Skip to content
/ pydft Public

Python based localized-orbital Density Functional Theory code for educational purposes.

Notifications You must be signed in to change notification settings

ifilot/pydft

Repository files navigation

PyDFT

build build Anaconda-Server Badge PyPI License: GPL v3

Note

Python based Density Functional Theory code for educational purposes. The documentation of PyDFT can be found here.

Purpose

PyDFT is a pure-Python package for performing localized-orbital DFT calculations using Gaussian Type Orbitals. PyDFT currently supports LDA and PBE exchange-correlation functionals. The purpose of PyDFT is mainly to serve as an educational tool to explain the inner workings of a DFT calculation. This program is not intended for professional calculations. It is not particularly fast nor offers a lot of features that more mature open-source of commercial packages offer. It does offer a unique insight into a working code and a considerable effort was made in documenting everything.

Tip

Interested in other education quantum chemical codes? Have a look at the packages below.

  • PyQInt is a hybrid C++/Python (Cython) code for performing Hartree-Fock calculations. This code contains many relevant features, such a geometry optimization, orbital localization and crystal orbital hamilton population analysis.
  • HFCXX is a full C++ code for performing Hartree-Fock calculations.
  • DFTCXX is a full C++ code for performing Density Functional Theory Calculations.

Features

Numerical integration using Becke grids

Electron-electron interaction terms (both classical as well as exchange-correlation) are performed by means of extensive numerical integration schemes performed over so-called Becke grids. Utilizing these grids, molecular integrals are decomposed into series of weighted atomic integrals.

Becke grids

Molecular orbital visualization

PyDFT can be readily used alongside matplotlib to make figures of molecular orbitals or density fields.

Molecular orbitals of CO

Extensive output

Internal matrices, e.g. overlap or Hamiltonian matrix, are exposed to the user and can be readily visualized using specific matrix visualization routines.

Matrices

Installation

This code depends on a few other packages. To install this code and its dependencies, run the following one-liner from Anaconda prompt

conda install -c ifilot pydft pyqint pylebedev pytessel

Usage

Check the current version

import pydft
print(pydft.__version__)

Performing a simple calculation

from pydft import MoleculeBuilder, DFT

CO = MoleculeBuilder().get_molecule("CO")
dft = DFT(CO, basis='sto3g')
en = dft.scf(1e-4, verbose=True)
print("Total electronic energy: %f Ht" % en)

Community guidelines

License

Unless otherwise stated, all code in this repository is provided under the GNU General Public License version 3.

Languages