Test about some Compound phases in Sm-Fe-B.

[Hans540]

We are happy to quickly add any structure-informed model which is a plug-and-play addition to our infrastructure, which will generally mean it either:

• Utilizes already implemented representation, feature set, or its subset. Please check below as appropriate:

  • [ ] My model uses KS2022 or its subset.
  • [ ] My model uses ALIGNN graph representation.
  • [ ] My model is a refitting or a variation of CHGNet
  • [ ] My model is available from a public citable source like Zenodo (preferred) or figshare.
  • [ ] My model can be fetched within 30s, corresponding to ~2GB on Zenodo or 250MB on figshare.
  • [ ] My model can run single-threaded in under 500ms / structure
  • [ ] My model can run single-threaded in under 5s / structure

• Is a lightweight tool, which can be quickly installed and run. Please check below as appropriate:

  • [ ] My model is well maintained and has been used in past research.
  • [ ] My model is actively tested at least weekly and has been well-maintained for at least 6 months.
  • [ ] My model is available from a public citable source like Zenodo (preferred) or figshare.
  • [ ] My model can be fetched within 30s, corresponding to ~2GB on Zenodo or 250MB on figshare.
  • [ ] My model can run single-threaded in under 500ms / structure
  • [ ] My model can run single-threaded in under 5s / structure

If it does not fall into the above categories, please dont get discouraged and still let us know! It will be much more work on our side, but we will probably be happy to work with you. To get started on that, please explain it in a few sentences.

[github-actions[bot]]

Hello @Hans540! Please comment below on this issue while attaching a ZIP file with atomic structures (POSCAR/CIFs) to get started! You can put keywords describing it in the body of the comment.

As soon as you do it, your atomic structures will be processed through several tools, described below, and return a neat Markdown report.

• pySIPFENN framework, returning (1) array of descriptors (feature vectors) in Numpy .npy and CSV formats you can use for your ML modelling, alongside formation energy predictions.
• ALIGNN framework, returning (1) results from 7 ALIGNN models specified here and (2) compressed graph representation files.
• CHGNet model, returning (1) energy prediction for your input, (2) CHGNet-relaxed structures in the same format (POSCAR/CIF) as your input, and (3) energy prediction for the relaxed structures.

[Hans540]

[Uploading Sm-Fe-B.zip…]()

[github-actions[bot]]

😢 Your comment does not contain any direct links to ZIP files. Please note that certain cloud providers do not support that. Try to directly drag-and-drop into a comment.

[github-actions[bot]]

😢 I could not download the task ZIP file. Exiting now...

[Hans540]

Sm-Fe-B.zip

[github-actions[bot]]

👍 [1/3] I found the ZIP file linked in your comment. I will now attempt to download it and validate contents!

[github-actions[bot]]

👍 [2/3] I received your files and extracted them! Now, I will set up the calculation environment and run: pySIPFENN, CHGNet, and ALIGNN. You can now have A coffee and wait for results. Obtaining results should take at least a couple of minutes.

[amkrajewski]

Hi @Hans540 these seems to be an issue with your CIF files not being able to be read by neither pymatgen nor jarvis.

pymatgen:

Importing structures...
  0%|          | 0/4 [00:00<?, ?it/s]/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pymatgen/io/cif.py:213: UserWarning: Possible issue in CIF file at line: P42/mnm
  warnings.warn(f"Possible issue in CIF file at line: {issue}")
Traceback (most recent call last):
  File "/Users/runner/work/MPDD-X/MPDD-X/featurization/pysipfenn-minimal.py", line 12, in <module>
    c.runFromDirectory('structures', 'KS2022', 'serial')
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pysipfenn/core/pysipfenn.py", line 921, in runFromDirectory
    structList = [Structure.from_file(f'{directory}/{eif}') for eif in tqdm(self.inputFiles)]
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pysipfenn/core/pysipfenn.py", line 921, in <listcomp>
    structList = [Structure.from_file(f'{directory}/{eif}') for eif in tqdm(self.inputFiles)]
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pymatgen/core/structure.py", line 2937, in from_file
    return cls.from_str(contents, fmt="cif", primitive=primitive, sort=sort, merge_tol=merge_tol, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pymatgen/core/structure.py", line 2847, in from_str
    struct = parser.parse_structures(primitive=primitive)[0]
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pymatgen/io/cif.py", line 1188, in parse_structures
    raise RuntimeError("remove the change of default primitive=True to False made on 2023-10-24")
RuntimeError: remove the change of default primitive=True to False made on 2023-10-24

jarvis:

File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/jarvis/core/atoms.py", line 340, in from_cif
    lines = f.read().splitlines()
            ^^^^^^^^
  File "<frozen codecs>", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd5 in position 846: invalid continuation byte

[Hans540]

Sm-Fe-B(1).zip

[github-actions[bot]]

👍 [1/3] I found the ZIP file linked in your comment. I will now attempt to download it and validate contents!

[github-actions[bot]]

👍 [2/3] I received your files and extracted them! Now, I will set up the calculation environment and run: pySIPFENN, CHGNet, and ALIGNN. You can now have A coffee and wait for results. Obtaining results should take at least a couple of minutes.

[github-actions[bot]]

🚀 [3/3] All Done! Your submission and all results been persisted under contrib.mpdd.org/f3b72430. For results, please see the table below:

pySIPFENN:	name	SIPFENN_NN30-OQMD [eV/atom]
Sm2Fe14B.POSCAR	-0.0568
Sm5Fe2B6.POSCAR	0.3408
SmFe4B4.POSCAR	-0.3881
SmFeB4.POSCAR	-0.4936

ALIGNN:	name	ALIGNN-JARVIS Formation Energy [eV/atom]	ALIGNN-JARVIS MBJ Bandgap [eV]	ALIGNN-JARVIS Shear Modulus [GPa]	ALIGNN-JARVIS Bulk Modulus [GPa]	ALIGNN-JARVIS Exfoliation Energy [meV/atom]	ALIGNN-MP Formation Energy [eV/atom]	ALIGNN-MP PBE Bandgap [eV]
Sm2Fe14B.POSCAR	-0.0366	-0.0345	29.6276	129.9217	383.9913	-0.0738	0.0088
Sm5Fe2B6.POSCAR	0.7372	0.0003	46.7717	63.3542	154.6127	0.1532	0.016
SmFe4B4.POSCAR	-0.3926	-0.0016	85.6641	175.8087	139.6198	-0.4272	0.0124
SmFeB4.POSCAR	-0.5379	0.0424	165.34	201.7846	44.0713	-0.545	0.0009

CHGNet:

Please note that these are energies, not formation energies.	Name	CHGNet_0.3.0-MP Energy [eV/atom]	CHGNet_0.3.0-MP Relaxed Energy [eV/atom]
Sm2Fe14B.POSCAR	-7.9626	-7.9632
Sm5Fe2B6.POSCAR	-4.928	-5.2824
SmFe4B4.POSCAR	-7.5239	-7.6733
SmFeB4.POSCAR	-7.1706	-7.1914

For the next 30 days, you can also download other results like pySIPFENN's raw descriptor data Numpy array and CHGNet-relaxed structure files under Artifact tab here Enjoy!