{mlr3spatiotempcv} makes use of {plotly} to create the 3D plots for visualizing spatiotemporal folds created via the CLUTO algorithm. Arranging multiple 3D plots in {plotly} is done via 3D subplots.
Unfortunately, {plotly}’s subplot implementation is not dynamic. This
means that multiple “scene” objects need to be specified in
plotly::layout()
to determine the coordinates of the
respective subplot. Depending on the number of chosen folds by the user
in autoplot()
, a different number of scenes with different
coordinates needs to be given to align the plots properly.
Hence, manual action is needed to create a properly aligned grid of 3D plots.
Below is an example how to create a 2x2 grid showing four folds as 3D
subplots. It makes use of the returned 3D plotly objects which are
returned in a list by autoplot()
:
library(mlr3)
library(mlr3spatiotempcv)
= tsk("cookfarm")
task_st = rsmp("sptcv_cstf",
resampling folds = 5, time_var = "Date",
space_var = "SOURCEID")
$instantiate(task_st)
resampling
= autoplot(resampling, task_st, c(1, 2, 3, 4),
pl crs = 4326, point_size = 3, axis_label_fontsize = 10,
plot3D = TRUE
)
# Warnings can be ignored
= plotly::subplot(pl)
pl_subplot
::layout(pl_subplot,
plotlytitle = "Individual Folds",
scene = list(
domain = list(x = c(0, 0.5), y = c(0.5, 1)),
aspectmode = "cube",
camera = list(eye = list(z = 2.5))
),scene2 = list(
domain = list(x = c(0.5, 1), y = c(0.5, 1)),
aspectmode = "cube",
camera = list(eye = list(z = 2.5))
),scene3 = list(
domain = list(x = c(0, 0.5), y = c(0, 0.5)),
aspectmode = "cube",
camera = list(eye = list(z = 2.5))
),scene4 = list(
domain = list(x = c(0.5, 1), y = c(0, 0.5)),
aspectmode = "cube",
camera = list(eye = list(z = 2.5))
) )
Note: The image shown above is a static version created with
plotly::orca()
.
Subplot titles can unfortunately not created dynamically. However, there is a manual workaround via annotations show in this RPubs post.
The following plots are based on a three fold partitioning of the ecuador
example task (expect method p_buffer
which is LOO-CV). They
do not claim to make sense or make use of useful settings - they only
have a showcase purpose. The code which produced the plots can be found
here.
A: "spcv_block"
B: "spcv_coords"
C: "spcv_env"
D: "spcv_disc"
E: "spcv_tiles"
F: "spcv_buffer"