Open Access

Fig. 2.

image

Download original image

Confusion matrix built using leave-one-out cross-validation (upper panels) and relative feature importance returned by the XGBOOST package (lower panels) for the nuclear (left panels) and broad (right panels) models. The percentages displayed inside the confusion matrices are values normalized on completeness.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.