Per-box-type footprint aspect ratio (1 = square base) and
relative height (height over the longer base edge) for the training
distribution and five unseen distributions.
Distribution
Box types
Aspect median (IQR)
W1
Rel. height median (IQR)
W1
Figure 2. Kernel density estimates over the unique box dimensions in each
box distribution. Inner marks represent the quartiles and W1 is
the 1-D Wasserstein distance to the training distribution. Higher
W1 values indicate the distribution is more dissimilar from the
training distribution.
Distributions C and E have only 3 and 2 box types and are drawn as points
(×n marks coincident values). Hover or focus the chart and use arrow keys
for exact values; the table view lists them all.