Free Access

Fig. A.3.

image

Precision, recall, and F1 score plotted as a function of each magnitude feature per class, as derived from the random forest model applied to the test dataset of 1.55 million spectroscopically confirmed sources. In the top row, a histogram of each magnitude feature is also shown as a dotted line per class (normalised to one third) to show the source density. In the bottom row the classification probabilities from the random forest model for the assigned classes are shown by dashed lines. Galaxies are shown in green, quasars in pink, and stars in blue.

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.