Open Access

Table 5

Classification metrics for the XGBoost classification model in the multi-class approach, with the monitoring model for the photo-z predictions.

Drop outliers Accuracy Precision Recall F1-score
No 0.988 0.985 0.979 0.982
Yes 0.989 0.988 0.981 0.984

Notes. The impact of the removal of potential catastrophic outliers is studied.

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.