Add Kenya (KEN) data and experiment configs for hydra

[robknapen]

What does this PR do?

Add Kenya (KEN) Hydra configs for yield Africa experiments

Implementations
Adds data and experiment configs to run yield Africa models restricted to Kenya (2017–2020), as a country-level subset complementing the existing all-Africa and LOCO configs.

Data configs (configs/data/):

• yield_africa_KEN.yaml — tabular/coords-only datamodule, random 70/15/15 split, countries filtered to ["KEN"]
• yield_africa_tessera_KEN.yaml — same but with TESSERA modality (9-pixel tiles, per-record year)

Experiment configs (configs/experiment/):

• yield_africa_tabular_KEN.yaml — tabular-only model (yield_tabular_reg) on Kenya data, 150 epochs
• yield_africa_tessera_reg_KEN.yaml — TESSERA-only model (yield_tessera_reg) on Kenya data
• yield_africa_tessera_fusion_KEN.yaml — TESSERA + tabular fusion (yield_tessera_fusion_reg) on Kenya data; includes notes on required preprocessing steps (TESSERA tile fetch, LOCO split generation) and how to swap the held-out country

Usage
python src/train.py experiment=yield_africa_tabular_KEN
python src/train.py experiment=yield_africa_tessera_reg_KEN
python src/train.py experiment=yield_africa_tessera_fusion_KEN

Before submitting

• Did you make sure title is self-explanatory and the description concisely explains the PR?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you list all the breaking changes introduced by this pull request?
• Did you test your PR locally with pytest command?