Generalize data creation for RSS workflow#397
Conversation
…ex into generalize_data_creation
…ex into generalize_data_creation
…ex into generalize_data_creation
…ex into generalize_data_creation
…ex into generalize_data_creation
|
The isolated atom maker has been added. Should we consider enabling the configuration of both |
|
@YuanbinLiu Great! It would be great to add it to the yaml. But we can also first merge this PR and do this subsequently. |
Bumps [numpydoc](https://github.com/numpy/numpydoc) from 1.8.0 to 1.9.0. - [Release notes](https://github.com/numpy/numpydoc/releases) - [Changelog](https://github.com/numpy/numpydoc/blob/main/RELEASE.rst) - [Commits](numpy/numpydoc@v1.8.0...v1.9.0) --- updated-dependencies: - dependency-name: numpydoc dependency-version: 1.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Pre commit update
Sounds good! |
update mace version
--- updated-dependencies: - dependency-name: myst-nb dependency-version: 1.3.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]>
--- updated-dependencies: - dependency-name: matgl dependency-version: 1.2.7 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
src/autoplex/data/common/jobs.py
Outdated
| converged = check_convergence_vasp(os.path.join(val, "vasprun.xml.gz")) | ||
|
|
||
| if converged: | ||
| if (has_vasp_output and converged) or has_ase_output: |
There was a problem hiding this comment.
Likely my fault but I just realized that it is probably rather
| if (has_vasp_output and converged) or has_ase_output: | |
| if has_vasp_output or has_ase_output: |
Bump matgl from 1.2.6 to 1.2.7
Bump myst-nb from 1.2.0 to 1.3.0
…ex into generalize_data_creation
|
Hi @YuanbinLiu , I am attaching a script that allows you to run the workflow with Quantum Espresso. You need to install qe, get some pseudopotentials (set the path correctly) and figure out the run command locally to test it. |
Hi @JaGeo, I had a quick check. All look good to me! Thank you! |
|
Awesome! Thank you @YuanbinLiu ! Merged! And ee can build upon the attached script to document the, so far, experimental support for other dft codes! |
Make ML potential-based training in the RSS workflow available. This will then also allow to extend towards other data generation mechanisms.