Fig. 4: The performance of final classification models over varying numbers of training instances. | npj Viruses

Fig. 4: The performance of final classification models over varying numbers of training instances.

From: Automated classification of giant virus genomes using a random forest model built on trademark protein families

Fig. 4

The curves are plotted with the mean cross validated test scores. Shaded areas represent a standard deviation above and below the mean for all cross-validations. The scores of model at the order level are shown in blue and scores of model at the family level are in green.

Back to article page