Remove the notebook builder script

CHANGELOG.md

@@ -16,7 +16,7 @@ versions of pandas (>= 2.2), GeoPandas (>= 1.0), scikit-learn and statsmodels.
   `osmnx.geocode_to_gdf` returning the raw city shape; `osmnx` is now a core
   dependency (the `osm` extra is kept, empty, for compatibility).
 - `examples/natal.ipynb`: an executed end-to-end walkthrough on Natal with
-  synthetic data, also rendered in the documentation.
+  synthetic data (executed, with outputs), also rendered in the documentation.
 - `PredictionPipeline.evaluate` accepts a list of scorings and returns a
   DataFrame (one CV pass for all metrics).
 - README section explaining the framework (thesis, Chapter 3, Figures 7-12);

CONTRIBUTING.md

@@ -36,11 +36,12 @@ mkdocs build --strict   # what CI runs
 
 Pushing to `master` deploys the site to GitHub Pages automatically. The home
 page is generated from `README.md` (see `docs/hooks/readme.py`), and the
-example notebook is rendered from `examples/natal.ipynb`; regenerate and
-re-execute it with:
+example notebook is rendered from `examples/natal.ipynb` with its stored
+outputs. After editing the notebook, re-execute it so the outputs stay in sync
+(it needs network access for `get_city_shape`):
 
 ```bash
-python examples/build_natal_notebook.py
+pip install -e ".[examples]"
 jupyter nbconvert --to notebook --execute --inplace examples/natal.ipynb
 ```