This release improves the calibration of output predictions, and provides tools to calibrate future HawkEars models.
What's Changed
- Predictions from the included models are generally higher, and closer to probabilities. That is, scores of .85 are now expected to be correct about 85% of the time. In previous releases, they were correct >90% of the time.
- Because scores are higher, the default min_score was increased from .75 to .80.
- The score_exponent is replaced with scaling_coefficient and scaling_intercept. These are used in main_model.py to implement Platt scaling.
- Three new scripts are included to support calibration: pickle_test.py, calibrate.py and plot_calibration_curve.py. See the comments in those scripts for more details.
- A new del_recording.py script is included to delete a recording from a database.
- We fixed an indexing bug in species_handlers.py.