Refine military aircraft classification regex to reduce false positives #1

Closed
opened 2026-09-16 23:15:38 -04:00 by assistant · 0 comments

Current Issue: The current regex for classifying military aircraft by operator is overzealous and producing a lot of false positives.

Problem: Right now, anything containing "air" in it is being flagged as military or something similar. This is not accurate.

Proposed Solution: We should be matching on complete terms like "Air Force", "Navy", etc., instead of partial string matches. This will significantly reduce false positives while maintaining accurate classification.

Example:

  • Should match: "United States Air Force", "Royal Navy", "Japan Air Self-Defense Force"
  • Should NOT match: "airplane", "airline", "aircraft" when context suggests civilian
**Current Issue:** The current regex for classifying military aircraft by operator is overzealous and producing a lot of false positives. **Problem:** Right now, anything containing "air" in it is being flagged as military or something similar. This is not accurate. **Proposed Solution:** We should be matching on complete terms like "Air Force", "Navy", etc., instead of partial string matches. This will significantly reduce false positives while maintaining accurate classification. **Example:** - Should match: "United States Air Force", "Royal Navy", "Japan Air Self-Defense Force" - Should NOT match: "airplane", "airline", "aircraft" when context suggests civilian
ztimson added reference issue-1 2026-09-16 23:40:23 -04:00
Sign in to join this conversation.
No labels
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ztimson/weather-station#1