[Josef-Haupt]

• Evaluation binning is about 20x faster and gives identical output.
• Rows, the data table and the recording list are sorted by recording name.
• A missing or empty confidence column raises an error instead of scoring 0.
• Data-processor warnings are logged, so CLI users see them.
• Recordings with annotations but no predictions are kept and scored as misses.
• Header-only tables no longer trigger a pandas FutureWarning.
• birdnet-evaluate writes uncaught errors to the error log, like the other CLIs.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has insufficient remaining quota.

An organization owner can choose the repository organization as the billing source for reviews requested by members with a paid Copilot license. Learn about Copilot code review billing.