Specify measure.vars via regex or separator

These functions compute an integer vector or list for use as the measure.vars argument to melt. Each measured variable name is converted into several groups that occupy different columns in the output melted data. measure allows specifying group names/conversions in R code (each group and conversion specified as an argument) whereas measurev allows specifying group names/conversions using data values (each group and conversion specified as a list element). See vignette("datatable-reshape") for more info.

Usage

measure(..., sep, pattern, cols, multiple.keyword="value.name")
measurev(fun.list, sep, pattern, cols, multiple.keyword="value.name",
  group.desc="elements of fun.list")

Arguments

...: One or more (1) symbols (without argument name; symbol is used for group name) or (2) functions to convert the groups (with argument name that is used for group name). Must have same number of arguments as groups that are specified by either sep or pattern arguments.
fun.list: Named list which must have the same number of elements as groups that are specified by either sep or pattern arguments. Each name used for a group name, and each value must be either a function (to convert the group from a character vector to an atomic vector of the same size) or NULL (no conversion).
sep: Separator to split each element of cols into groups. Columns that result in the maximum number of groups are considered measure variables.
pattern: Perl-compatible regex with capture groups to match to cols. Columns that match the regex are considered measure variables.
cols: A character vector of column names.
multiple.keyword: A string, if used as a group name, then measure returns a list and melt returns multiple value columns (with names defined by the unique values in that group). Otherwise if the string not used as a group name, then measure returns a vector and melt returns a single value column.
group.desc: Internal, used in error messages.

Examples

(two.iris = data.table(datasets::iris)[c(1,150)])
#>    Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
#>           <num>       <num>        <num>       <num>    <fctr>
#> 1:          5.1         3.5          1.4         0.2    setosa
#> 2:          5.9         3.0          5.1         1.8 virginica
# melt into a single value column.
melt(two.iris, measure.vars = measure(part, dim, sep="."))
#>      Species   part    dim value
#>       <fctr> <char> <char> <num>
#> 1:    setosa  Sepal Length   5.1
#> 2: virginica  Sepal Length   5.9
#> 3:    setosa  Sepal  Width   3.5
#> 4: virginica  Sepal  Width   3.0
#> 5:    setosa  Petal Length   1.4
#> 6: virginica  Petal Length   5.1
#> 7:    setosa  Petal  Width   0.2
#> 8: virginica  Petal  Width   1.8
# do the same, programmatically with measurev
my.list = list(part=NULL, dim=NULL)
melt(two.iris, measure.vars=measurev(my.list, sep="."))
#>      Species   part    dim value
#>       <fctr> <char> <char> <num>
#> 1:    setosa  Sepal Length   5.1
#> 2: virginica  Sepal Length   5.9
#> 3:    setosa  Sepal  Width   3.5
#> 4: virginica  Sepal  Width   3.0
#> 5:    setosa  Petal Length   1.4
#> 6: virginica  Petal Length   5.1
#> 7:    setosa  Petal  Width   0.2
#> 8: virginica  Petal  Width   1.8
# melt into two value columns, one for each part.
melt(two.iris, measure.vars = measure(value.name, dim, sep="."))
#>      Species    dim Sepal Petal
#>       <fctr> <char> <num> <num>
#> 1:    setosa Length   5.1   1.4
#> 2: virginica Length   5.9   5.1
#> 3:    setosa  Width   3.5   0.2
#> 4: virginica  Width   3.0   1.8
# melt into two value columns, one for each dim.
melt(two.iris, measure.vars = measure(part, value.name, sep="."))
#>      Species   part Length Width
#>       <fctr> <char>  <num> <num>
#> 1:    setosa  Sepal    5.1   3.5
#> 2: virginica  Sepal    5.9   3.0
#> 3:    setosa  Petal    1.4   0.2
#> 4: virginica  Petal    5.1   1.8
# melt using sep, converting child number to integer.
(two.families = data.table(sex_child1="M", sex_child2="F", age_child1=10, age_child2=20))
#>    sex_child1 sex_child2 age_child1 age_child2
#>        <char>     <char>      <num>      <num>
#> 1:          M          F         10         20
print(melt(two.families, measure.vars = measure(
  value.name, child=as.integer,
  sep="_child"
)), class=TRUE)
#>    child    sex   age
#>    <int> <char> <num>
#> 1:     1      M    10
#> 2:     2      F    20
# same melt using pattern.
print(melt(two.families, measure.vars = measure(
  value.name, child=as.integer,
  pattern="(.*)_child(.)"
)), class=TRUE)
#>    child    sex   age
#>    <int> <char> <num>
#> 1:     1      M    10
#> 2:     2      F    20
# same melt with pattern and measurev function list.
print(melt(two.families, measure.vars = measurev(
  list(value.name=NULL, child=as.integer),
  pattern="(.*)_child(.)"
)), class=TRUE)
#>    child    sex   age
#>    <int> <char> <num>
#> 1:     1      M    10
#> 2:     2      F    20
# inspired by data(who, package="tidyr")
(who <- data.table(id=1, new_sp_m5564=2, newrel_f65=3))
#>       id new_sp_m5564 newrel_f65
#>    <num>        <num>      <num>
#> 1:     1            2          3
# melt to three variable columns, all character.
melt(who, measure.vars = measure(diagnosis, gender, ages, pattern="new_?(.*)_(.)(.*)"))
#>       id diagnosis gender   ages value
#>    <num>    <char> <char> <char> <num>
#> 1:     1        sp      m   5564     2
#> 2:     1       rel      f     65     3
# melt to five variable columns, two numeric (with custom conversion).
print(melt(who, measure.vars = measure(
  diagnosis, gender, ages,
  ymin=as.numeric,
  ymax=function(y)ifelse(y=="", Inf, as.numeric(y)),
  pattern="new_?(.*)_(.)(([0-9]{2})([0-9]{0,2}))"
)), class=TRUE)
#>       id diagnosis gender   ages  ymin  ymax value
#>    <num>    <char> <char> <char> <num> <num> <num>
#> 1:     1        sp      m   5564    55    64     2
#> 2:     1       rel      f     65    65   Inf     3

Specify measure.vars via regex or separator

Usage

Arguments

See also

Examples