mychaleckyj, Josyf C (jcm6t) <jcm6t at
virginia.edu> wrote:
> 
> 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 at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel
-- 
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Office: A 4.23
Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com

Peter,
Thanks for the response. I have no wish to prolong this and have no axe to
grind. I?m sure you were delighted to see another stringsAsFactors issue.

Perhaps we talking about the conflation of two steps: the first is the language
?pure' conversion of the table to a data.frame with the cross-tab factor,
followed by an optional  subsequent step with programmatic utility for a
specific application, of conversion of that factor to a character column.

As my toy example shows, the as.data.frame.table() function permits passing the
inline stringsAsFactors argument and returns a data.frame with a factor
cross-tab column coerced as a character column, permitting these two steps to be
accomplished in a single function.

If you intend the function to only meet the first step, then I would suggest you
remove stringsAsFactors as an argument to this function and amend the
documentation.
Following this, if an application needed a coercion to a character, then it
should be accomplished in a second step.

If you are implying that the core team intended options(stringsAsFactors) to be
a ?selective? global option then I am guess I am confused and have not seen
documentation about a limited scope of the session-wide options().

?options
  ?stringsAsFactors?: The default setting for arguments of
          ?data.frame? and ?read.table?.

As a practical programming matter this inconsistency created a bug in our code
that was very insidious and cost hours of debugging and a lot of head
scratching. Chars and factors are always prime candidates, but we never even
considered that the session option would not have been respected by a low level
core function in which the function call in the documentation explicitly
included the inline argument.

?as.data.frame.table() 

From the Usage section of as.data.frame.table()

     ## S3 method for class 'table'
     as.data.frame(x, row.names = NULL, ...,
                   responseName = "Freq", stringsAsFactors = TRUE,
                   sep = "", base = list(LETTERS))


Thanks,  Joe.

> On Mar 14, 2019, at 11:18 AM, peter dalgaard <pdalgd at gmail.com>
wrote:
> 
> I have no recollection of the original rationale for as.data.frame.table,
but I actually think it is fine as it is:
> 
> The classifying _factors_ of a crosstable should be factors unless very
specifically directed otherwise and that should not depend on the setting of an
option that controls the conversion of character data.
> 
> For as.data.frame.matrix, in contrast, it is the _content_ of the matrix
that is being converted, and it seems much more reasonable to follow the same
path as for other character data.
> 
> -pd
> 
>> On 12 Mar 2019, at 21:39 , Mychaleckyj, Josyf C (jcm6t) <jcm6t at
virginia.edu> wrote:
>> 
>> 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 at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-devel
> 
> -- 
> Peter Dalgaard, Professor,
> Center for Statistics, Copenhagen Business School
> Solbjerg Plads 3, 2000 Frederiksberg, Denmark
> Phone: (+45)38153501
> Office: A 4.23
> Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com
> 
> 
> 
> 
> 
> 
> 
> 
>

>>>>> peter dalgaard 
>>>>>     on Thu, 14 Mar 2019 16:18:55 +0100 writes:
    > I have no recollection of the original rationale for
as.data.frame.table, but I actually think it is fine as it is:
    > The classifying _factors_ of a crosstable should be factors unless very
specifically directed otherwise and that should not depend on the setting of an
option that controls the conversion of character data.

    > For as.data.frame.matrix, in contrast, it is the _content_ of the
matrix that is being converted, and it seems much more reasonable to follow the
same path as for other character data.

    > -pd

I very strongly agree that as.data.frame.table() should not be
changed to follow a global option.

To the contrary: I've repeatedly mentioned that in my view it
has been a design mistake to allow data.frame() and as.data.frame() be
influenced
by a global option
 [and we should've tried harder to keep things purely functional
   (R remaining as closely as possible a "functional language"), 
  e.g. by providing wrapper functions the same way we have such
  wrappers for versions of read.table() with different defaults
  for some of the arguments
 ]

Martin


    >> On 12 Mar 2019, at 21:39 , Mychaleckyj, Josyf C (jcm6t) <jcm6t
at virginia.edu> wrote:
    >> 
    >> 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 at r-project.org mailing list
    >> https://stat.ethz.ch/mailman/listinfo/r-devel

    > -- 
    > Peter Dalgaard, Professor,
    > Center for Statistics, Copenhagen Business School
    > Solbjerg Plads 3, 2000 Frederiksberg, Denmark
    > Phone: (+45)38153501
    > Office: A 4.23
    > Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com

    > ______________________________________________
    > R-devel at r-project.org mailing list
    > https://stat.ethz.ch/mailman/listinfo/r-devel