Open Access
Table D.1.
Values of Hyperparameters for meta learners after tuning.
| AGN-galaxy model (CatBoost) | |||
|---|---|---|---|
| Parameter | Value | Parameter | Value |
| learning_rate | 0.0075 | random_strength | 0.1 |
| depth | 6 | l2_leaf_reg | 10 |
| Radio detection model (GradientBoosting) | |||
| Parameter | Value | Parameter | Value |
| n_estimators | 187 | min_samples_leaf | 2 |
| learning_rate | 0.0560 | max_depth | 9 |
| subsample | 0.3387 | max_features | 0.5248 |
| min_samples_split | 5 | ||
| Redshift prediction model (ET) | |||
| Parameter | Value | Parameter | Value |
| n_estimators | 100 | criterion | mae |
| max_depth | None | min_samples_split | 2 |
| max_features | auto | min_samples_leaf | 1 |
| bootstrap | False | ||
Notes. This table shows the parameters which were subject to tuning. Remaining hyperparameters used their default values as defined by their developers.
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.