angus-spence/loc2vec

Learning semantic embeddings from OSM data: A Pytorch implementation of the loc2vec general method outlined in: https://sentiance.com/loc2vec-learning-location-embeddings-w-triplet-loss-networks.

28
/ 100
Experimental

This tool helps urban planners, real estate analysts, or logistics experts understand the unique characteristics and similarities between different geographic areas. By taking raster data representing OpenStreetMap features like roads, parks, and commercial zones, it generates a unique 'fingerprint' for each location. These 'fingerprints' can then be used to compare locations, find similar areas, or predict behavior based on geographical context.

No commits in the last 6 months.

Use this if you need to quantitatively understand the 'personality' of a location based on its built environment and natural features, especially for tasks like urban planning, site selection, or regional comparison.

Not ideal if your primary goal is simple mapping visualization or if you don't have existing geographic feature data in a raster format.

urban-planning real-estate-analysis location-intelligence geographic-similarity geospatial-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

MIT

Last pushed

Oct 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/angus-spence/loc2vec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.