Embedding factory script looping through each MGRS tile

[weiji14]

Jupyter notebook script to generate GeoParquet embedding files on a per MGRS tile basis.

Steps:

1. The script first generates an mgrs_world.txt file with a list of MGRS code names like 12ABC. Need to run this command first:

   aws s3 ls s3://clay-tiles-02/02/ | tr -s ' ' |  cut -d ' ' -f 3 | cut -d '/' -f 1 > mgrs_world.txt

2. A for-loop then goes through each MGRS tile, with the model running the prediction to generate GeoParquet files that are uploaded to s3.

Notes:

• There were about 947019 rows of embeddings generated from the clay-small-70MT-1100T-10E.ckpt model checkpoint in Dec 2023.
• Embeddings were generated using a g5.4xlarge EC2 instance with 1 NVIDIA A10G GPU that allows for bfloat16 dtype calculations.

Closes #120

[yellowcap]

This is out of date I think. Feel free to reopen if appropriate.