Skip to main content

pySIPFENN

GitHub top language PyPI - Python Version PyPI PyPI - Downloads

stable latest License: LGPL v3

Partial Test Full Test codecov

GitHub last commit (by committer) GitHub Release Date - Published_At GitHub commits since tagged version GitHub issues

DOI DOI

Major News

  • (v0.13.0) Model exports are now effortless the new pysipfenn.core.modelExporters module, which also allows users to reduce models to FP16 precision or simplify model structure. It supports ONNX, PyTorch, and CoreML formats. The latter allows use of highly efficient Neural Engine on all modern Apple devices. Note that to use these features, you need to install additional dependencies with pip install pysipfenn[dev].
  • (v0.12.2) The license has been changed to LGPLv3 to allow for integration with proprietary software developed by CALPHAD community, while supporting the development of new pySIPFENN features for all users. Many thanks to our colleagues from GTT-Technologies and other participants of 50th CALPHAD 2023 conference in Boston for fruitful discussions.
  • (v0.12.0) Official Python 3.11 support.
  • (March 2023 Workshop) We would like to thank all of our amazing attendees for making our workshop, co-organized with the Materials Genome Foundation, such a success! Over 100 of you simultaneously followed all exercises and, at the peak, we loaded over 1,200GB of models into the HPC's RAM. At this point, we would also like to acknowledge the generous support from IBM who funded the workshop. Please stay tuned for next workshops planned online and in-person at conferences. They will be announced both here and at the Materials Genome Foundation website.

Summary

This repository contains py(Structure-Informed Prediction of Formation Energy using Neural Networks) software package allowing efficient predictions of the energetics of atomic configurations. The underlying methodology and implementation is given in

  • Adam M. Krajewski, Jonathan W. Siegel, Jinchao Xu, Zi-Kui Liu, Extensible Structure-Informed Prediction of Formation Energy with improved accuracy and usability employing neural networks, Computational Materials Science, Volume 208, 2022, 111254 https://doi.org/10.1016/j.commatsci.2022.111254

While functionalities are similar to the software released along the paper, this package contains improved methods for featurizing atomic configurations. Notably, all of them are now written completely in Python, removing reliance on Java and making extensions of the software much easier thanks to improved readability. A fuller description of capabilities is given in documentation at https://pysipfenn.org and at PSU Phases Research Lab webpage under https://phaseslab.com/sipfenn.

Applications

pySIPFENN is a very flexible tool that can, in principle, be used for the prediction of any property of interest that depends on an atomic configuration with very few modifications. The models shipped by default are trained to predict formation energy because that is what our research group is interested in; however, if one wanted to predict Poisson’s ratio and trained a model based on the same features, adding it would take minutes. Simply add the model in open ONNX format and link it using the models.json file, as described in the documentation.

Real-World Examples

In our line of work, pySIPFENN and the formation energies it predicts are usually used as a computational engine that generates proto-data for creation of thermodynamic databases (TDBs) using ESPEI (https://espei.org). The TDBs are then used through pycalphad (https://pycalphad.org) to predict phase diagrams and other thermodynamic properties.

Another of its uses in our research is guiding the Density Functional Theory (DFT) calculations as a low-cost screening tool. Their efficient conjunction then drives the experiments leading to discovery of new materials, as presented in these two papers:

  • Sanghyeok Im, Shun-Li Shang, Nathan D. Smith, Adam M. Krajewski, Timothy Lichtenstein, Hui Sun, Brandon J. Bocklund, Zi-Kui Liu, Hojong Kim, Thermodynamic properties of the Nd-Bi system via emf measurements, DFT calculations, machine learning, and CALPHAD modeling, Acta Materialia, Volume 223, 2022, 117448, https://doi.org/10.1016/j.actamat.2021.117448.

  • Shun-Li Shang, Hui Sun, Bo Pan, Yi Wang, Adam M. Krajewski, Mihaela Banu, Jingjing Li & Zi-Kui Liu, Forming mechanism of equilibrium and non-equilibrium metallurgical phases in dissimilar aluminum/steel (Al–Fe) joints. Nature Scientific Reports 11, 24251 (2021). https://doi.org/10.1038/s41598-021-03578-0

Install pySIPFENN

Installing pySIPFENN is simple and easy utilizing either PyPI package repository or cloning from GitHub. While not required, it is recommended to first set up a virtual environment using venv or Conda. This ensures that one of the required versions of Python (3.9+) is used and there are no dependency conflicts. If you have Conda installed on your system (see instructions at https://docs.conda.io/en/latest/miniconda.html), you can create a new environment with:

conda create -n pysipfenn-workshop python=3.9 jupyter
conda activate pysipfenn-workshop

And then simply install pySIPFENN from PyPI with

pip install pysipfenn

Alternatively, you can also install pySIPFENN in editable mode if you cloned it from GitHub like

git clone https://github.com/PhasesResearchLab/pySIPFENN.git

Or by downloading a ZIP file. Please note, this will by default download the latest development version of the software, which may not be stable. For a stable version, you can specify a version tag after the URL with --branch <tag_name> --single-branch.

Then, move to the pySIPFENN folder and install in editable (-e) mode

cd pySIPFENN
pip install -e .

Developer Install

If you want to utilize pySIPFENN beyond its core functionalities, for instance, to train new models on custom datasets or to export models in different formats or precisions, you need to install additional dependencies. This can be done by installing the dev extras with

pip install pysipfenn[dev]

Note: If you are using MacOS zsh shell, you may need to enclose the dev extras in quotes like pip install "pysipfenn[dev]" or pip install ".[dev]".

Metadata

Release files for pysipfenn 0.13.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pysipfenn 0.13.0
File Size Uploaded Provenance Actions
pysipfenn-0.13.0.tar.gz 139.3 kB Without provenance Details for pysipfenn-0.13.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for pysipfenn 0.13.0
File Interpreter ABI Platform Actions
pysipfenn-0.13.0-py3-none-any.whl Python 3 none any Details for pysipfenn-0.13.0-py3-none-any.whl

Total release size: 303.2 kB

Release files / pysipfenn-0.13.0.tar.gz

Download URL pysipfenn-0.13.0.tar.gz
Size 139.3 kB
Tags Source
SHA-256 checksum
How to use checksums
ffe1c8e773d147a98353d456566834a966c6d3fac8c02f95d2e62e45f75c3b71
BLAKE2b-256 checksum
How to use checksums
fda0b08b2376fd2785579947ad4f3d0ecab05903e3956282af5aee8c56bb8fa1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.16

Release files / pysipfenn-0.13.0-py3-none-any.whl

Download URL pysipfenn-0.13.0-py3-none-any.whl
Size 163.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b53d4eb07907f72e9c26fe80747ce76cecbb7d4940041f7f008b26006faa831a
BLAKE2b-256 checksum
How to use checksums
9770d3e58845aef72c328e24ef966f3c68adaf67cec6806bf01d77b3fabf1a85
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.16

Security for pysipfenn 0.13.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page