Energy response#523
Conversation
…or an explicit list.
ElliottKasoar
added
the
new benchmark
| data_path = download_github_data( | ||
| filename="LINEAR_CARBON_wB97M-V.zip", | ||
| github_uri="https://github.com/viktorsvahn/teoroo_ML-PEG/raw/refs/heads/main/data/source", | ||
| ) |
There was a problem hiding this comment.
woudl you like us to uplaod this to the s3 bucket or are you happy with this download?
| Total MAE: | ||
| good: 0.01 | ||
| bad: 5.0 | ||
| unit: eV |
There was a problem hiding this comment.
should these units be eV or kJ/mol?
| bad: 5.0 | ||
| unit: eV | ||
| tooltip: "Mean Absolute Error for all systems" | ||
| level_of_theory: wB97V-M |
There was a problem hiding this comment.
should this end in V not M? like stated in the calc file
| _ = mol.get_potential_energy() | ||
|
|
||
| mol_name = str(mol.get_chemical_formula()) | ||
| mol_dir = APP_ROOT / f"data/electric_field/energy_response/{model_name}" |
There was a problem hiding this comment.
we should avoid writing directory to the app data in the calc script. usually we do this in the analysis step which does often duplicate files, but keeps everything modular
|
Hi @viktorsvahn thanks for the PR, looking really nice so far! a few initial points:
|
|
Hi @viktorsvahn, just wanted to check in and see if there's anything we can do to help? In addition to the above comments, please can you take a look at our new filtering guidelines: https://ddmms.github.io/ml-peg/developer_guide/filter.html The principles are relatively simple, but you do have to be a little careful, so again, if anything is unclear, please do ask! (You'll need to rebase to test this) |
|
Sorry for taking so long. I am currently on it and I will look at the new guidelines as well! |
3 participants
Pre-review checklist for PR author
Summary
Energy response of linear organic molecules of varying chain length to an external electrical field.
Linked issue
#433
Progress
Testing
mace-mp-0b3
mace-polar-1-s
New decorators/callbacks
N/A