This task specializes Task and TaskSupervised for spatiotemporal classification problems.
A spatial example task is available via tsk("ecuador")
, a spatiotemporal
one via tsk("cookfarm")
.
The coordinate reference system passed during initialization must match the
one which was used during data creation, otherwise offsets of multiple meters
may occur. By default, coordinates are not used as features. This can be
changed by setting extra_args$coords_as_features = TRUE
.
mlr3::Task
-> mlr3::TaskSupervised
-> mlr3::TaskRegr
-> TaskRegrST
extra_args
(named list()
)
Additional task arguments set during construction.
Required for convert_task()
.
new()
Create a new spatiotemporal resampling Task
TaskRegrST$new( id, backend, target, extra_args = list(coords_as_features = FALSE, crs = NA, coordinate_names = NA) )
id
[character(1)]
Identifier for the task.
backend
DataBackend
Either a DataBackend, or any object which is convertible to a
DataBackend with as_data_backend()
. E.g., a data.frame()
will be
converted to a DataBackendDataTable.
target
[character(1)]
Name of the target column.
extra_args
[named list]
Additional task arguments set during construction. Required for
convert_task()
.
crs [character(1)]
Coordinate reference system. Either a PROJ string or an
EPSG code.
coords_as_features [logical(1)]
Whether the coordinates should also be used as features.
coordinate_names [character(2)]
The variables names of the coordinates in the data.
coordinates()
Return the coordinates of the task
TaskRegrST$coordinates(rows = NULL)
rows
Row IDs. Can be used to subset the returned coordinates.
print()
Print the task.
TaskRegrST$print(...)
...
Arguments passed to the $print()
method of the superclass.
clone()
The objects of this class are cloneable with this method.
TaskRegrST$clone(deep = FALSE)
deep
Whether to make a deep clone.
Other Task:
TaskClassifST
,
mlr_tasks_cookfarm
,
mlr_tasks_diplodia
,
mlr_tasks_ecuador