Installation¶
Stable release (recommended)¶
Most systems come with the default package manager for Python pip
already preinstalled. In that case, installing sgdml
is as simple as calling:
$ pip install sgdml
The sgdml
command-line interface can now be used from anywhere on the system:
$ sgdml all datasets/npz/ethanol.npz 200 1000 5000
Similarly, the sgdml
Python API is available to other programs across the whole system:
from sgdml.predict import GDMLPredict
gdml_predict = GDMLPredict(<model>)
Development version¶
The sGDML repository is available on GitHub, which can be browsed at: https://github.com/stefanch/sGDML
To install the latest development version, clone the whole repository with
$ git clone https://github.com/stefanch/sGDML.git
$ cd sGDML
… or just update your existing local copy using
$ git pull origin master
During development, it is convenient to install the package locally and simlink the files at the current location, so that all changes to those files become immediately available to other users of the package on your system:
$ pip install -e .
Note
Using the flag --user
, pip
installs the package to the current users’s home directory, instead of system-wide. This option might require you to update your system’s PATH
variable accordingly.
Optional dependencies¶
Some sgdml
functionality relies on third-party libraries that are not installed by default. These optional dependencies (or package extras) are specified during installation using the square bracket syntax
$ pip install sgdml[<optional>]
… or for local installs,
$ pip install -e .[<optional>]
Atomic Simulation Environment (ASE)¶
If you are interested in interfacing sgdml
with ASE (see our applications section for examples), use the ase
keyword:
$ pip install sgdml[ase]