Metadata-Version: 2.4
Name: agat
Version: 9.1.1
Summary: Atomic Graph ATtention networks for predicting atomic energies and forces.
Home-page: https://github.com/jzhang-github/AGAT
Author: ZHANG Jun; ZHAO Shijun
Author-email: j.zhang@my.cityu.edu.hk
License: GPL
Platform: all
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: GNU General Public License (GPL)
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Natural Language :: English
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: ase
Requires-Dist: tqdm
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: platform
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary


# AGAT (Atomic Graph ATtention networks)
[![GitHub](https://img.shields.io/github/license/jzhang-github/AGAT)](https://github.com/jzhang-github/AGAT/blob/main/LICENSE)
[![Pypi](https://img.shields.io/pypi/v/agat.svg)](https://pypi.org/project/agat/)
[![PyPI - Downloads](https://img.shields.io/pypi/dm/agat)](https://pypi.org/project/agat/)
[![PyPI - Wheel](https://img.shields.io/pypi/wheel/agat)](https://pypi.org/project/agat/)

<!--
[![Documentation Status](https://readthedocs.org/projects/agat/badge/?version=latest)](https://jzhang-github.github.io/AGAT/)
-->

  <br>  <br>  ![Model architecture](files/architecture.svg)

# Using AGAT
The [documentation](https://jzhang-github.github.io/AGAT/) of AGAT API is available.

# Installation

### Install with [conda](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) environment

- Download the [`agat_linux_gpu_cu124.yml`](agat_linux_gpu_cu124.yml) file.

- Run

  ```shell
  conda env create -f agat_linux_gpu_cu124.yml
  ```

  

- Install CUDA and CUDNN [**Optional**].
  
  - For HPC, you may load CUDA by checking `module av`, or you can contact your administrator for help.
  - [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads)
  - [cuDNN](https://developer.nvidia.com/cudnn)



- More installation options: [**Customized installation**](Customized_installation.md)



# Quick start

### Prepare VASP calculations

Run VASP calculations at this step.

### Collect paths of VASP calculations

- We provided examples of VASP outputs at [VASP_calculations_example](https://github.com/jzhang-github/AGAT/tree/v1.0.0/files/VASP_calculations_example).   

- Find all directories containing `OUTCAR` file:   

  ```
  find . -name OUTCAR > paths.log
  ```

- Remove the string 'OUTCAR' in `paths.log`.   

  ```
  sed -i 's/OUTCAR$//g' paths.log
  ```

- Specify the absolute paths in `paths.log`.   

  ```
  sed -i "s#^.#${PWD}#g" paths.log
  ```

### Build database

```python
from agat.data import BuildDatabase
if __name__ == '__main__':
    database = BuildDatabase(mode_of_NN='ase_dist', num_of_cores=16)
    dataset = database.build()
```

### Train AGAT model

```python
from agat.model import Fit
f = Fit()
f.fit()
```

### Application (geometry optimization)

```python
from ase.optimize import BFGS
from ase.io import read
from agat.app import AgatCalculator

model_save_dir = 'agat_model'
graph_build_scheme_dir = 'dataset'

atoms = read('POSCAR')
calculator=AgatCalculator(model_save_dir,
                          graph_build_scheme_dir)
atoms = Atoms(atoms, calculator=calculator)
dyn = BFGS(atoms, trajectory='test.traj')
dyn.run(fmax=0.05)
```

### Application (high-throughput prediction)

```python
from agat.app.cata import HtAds

model_save_dir = 'agat_model'
graph_build_scheme_dir = 'dataset'
formula='NiCoFePdPt'

ha = HtAds(model_save_dir=model_save_dir, graph_build_scheme_dir=graph_build_scheme_dir)
ha.run(formula=formula)
```



### Tips:

See [API doc](https://jzhang-github.github.io/AGAT/API_Docs.html) for more details. For example:

- Manipulating `agat.dataset`: 
- AGAT molecular dynamics simulations:
- More options for controlling the AGAT training process: [docs/sphinx/source/Default parameters.md](https://github.com/jzhang-github/AGAT/blob/main/docs/sphinx/source/Default%20parameters.md).

<!--
[![Documentation Status](https://readthedocs.org/projects/agat/badge/?version=latest)](https://jzhang-github.github.io/AGAT/)
-->


### Some default parameters
[agat/default_parameters.py](agat/default_parameters.py); Explanations: [docs/sphinx/source/Default parameters.md](https://github.com/jzhang-github/AGAT/blob/main/docs/sphinx/source/Default%20parameters.md).



# Package structure

![Model architecture](files/Package.svg)



# Change log  

Please check [Change_log.md](https://github.com/jzhang-github/AGAT/blob/main/Change_log.md)
