view article
Figure 4
Confusion matrices reporting the performances of all the XGBoost models (noise-free, noisy, sparsely sampled, densely sampled in columns 2–5) on different structural descriptors. Compared with the truth–truth matrices in column 1, all the trained models perform well on both the training set and the testing set, suggesting the ability to generalize for unknown datasets.

IUCrJ
Volume 7| Part 5| September 2020| Pages 870-880
ISSN: 2052-2525
https://doi.org/10.1107/S2052252520008830