This paper presents Geomancer, an open-source framework for geospatial feature engineering. It simplifies the acquisition of geospatial attributes for downstream, large-scale machine learning tasks. Geomancer leverages any geospatial dataset stored in a data warehouse, users need only to define the features (Spells) they want to create, and cast them on any spatial dataset. In addition, these features can be exported into a JSON file (SpellBook) for sharing and reproducibility. Geomancer has been useful to some of our production use-cases such as property value estimation, area valuation, and more. It is available on Github, and can be installed from PyPI.
Cite
@article{arxiv.1910.05571,
title = {Geomancer: An Open-Source Framework for Geospatial Feature Engineering},
author = {Lester James V. Miranda and Mark Steve Samson and Alfiero K. Orden and Bianca S. Silmaro and Ram K. De Guzman and Stephanie S. Sy},
journal= {arXiv preprint arXiv:1910.05571},
year = {2019}
}