c2g-dev/city2graph

Health v2 · maintenance only

Adoption not part of the score

1940 stars · 204 forks observed · 2026-10-09

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

City2Graph is a Python library that converts geospatial data such as buildings, streets, GTFS transit feeds, and origin-destination matrices into spatial and heterogeneous graphs. It bridges GeoPandas, NetworkX, and PyTorch Geometric so the same data supports both network analysis and Graph Neural Network workflows.

Use cases

• convert openstreetmap buildings and streets into graphs for gnn training
• build stop-to-stop transit graphs from gtfs feeds
• turn origin-destination mobility matrices into weighted spatial graphs
• compute knn delaunay or queen contiguity spatial weights
• convert geodataframes to pytorch geometric heterodata tensors
• urban morphology and street network analysis
• spatial knowledge graphs for geoai applications

When to choose

• you need to bridge geospatial vector data with graph neural networks
• you work with gtfs, gbfs, or od flow data and want graph representations
• you want one library spanning geopandas, networkx, and pytorch geometric
• you do urban analytics, transportation, or geoai research in python

When to avoid

• you need raster or satellite imagery processing rather than vector graphs
• you need production gnn training infrastructure rather than graph construction
• you work outside python or need non-geospatial graph databases

Facets

library · maturity active

geospatial machine-learning data-science parser machine-learning data-science python cross-platform graph-neural-networks pytorch-geometric urban-analytics gis network-analysis gtfs mobility spatial-graphs geopandas networkx geoai urban-morphology geospatial maps transportation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="c2g-dev/city2graph")