mpdd-alignn 1.0.0__tar.gz

mpdd-alignn-1.0.0/.github/workflows/publishToPyPI.yaml

@@ -0,0 +1,50 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "**"
+
+jobs:
+    release-build:
+      runs-on: ubuntu-latest
+  
+      steps:
+        - uses: actions/checkout@v4
+  
+        - uses: actions/setup-python@v4
+          with:
+            python-version: "3.10"
+
+        - name: Install dependencies
+          run: |
+            python -m pip install --upgrade pip
+            pip install build
+  
+        - name: build release distributions
+          run: |
+            python -m build
+  
+        - name: upload dists
+          uses: actions/upload-artifact@v4
+          with:
+            name: release-dists
+            path: dist/
+  
+    pypi-publish:
+      runs-on: ubuntu-latest
+      needs:
+        - release-build
+      permissions:
+        id-token: write
+  
+      steps:
+        - name: Retrieve release distributions
+          uses: actions/download-artifact@v4
+          with:
+            name: release-dists
+            path: dist/
+  
+        - name: Publish release distributions to PyPI
+          uses: pypa/gh-action-pypi-publish@release/v1
+  

mpdd-alignn-1.0.0/.gitignore

@@ -0,0 +1,135 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+graphs/**
+mpddtest/**
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# MacOS finder
+.DS_Store

mpdd-alignn-1.0.0/LICENSE.md

@@ -0,0 +1,49 @@
+The MIT License (MIT)
+
+Copyright (c) 2024 Adam M. Krajewski
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+Copyright (c) National Institute of Standards and Technology (NIST)
+
+This software was developed by employees of the [National Institute of
+Standards and Technology (NIST)](http://www.nist.gov/), an agency of the 
+Federal Government and is being made available as a public service.  Pursuant 
+to [title 17 United States Code Section 105](https://www.copyright.gov/title17/92chap1.html#105), 
+works of [(NIST)](http://www.nist.gov/) employees are not subject to
+copyright protection in the United States.  This software may be subject to
+foreign copyright.  Permission in the United States and in foreign
+countries, to the extent that [(NIST)](http://www.nist.gov/) may hold copyright, to use, copy,
+modify, create derivative works, and distribute this software and its
+documentation without fee is hereby granted on a non-exclusive basis,
+provided that this notice and disclaimer of warranty appears in all copies.
+
+THE SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY WARRANTY OF ANY KIND, EITHER
+EXPRESSED, IMPLIED, OR STATUTORY, INCLUDING, BUT NOT LIMITED TO, ANY
+WARRANTY THAT THE SOFTWARE WILL CONFORM TO SPECIFICATIONS, ANY IMPLIED
+WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND
+FREEDOM FROM INFRINGEMENT, AND ANY WARRANTY THAT THE DOCUMENTATION WILL
+CONFORM TO THE SOFTWARE, OR ANY WARRANTY THAT THE SOFTWARE WILL BE ERROR
+FREE. IN NO EVENT SHALL NIST BE LIABLE FOR ANY DAMAGES, INCLUDING, BUT NOT
+LIMITED TO, DIRECT, INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES, ARISING OUT
+OF, RESULTING FROM, OR IN ANY WAY CONNECTED WITH THIS SOFTWARE, WHETHER OR
+NOT BASED UPON WARRANTY, CONTRACT, TORT, OR OTHERWISE, WHETHER OR NOT
+INJURY WAS SUSTAINED BY PERSONS OR PROPERTY OR OTHERWISE, AND WHETHER OR
+NOT LOSS WAS SUSTAINED FROM, OR AROSE OUT OF THE RESULTS OF, OR USE OF, THE
+SOFTWARE OR SERVICES PROVIDED HEREUNDER.

