pypolymlp 0.3.3

This is the pypolymlp module.

A generator of polynomial machine learning potentials

Polynomial machine learning potentials

• Polynomial machine learning potential repository
• A. Seko, J. Appl. Phys. 133, 011101 (2023)

Required libraries and python modules

• python >= 3.9
• numpy < 2.0.0
• scipy
• pyyaml
• setuptools
• eigen3
• pybind11
• openmp (recommended)
• phonopy (if using phonon datasets and/or computing force constants)
• phono3py (if using phonon datasets and/or computing force constants)
• symfc (if computing force constants)
• spglib (optional)

How to install pypolymlp

• Install from conda-forge: Coming soon.

• Install from PyPI

conda create -n pypolymlp-env
conda activate pypolymlp-env
conda install -c conda-forge numpy scipy pybind11 eigen cmake cxx-compiler
pip install pypolymlp

• Install from GitHub

git clone https://github.com/sekocha/pypolymlp.git
cd pypolymlp
conda create -n pypolymlp-env
conda activate pypolymlp-env
conda install -c conda-forge numpy scipy pybind11 eigen cmake cxx-compiler
pip install . -vvv

Building C++ codes in pypolymlp may require a significant amount of time.

How to use pypolymlp

• Polynomial MLP development
• Property calculators
  • Energy, forces on atoms, and stress tensor
  • Force constants
  • Elastic constants
  • Equation of states
  • Structural features (Polynomial invariants)
  • Local geometry optimization
  • Phonon properties, Quasi-harmonic approximation
  • Self-consistent phonon calculations
• Utilities
  • Random structure generation
  • Estimation of computational costs
  • Enumeration of optimal MLPs
  • Compression of vasprun.xml files
  • Automatic division of DFT dataset
  • Atomic energies
• Python API (MLP development)
• Python API (Property calculations)