Thin R wrapper around sample_mode_cpp(), which returns the most
frequently occurring value in data. Integer, logical, double,
character, and factor vectors are all supported (dispatched internally on
TYPEOF(data); factors preserve their class/levels
attributes on the returned value). NA (and, for doubles, NaN
as a category distinct from NA) is counted like any other value and
can itself be returned as "the mode" if it is the most frequent entry.
Ties are broken by first occurrence: among values tied for the
highest count, the one that appears earliest in data is returned —
this is a positional, not a numeric/lexicographic, tie-break rule.
Value
A length-1 vector (same type as data) holding the most frequently occurring
value, with ties broken in favor of whichever tied value occurs earliest in data.
Examples
sample_mode(c(1, 2, 2, 3))
#> [1] 2