mpdd-alignn-1.0.0/MANIFEST.in

@@ -0,0 +1,3 @@
+recursive-exclude alignn/examples *
+recursive-exclude alignn/tex *
+include alignn/examples/sample_data/POSCAR-JVASP-10.vasp

mpdd-alignn-1.0.0/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.1
+Name: mpdd-alignn
+Version: 1.0.0
+Summary: A version of the NIST-JARVIS ALIGNN optimized in terms of model performance and to some extent reliability, for large-scale deployments over the MPDD infrastructure by Phases Research Lab.
+Author-email: Adam Krajewski <ak@psu.edu>
+Project-URL: Research Page, https://phaseslab.com/mpdd
+Project-URL: Homepage, https://phaseslab.org
+Project-URL: OPTIMADE Access, https://optimade.mpdd.org
+Project-URL: Simple GUI, http://mpdd.org
+Project-URL: Bug Tracker, https://github.com/PhasesResearchLab/MPDD/issues
+Project-URL: ALIGNN, https://github.com/usnistgov/alignn
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Classifier: Topic :: Scientific/Engineering :: Physics
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: scipy>=1.11.0
+Requires-Dist: jarvis-tools>=2021.07.19
+Requires-Dist: torch==2.1.0
+Requires-Dist: dgl>=1.1.3
+Requires-Dist: spglib==2.0.2
+Requires-Dist: scikit-learn>=1.3.1
+Requires-Dist: matplotlib>=3.4.1
+Requires-Dist: tqdm>=4.60.0
+Requires-Dist: pandas>=1.2.3
+Requires-Dist: pydantic==1.8.1
+Requires-Dist: ruamel.yaml
+Requires-Dist: pysmartdl2
+Provides-Extra: full
+Requires-Dist: pytorch-ignite>=0.5.0.dev20221024; extra == "full"
+Requires-Dist: ase; extra == "full"
+Requires-Dist: flake8>=3.9.1; extra == "full"
+Requires-Dist: pycodestyle>=2.7.0; extra == "full"
+Requires-Dist: pydocstyle>=6.0.0; extra == "full"
+Requires-Dist: pyparsing<3,>=2.2.1; extra == "full"
+Requires-Dist: accelerate>=0.20.3; extra == "full"
+
+# MPDD - ALIGNN Calculator
+
+This tool is a modified version of the **NIST-JARVIS** [**`ALIGNN`**](https://github.com/usnistgov/alignn) optimized in terms of model performance and to some extent reliability, for large-scale deployments over the [**`MPDD`**](https://phaseslab.org/mpdd) infrastructure by Phases Research Lab.
+
+## Critical Changes
+
+Key modifications that were made here:
+- A set of models of interest has been selected and defined in [**`config.yaml`**](alignn/config.yaml) for consistency, readability, and easy tracking. These are the models which will be populating MPDD.
+- **Dependency optimizations for running models**, skipping by default installation of several packages needed only for training and auxiliary tasks. Full
+set can still be installed by `pip install "mpdd-alignn[full]"`.
+- The process of model fetching was far too slow using `pretrained.get_figshare_model()`; thus, we reimplemented it similar to [`pySIPFENN`](https://pysipfenn.org) by multi-threading connection to Figshare via `pysmartdl2` we maintain, and parallelize the process on per-model basis. **Model download is now 7 times faster**, fetching all 7 default models in 6.1 vs 41.4 seconds.
+- Optimized what is included in the built package. Now, its **package size is reduced 33.5 times**, from 21.7MB to 0.65MB.
+- Streamlined operation, where we can get results for a directory of POSCARS for all default models in just 3 quick lines
+    ```python
+    from alignn import pretrained
+    pretrained.download_default_models()
+    result = pretrained.run_models_from_directory('example.SigmaPhase', mode='serial')
+    ```
+
+    Which give us neat:
+
+    ```
+    [{
+        'ALIGNN-JARVIS Bulk Modulus [GPa]': 98.06883239746094,
+        'ALIGNN-JARVIS Exfoliation Energy [meV/atom]': 101.71208190917969,
+        'ALIGNN-JARVIS Formation Energy [eV/atom]': -1.1146986484527588,
+        'ALIGNN-JARVIS MBJ Bandgap [eV]': 0.5845542550086975,
+        'ALIGNN-JARVIS Shear Modulus [GPa]': 39.18968963623047,
+        'ALIGNN-MP Formation Energy [eV/atom]': -1.4002774953842163,
+        'ALIGNN-MP PBE Bandgap [eV]': 1.074204921722412,
+        'name': '9-Pb8O12.POSCAR'
+    },
+    {
+        'ALIGNN-JARVIS Bulk Modulus [GPa]': 194.2947540283203,
+        'ALIGNN-JARVIS Exfoliation Energy [meV/atom]': 362.1310729980469,
+        'ALIGNN-JARVIS Formation Energy [eV/atom]': 0.010236039757728577,
+        'ALIGNN-JARVIS MBJ Bandgap [eV]': 0.0064897798001766205,
+        'ALIGNN-JARVIS Shear Modulus [GPa]': 85.74588775634766,
+        'ALIGNN-MP Formation Energy [eV/atom]': -0.018119990825653076,
+        'ALIGNN-MP PBE Bandgap [eV]': -0.00551827996969223,
+        'name': '19-Fe4Ni26.POSCAR'
+    },
+    {
+        'ALIGNN-JARVIS Bulk Modulus [GPa]': 185.35687255859375,
+        'ALIGNN-JARVIS Exfoliation Energy [meV/atom]': 379.46417236328125,
+        'ALIGNN-JARVIS Formation Energy [eV/atom]': 0.10529126971960068,
+    ...
+    ```
+
+## ALIGNN Compatibility and Install
+
+In general, we tried to retain full compatibility with the original `ALIGNN`, so this should be a drop-in replacement. You have to simply:
+
+    pip install mpdd-alignn
+
+or (as recommended) clone this repository and
+
+    pip install -e .
+
+## Contributions
+
+Please direct all contributions to [the ALIGNN repository](https://github.com/usnistgov/alignn). We will be synching our fork with them every once in a while and can do it quickly upon reasonable request. 
+
+The only contributions we will accept here are:
+- Expanding the list of default models.
+- Performance improvements to our section of the code.

