2025-11-23 –, Plenary Space
Crow Advisory chose python for their spatial forecast analysis of the Wellington housing development response to Wellington's 2024 District Plan, which greatly increased allowable building capacity across the city. We'll talk through the tools we used, the design approach, and what we learned about doing spatial data science in python.
Tools used include
- poetry for dependency management,
- hydra (via hydra-zen) with dataclasses for config management, CLI setup, and keeping a record of config inputs vs model outputs
- DVC for data version control, preprocessing management, efficient pipeline runs, and more tracking of inputs vs outputs
- loguru for logging and terminal outputs
- pandas, numpy, and geopandas for data wrangling
- osmnx and networkx for street and public transport network analysis
- 'statsmodels', scikit-learn, econML, scipy, and pulp for modelling and prediction
- matplotlib and pyDeck for visualisation
- Github for source control
Domain-specific knowledge (e.g. data science, image processing)
