Cross-country rollouts

[tm-jace-peralta]

What does this PR contain?

Output for https://github.com/thinkingmachines/unicef-ai4d-poverty-mapping/issues/130, https://github.com/thinkingmachines/unicef-ai4d-poverty-mapping/issues/131, https://github.com/thinkingmachines/unicef-ai4d-poverty-mapping/issues/132, https://github.com/thinkingmachines/unicef-ai4d-poverty-mapping/issues/133

• Adds folders for each country: Vietnam (vn), Thailand (tl), Malaysia (my), Laos (la)
• Adds notebooks for generating the populated grids 2_*_generate_grids.ipynb and rolling out the cross-country model over this grid 3_*_rollout_model.ipynb.

The final output of these notebooks contain (1) the predicted relative wealth index and (2) binned wealth category from A-E

Notes on rollout runs

• These are the region variable names used per country

~~	Country	Region variable value
Vietnam	“viet nam”
Thailand	“thailand”
Malaysia	“malaysia”
Laos	"lao people's democratic republic"	~~

• Added standard country name lookup dicts for iso3.py and hdx.py. All *_generate grids.ipynb can now take common country names, e.g. "vietnam","laos".

  • First time runtimes This can vary based on machine specs and time of run (due to server capacity of the source datasets)

Country	N grids	Grid generation	Feature generation
Vietnam	50880	10 mins	110 mins
Thailand	78254	15 mins	89 mins
Malaysia	30202	27 mins	20 mins
Laos	50880	8 mins	24 mins

• Removed all of the output of the cells with .explore in all 3_*_rollout_model.ipynb notebooks to reduce overall repo memory consumption. An accompanying screenshot of what is expected after .explore is ran was provided instead.

• Modifications to povertymapping/iso3.py Added country ISO standard name lookup https://github.com/thinkingmachines/unicef-ai4d-poverty-mapping/blob/b2c85028869017c6be58e38a66e53b8ceca53e1b/povertymapping/iso3.py#L18-L19

• Modifications to povertymapping/osm.py Added country osm standard name lookup https://github.com/thinkingmachines/unicef-ai4d-poverty-mapping/blob/b2c85028869017c6be58e38a66e53b8ceca53e1b/povertymapping/osm.py#L204-L206

[review-notebook-app[bot]]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[tm-jace-peralta]

Added standard country name lookup dicts for iso3.py and hdx.py. All *_generate grids.ipynb can now take in the common country name, e.g. "vietnam","laos"