mpdd-alignn-1.0.0/README.md

@@ -0,0 +1,66 @@
+# MPDD - ALIGNN Calculator
+
+This tool is a modified version of the **NIST-JARVIS** [**`ALIGNN`**](https://github.com/usnistgov/alignn) optimized in terms of model performance and to some extent reliability, for large-scale deployments over the [**`MPDD`**](https://phaseslab.org/mpdd) infrastructure by Phases Research Lab.
+
+## Critical Changes
+
+Key modifications that were made here:
+- A set of models of interest has been selected and defined in [**`config.yaml`**](alignn/config.yaml) for consistency, readability, and easy tracking. These are the models which will be populating MPDD.
+- **Dependency optimizations for running models**, skipping by default installation of several packages needed only for training and auxiliary tasks. Full
+set can still be installed by `pip install "mpdd-alignn[full]"`.
+- The process of model fetching was far too slow using `pretrained.get_figshare_model()`; thus, we reimplemented it similar to [`pySIPFENN`](https://pysipfenn.org) by multi-threading connection to Figshare via `pysmartdl2` we maintain, and parallelize the process on per-model basis. **Model download is now 7 times faster**, fetching all 7 default models in 6.1 vs 41.4 seconds.
+- Optimized what is included in the built package. Now, its **package size is reduced 33.5 times**, from 21.7MB to 0.65MB.
+- Streamlined operation, where we can get results for a directory of POSCARS for all default models in just 3 quick lines
+    ```python
+    from alignn import pretrained
+    pretrained.download_default_models()
+    result = pretrained.run_models_from_directory('example.SigmaPhase', mode='serial')
+    ```
+
+    Which give us neat:
+
+    ```
+    [{
+        'ALIGNN-JARVIS Bulk Modulus [GPa]': 98.06883239746094,
+        'ALIGNN-JARVIS Exfoliation Energy [meV/atom]': 101.71208190917969,
+        'ALIGNN-JARVIS Formation Energy [eV/atom]': -1.1146986484527588,
+        'ALIGNN-JARVIS MBJ Bandgap [eV]': 0.5845542550086975,
+        'ALIGNN-JARVIS Shear Modulus [GPa]': 39.18968963623047,
+        'ALIGNN-MP Formation Energy [eV/atom]': -1.4002774953842163,
+        'ALIGNN-MP PBE Bandgap [eV]': 1.074204921722412,
+        'name': '9-Pb8O12.POSCAR'
+    },
+    {
+        'ALIGNN-JARVIS Bulk Modulus [GPa]': 194.2947540283203,
+        'ALIGNN-JARVIS Exfoliation Energy [meV/atom]': 362.1310729980469,
+        'ALIGNN-JARVIS Formation Energy [eV/atom]': 0.010236039757728577,
+        'ALIGNN-JARVIS MBJ Bandgap [eV]': 0.0064897798001766205,
+        'ALIGNN-JARVIS Shear Modulus [GPa]': 85.74588775634766,
+        'ALIGNN-MP Formation Energy [eV/atom]': -0.018119990825653076,
+        'ALIGNN-MP PBE Bandgap [eV]': -0.00551827996969223,
+        'name': '19-Fe4Ni26.POSCAR'
+    },
+    {
+        'ALIGNN-JARVIS Bulk Modulus [GPa]': 185.35687255859375,
+        'ALIGNN-JARVIS Exfoliation Energy [meV/atom]': 379.46417236328125,
+        'ALIGNN-JARVIS Formation Energy [eV/atom]': 0.10529126971960068,
+    ...
+    ```
+
+## ALIGNN Compatibility and Install
+
+In general, we tried to retain full compatibility with the original `ALIGNN`, so this should be a drop-in replacement. You have to simply:
+
+    pip install mpdd-alignn
+
+or (as recommended) clone this repository and
+
+    pip install -e .
+
+## Contributions
+
+Please direct all contributions to [the ALIGNN repository](https://github.com/usnistgov/alignn). We will be synching our fork with them every once in a while and can do it quickly upon reasonable request. 
+
+The only contributions we will accept here are:
+- Expanding the list of default models.
+- Performance improvements to our section of the code.

