Installation

Asparagus Bundle is a package that depends majorly on Pytorch and the Atomic Simulation Environment (ASE). Other than that, it is designed to rely on just a few of packages and is written fully in Python without the need for compilation. We recommend that you use a virtual environment to install Asparagus.

Dependencies

Asparagus depends on the following packages, which will be (except for Python itself) automatically managed when installing Asparagus via pip or python setup.py install (see below):

  • Python \(\geq\) 3.8

  • ASE (Atomic Simulation Environment) \(\geq\) 3.22

  • PyTorch \(\geq\) 2.0

  • Torch-ema \(\geq\) 0.3

  • TensorBoard \(\geq\) 2.4

  • Numpy, Scipy, Pandas, Mathplotlib, Seaborn

Optional:

Setting up the environment

We recommend to use virtual environment sucha as mamba or miniconda.

In mamba, you can create a virtual enviroment called asparagus by

mamba create --name asparagus python=3.11

and activate the virtual environment by the command:

mamba activate asparagus

Note: If you are using Miniconda, just replace mamba by conda.

Install Asparagus

To install Asparagus first clone the repository:

git clone https://github.com/MMunibas/Asparagus.git

Then, go to the folder where you cloned the repository and install via pip:

pip install -e .

Alternatively, install via setup.py:

python setup.py install

BEWARE: With this command any modification that is done to the code in the folder asparagus will be automatically reflected in the modules that you import.