Installation¶

VoxCity runs on Python 3.12. GDAL is the one dependency that is easiest to install through conda; everything else is available from PyPI.

Requirements¶

Python 3.12
GDAL (install via conda-forge, see below)
A Google Earth Engine account for the cloud-served data sources (see Set up Google Earth Engine)

Install with conda + pip (recommended)¶

conda create --name voxcity python=3.12
conda activate voxcity
conda install -c conda-forge gdal timezonefinder
pip install voxcity

Install on Google Colab¶

VoxCity installs directly with pip on Colab:

!pip install voxcity

Verify the installation¶

import voxcity
print(voxcity.__version__)

Set up Google Earth Engine¶

Many VoxCity data sources are served through Google Earth Engine. Create an Earth Engine–enabled Cloud Project by following the official setup guide, then authenticate:

# Local environment
earthengine authenticate

# Google Colab: click the displayed link, generate a token, then paste it
!earthengine authenticate --auth_mode=notebook

For a full walkthrough of authentication and project configuration, see the Earth Engine setup guide.

Next steps¶

Follow the tutorial notebooks to generate your first model.
Browse the how-to guides for task-focused recipes.