mpdd-alignn-1.0.0/alignn/__init__.py

@@ -0,0 +1,2 @@
+"""Version number."""
+__version__ = "2024.2.4"

mpdd-alignn-1.0.0/alignn/cli.py

@@ -0,0 +1,73 @@
+"""Ignite training cli."""
+
+import json
+import os
+import shutil
+from pathlib import Path
+
+# from typing import Any, Dict, Optional, Union
+from typing import Optional
+
+import torch
+import typer
+
+from alignn.config import TrainingConfig
+from alignn.profile import profile_dgl
+from alignn.train import train_dgl
+
+
+def cli(
+    config: Optional[Path] = typer.Argument(None),
+    progress: bool = False,
+    checkpoint_dir: Path = Path("/tmp/models"),
+    store_outputs: bool = False,
+    tensorboard: bool = False,
+    profile: bool = False,
+):
+    """ALIGNN training cli.
+
+    config: path to json config file (conform to TrainingConfig)
+    progress: enable tqdm console logging
+    tensorboard: enable tensorboard logging
+    profile: run profiling script for one epoch instead of training
+    """
+    model_dir = config.parent
+
+    if config is None:
+        model_dir = os.getcwd()
+        config = TrainingConfig(epochs=10, n_train=32, n_val=32, batch_size=16)
+
+    elif config.is_file():
+        model_dir = config.parent
+        with open(config, "r") as f:
+            config = json.load(f)
+            config = TrainingConfig(**config)
+
+    if profile:
+        profile_dgl(config)
+        return
+
+    hist = train_dgl(
+        config,
+        progress=progress,
+        checkpoint_dir=checkpoint_dir,
+        store_outputs=store_outputs,
+        log_tensorboard=tensorboard,
+    )
+
+    # print(model_dir)
+    # with open(model_dir / "metrics.json", "w") as f:
+    #     json.dump(hist, f)
+
+    torch.save(hist, model_dir / "metrics.pt")
+
+    with open(model_dir / "fullconfig.json", "w") as f:
+        json.dump(json.loads(config.json()), f, indent=2)
+
+    # move temporary checkpoint data into model_dir
+    for checkpoint in checkpoint_dir.glob("*.pt"):
+        shutil.copy(checkpoint, model_dir / checkpoint.name)
+
+
+if __name__ == "__main__":
+    typer.run(cli)