Skip to content

Conversation

@mdeylessard
Copy link

@mdeylessard mdeylessard commented Oct 16, 2025

Overview

Brief description of what this PR does, and why it is needed.

Using usaddress (0.5.16) in a BigQuery UDF and noticing inaccurate parsing of addresses with the following patterns:

  • Multi-word street names, particular if name contains more than one street suffix
  • Occupancy types of "basement" and "trailer"
  • Occupancy identifiers of "upper," "lower," and "ground"

Testing

  • 3 iterations of labeling and training real and mock addresses

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant