Urbanity is a network-based Python package developed at the NUS Urban Analytics Lab to automate the construction of feature rich (contextual and semantic) urban networks at any geographical scale. Through an accessible and simple to use interface, users can request heterogeneous urban information such as street view imagery, building morphology, population (including sub-group), and points of interest for target areas of interest.
- Rapid city-scale network generation
- Seamless computation of metric, topological, contextual, and semantic network indicators
- Node and edge spatial context computation
- Areal statistics for arbitrary urban subzones
- Validity checks for OpenStreetMap attribute completeness (no. of buildings, percentage with height, percentage with levels, etc.)
- Primal planar, dual, and spatial graph generation
- Generating graph machine learning ready graphs
To facilitate quicker access to city scale graphs, we provide a set of analysis-ready graphs for many cities with a wide set of useful urban attributes. Users can directly download these datasets and use them quickly in their workflows:
Urbanity is designed in an object-oriented approach that parallels the urban planning process. The urban data science pipeline starts with a base map which users can use to explore their site. Subsequently, there are two ways to specify geographical area of interest: 1) drawing with the polygon and box tools provided; or 2) providing your own polygon shapefiles (all common formats .shp/.geojson are supported).
Towards exploring complexities underlying urban systems and facilitating comparative study between cities, Urbanity is developed to facilitate downstream descriptive, modelling, and predictive urban analytical tasks.
Urbanity is built on several geospatial packages (e.g., GeoPandas, ipyleaflet, rasterio, etc.,) that are best compiled through conda-forge. For seamless installation, we provide an environment.yml file for users to create their own conda environment. Please follow the steps below to ensure proper installation:
- Navigate to a location of choice (e.g., Desktop or project folder).
- Download environment.yml and setup.sh file and place it at the location of choice (Step 1).
- Open up a terminal/command prompt and input the following command:
$ chmod +x ./setup.sh
$ ./setup.sh
Google earth engine (GEE) API and community catalog provides open access to thousands of remote sensing data layers. Academic users can register for a free Google Earth Engine research account here
import ee
ee.Authenticate()
ee.Initialize(project='your-project-id')
Mapillary hosts the 8847 world's largest selection of crowdsourced streetview imagery which covers most cities in the world. Request for an access token here
Mapbox hosts a collection of freely available high resolution satellite imagery with global coverage. Request for an access token in account developer page here
$ touch .env
Open the .env file and fill out your registered API keys
MAPILLARY_API_SECRET=MLY|XXXXXXXXXXXXXXX|XXXXXXXXXXXXXXX
MAPILLARY_API_TOKEN=MLY|XXXXXXXXXXXXXXX|XXXXXXXXXXXXXXX
MAPBOX_API_TOKEN=pk.XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
(Optional) For JupyterLab / JupyterNotebook users, you can additionally add a notebook kernel via:
$ python -m ipykernel install --user --name=urbanity
$ jupyter lab
We demonstrate how you can conduct a diverse range of urban analytical tasks (such as graph machine learning, network assortativity analysis, and benchmarking across cities) with Urbanity. Check out the documentation and examples/tutorials in the documentation site examples.
Sample dataset and notebooks to follow examples can be accessed at this repository.
One popular use case for Urbanity is for graph machine learning on urban networks. These tasks are consistent with GraphML literature and include node level, edge level, and graph level predictive tasks.
Questions concerning use cases can be directed to the author: winstonyym@u.nus.edu
If you use Urbanity in your work, please cite:
Yap, W., Stouffs, R. & Biljecki, F. Urbanity: automated modelling and analysis of multidimensional networks in cities. npj Urban Sustain 3, 45 (2023). https://doi.org/10.1038/s42949-023-00125-w
Yap, W., Biljecki, F. A Global Feature-Rich Network Dataset of Cities and Dashboard for Comprehensive Urban Analyses. Sci Data 10, 667 (2023). https://doi.org/10.1038/s41597-023-02578-1
Yap, W., Chang, J. H., & Biljecki, F. (2023). Incorporating networks in semantic understanding of streetscapes: Contextualising active mobility decisions. Environment and Planning B: Urban Analytics and City Science, 50(6), 1416-1437. https://doi.org/10.1177/23998083221138832
urbanity was created by winstonyym. It is licensed under the terms of the MIT license.
- Logo design: April Zhu
- Colab notebooks: Kunihiko Fujiwara
- OSMnx Github
- Geopandas Github
- Pyrosm Github
- NetworkX Github
- ipyleaflet Github