Changelog
Source:NEWS.md
mlr3spatial 0.4.1
CRAN release: 2023-05-03
- refactor: Use the
terra::inMemory()
function instead of@ptr
.
mlr3spatial 0.4.0
CRAN release: 2023-02-27
- refactor: The data input of
spatial_predict()
acceptsSpatRaster
,stars
sf
RasterStack
andRasterBrick
objects now. Amlr3::TaskUnsupervised
can still be passed but the argument name changed fromtask
tonewdata
. - fix: The log showed a warning when the estimated values per chunk were a floating number.
mlr3spatial 0.3.1
CRAN release: 2022-12-16
- chore: Remove
rgdal
dependency and requireraster
version 3.6-11.
mlr3spatial 0.2.1
CRAN release: 2022-08-25
- fix: Add
"space"
and"time"
column role from mlr3spatiotempcv
mlr3spatial 0.2.0
CRAN release: 2022-08-18
- BREAKING CHANGE:
TaskClassifST
andTaskRegrST
are used to train a learner with spatial data. The new tasks unify the work with mlr3spatiotempcv. - BREAKING CHANGE: Raster objects cannot be used to create tasks for training anymore.
- BREAKING CHANGE:
TaskUnsupervised
is used to predict on rasters objects now. The new task type is more convenient for data without a response. - feat: Add
as_task_regr_st()
andas_task_classif_st()
from spatial objects. - feat: Add
as_task_unsupervised()
from raster objects. - feat: Task
leipzig
with land cover target. - feat:
data("leipzig")
loads ansf
object with land cover in Leipzig. - feat: GeoTIFF and GeoPackage of Leipzig in
extdata
folder. - refactor: Vector data is handled with
DataBackendDataTable
now andDataBackendVector
is removed. - BREAKING CHANGE:
DataBackendRaster
cannot be created fromRasterLayer
objects anymore. - fix:
spatial_predict()
returned an unnamed response. - fix:
spatial_predict()
wrote predictions to the wrong cell. - BREAKING CHANGE: Remove
demo_raster()
,demo_stack_spatraster()
,demo_stack_rasterbrick()
anddemo_rasterbrick()
functions. - feat: Prediction layer contains
NA
at raster cells withNA
values in one or more feature layers.