-
For space-filling designs for
$p$ parameters, there is a higher likelihood of finding a space-filling design for1 < size <= p
. Also, single-point designs now default to a random grid (#363). -
value_seq()
andvalue_sample()
now respect theinclusive
argument of quantitative parameters (#347). -
The constructors,
new_*_parameter()
, now label unlabeled parameter (i.e., constructed withlabel = NULL
) as such (#349). -
All messages, warnings and errors has been translated to use {cli} package (#311).
-
parameters.list()
now enforces the unused ellipsis to be empty (#378). -
Added three new parameters for use in postprocessing in the tailor package (#357).
-
buffer()
sets the distance on either side of a classification threshold
within which predictions are considered equivocal in
tailor::adjust_equivocal_zone()
. -
lower_limit()
andupper_limit()
sets the ranges for
numeric predictions intailor::adjust_numeric_range()
.
-
Breaking changes
-
The
grid_*()
functions now error instead of warn when provided with the wrong argument to control the grid size. Sogrid_space_filling()
,grid_random()
,grid_max_entropy()
, andgrid_latin_hypercube()
now error if used with alevels
argument andgrid_regular()
now errors if used with asize
argument (#368). -
The
"optimal"
option for theweight_func()
parameter has been removed since it is choosing the optimal value based on the resubstition error (#370). -
When constructing integer-valued parameters with a range of two consecutive values the
inclusive
argument needs to be set toc(TRUE, TRUE)
to leave at least two values to sample from (#373).