The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
train_color and test_color
in autoplot() (#241, #243).ppoints param in {CAST} functions to
predpoints to adhere with the upstream package renaming
(#237)autoplot() functions
(#231).autoplot() sub-functions.label_size to “spcv_block” to make label size
configurable (#227)show_omitted for “spcv_buffer” method (#228)label support for built-in tasksTaskClassifST
or TaskRegrST from an sf objectTaskClassifST or TaskRegrST
with {mlr3spatial}mlr_reflections changes in {mlr3} >
0.13.4autoplot.ResamplingSptCVCstf(): Add missing support for
argument axis_label_fontsize for x and y axesautoplot.ResamplingSptCVCstf: when multiple folds are
requested, the subplots are now returned again (before, the return was
empty)autoplot.ResamplingSptCVCstf: the legend item for the
“omitted” observations now displays the correct color and label
againcookfarm to cookfarm_mlr3.
This was done to distinguish the cookfarm task
implementation in {mlr3} better from the original cookfarm
dataset. cookfarm_mlr3 also now comes with all rows of the
upstream cookfarm task and not with a random subset as
before.mlr_resampling_spctcv_cstf implementation.
The method will produce different fold results compared to
{mlr3spatiotempcv} <= 1.0.1. This is because of a change/fix
in the sampling behavior: before, an (unwanted) stratified sampling was
done on time and space variables. While this
matched the upstream implementation in {CAST}, this did not match with
the actual theoretical underpinning described in the literature.TaskClassifST$new() and
TaskRegrST$new() only accepts
DataBackendDataTable. Support for sf objects
has moved to as_task_*_st() which accepts sf
objects directly and creates the DataBackend behind the scenes.DataBackendRaster (@be-marc, #191).mlr_resampling_spctcv_cstf: a log message returns the
column roles from the Task which are used for partitioningTask*ST classes now print column roles
space and time (if set) (#198)autoplot() gains plot_time_var argument
for 3D visualizations of mlr_resamplings_sptcv_cstf
resamplings with only ‘space’ used for partitioning (#197)cookfarm_mlr3 task now sets column roles “space”
and “time” for variables SOURCEID and Date,
respectively.autoplot() support for "groups" column
role in rsmp("cv")autoplot(): removed argument crs. The CRS
is now inferred from the supplied Task. Setting a different CRS than the
task might lead to spurious issues and the initial idea of changing the
CRS for plotting to have proper axes labeling does not apply (anymore)
(#144)autoplot() support for
ResamplingCustomCV (#140)"spcv_block": Assert error if folds > 2 when
selection = "checkerboard" (#150)TaskRegrST tasks
from sf objects (#152)"spcv_block"
since it is required in {blockCV} >= 2.1.4 and {sf} >= 1.0"sptcv_cluto"as_task_* S3 generics:
as_task_classif_st.data.frame(),
as_task_classif_st.DataBackend(),
as_task_classif_st.sf(),
as_task_regr_st.data.frame(),
as_task_regr_st.DataBackend(),
as_task_regr_st.sf(),
as_task_classif.TaskClassifST(),
as_task_regr.TaskRegrST() (#99)"spcv_tiles" and "repeated_spcv_tiles"
(#121)"spcv_disc" (#115)sptcv_cstf() with space and
time var (#135)$folds() active binding returning wrong fold
number (#120)man IDs (#122)autoplot.ResamplingSptCVCstf(): add 2D plotting method
(#106)autoplot.ResamplingSptCVCstf(): add arguments
show_omitted and static_image (#100)autoplot() (all methods): allow adjusting point size
via ... (#98)cookfarm dataset standaloneCstf method for spatiotemporal viz vignetteResamplingRepeatedSptCVCstf
(beforehand the Cluto method was referenced accidentally)autoplot.ResamplingSpcvBlock example
when rendering pkgdown site (unclear why this happens when
show_labels = TRUE)autoplot() examples and related
documentationrasterLayer argument in
blockCV::spatialBlock() (#94)blockCV::spatialBlock() functions actually
returns the same result when invoked via {mlr3spatiotempcv} (#93). Among
other issues,
blockCV::spatialBlock(selection = "checkerboard") was
ignored.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.