$predict_newdata() and
predict_spatial() work without optional column roles like
coordinate now.X and Y columns
are present in an sf objectterra::inMemory() function instead of
@ptr.spatial_predict() accepts
SpatRaster, stars sf
RasterStack and RasterBrick objects now. A
mlr3::TaskUnsupervised can still be passed but the argument
name changed from task to newdata.rgdal dependency and require
raster version 3.6-11.spatial_predict()."space" and "time" column role
from mlr3spatiotempcvTaskClassifST and
TaskRegrST are used to train a learner with spatial data.
The new tasks unify the work with mlr3spatiotempcv.TaskUnsupervised is used to predict on
rasters objects now. The new task type is more convenient for data
without a response.as_task_regr_st() and
as_task_classif_st() from spatial objects.as_task_unsupervised() from raster
objects.leipzig with land cover target.data("leipzig") loads an sf object
with land cover in Leipzig.extdata
folder.DataBackendDataTable now and DataBackendVector
is removed.DataBackendRaster cannot be created
from RasterLayer objects anymore.spatial_predict() returned an unnamed
response.spatial_predict() wrote predictions to the wrong
cell.demo_raster(),
demo_stack_spatraster(),
demo_stack_rasterbrick() and
demo_rasterbrick() functions.NA at raster cells with
NA values in one or more feature layers.
Need a high-speed mirror for your open-source project?
Contact our mirror admin team at info@clientvps.com.
This archive is provided as a free public service to the community.
Proudly supported by infrastructure from VPSPulse , RxServers , BuyNumber , UnitVPS , OffshoreName and secure payment technology by ArionPay.