History

Félix Dorn 43076bcbb1 old		2025-07-15 00:41:05 +02:00
..
analysis.ipynb	old	2025-07-15 00:41:05 +02:00
bck_estimates.csv	old	2025-07-15 00:41:05 +02:00
data_enrichment.ipynb	old	2025-07-15 00:41:05 +02:00
evaluate_llm_time_estimations.ipynb	old	2025-07-15 00:41:05 +02:00
legacy.ipynb	old	2025-07-15 00:41:05 +02:00
loss.py	old	2025-07-15 00:41:05 +02:00
onet_explorer_app.py	old	2025-07-15 00:41:05 +02:00
README.md	old	2025-07-15 00:41:05 +02:00
schema.txt	old	2025-07-15 00:41:05 +02:00
tasks_estimateable.csv	old	2025-07-15 00:41:05 +02:00
tasks_with_estimates.csv	old	2025-07-15 00:41:05 +02:00

Presentation

Notebooks

data enrichment - contains the code to gather things from the O*NET data, BLS's OEWS database (unused for now), Barnett's data...
prompt evaluation - the playground used to evaluate change in hyperparameters (system prompt, user prompt, schema, model...)
analysis - code to generate the graphs in the paper
legacy - if there are some missing pieces, it's worth looking in there.

To re-run everything, you need python and uv up and running, if you use have nix installed, run

nix develop .#impure

and then uv run ... as requested in the notebooks.

If some things are missing, email dorn@xfe.li, I'm usually reactive.

Copy .env.example to .env and fill in OPENAI_API_KEY. The total run and experiments cost less than <10$.