build_dataset¶

The high-level API in this script is BuildDatabase.

For example:

database = BuildDatabase()
database.build()

See https://jzhang-github.github.io/AGAT/Tutorial/Build_database.html for more info.

class CrystalGraph(object)¶

Read structural file and return a graph.

Caution

The constructed crystal graph may be unreasonable for high-entropy materials, if the connections are analyzed by Voronoi method.

Code example:

from Crystal2raph import CrystalGraph
cg = CrystalGraph(cutoff = 6.0, mode_of_NN='distance', adsorbate=True)
cg.get_graph('POSCAR')

Hint

Although we recommend representing atoms with one hot code, you can use the another way with: self.all_atom_feat = get_atomic_features()

Hint

In order to build a reasonable graph, a samll cell should be repeated. One can modify “self._cell_length_cutoff” for special needs.

Hint

We encourage you to use ase module to build crystal graphs. The pymatgen module needs some dependencies that conflict with other modules.

__init__(self, **data_config)¶

param **data_config:

Configuration file for building database. See https://jzhang-github.github.io/AGAT/Default%20parameters.html#default-data-config for the detailed info.

type **data_config:

str/dict

return:

A DGL.graph.

rtype:

DGL.graph.

Hint

Mode of how to get the neighbors, which can be:

'voronoi': consider Voronoi neighbors only.

'pymatgen_dist': build graph based on a constant distance using pymatgen module.

'ase_dist': build graph based on a constant distance using ase module.

'ase_natural_cutoffs': build graph from ase which has a dynamic cutoff scheme. In this case, the cutoff is deprecated because ase will use the dynamic cutoffs in ase.neighborlist.natural_cutoffs().

Parameters:: adsorbate (bool) – Identify the adsorbate or not.

get_adsorbate_bool(self, element_list)¶

Identify adsorbates based on elements： H and O.

Parameters:: element_list (list) – a list of element symbols.
Returns:: a list of bool values.
Return type:: torch.tensor

get_crystal(self, crystal_fpath, super_cell=True)¶

Read structural file and return a pymatgen crystal object.

Parameters:

crystal_fpath (str) – the path to the crystal structural.
super_cell (bool) – repeat the cell or not.

Returns:

a pymatgen structure object.

Return type:

pymatgen.core.structure.

get_1NN_pairs_voronoi(self, crystal)¶

The get_connections_new() of VoronoiConnectivity object is modified.

Parameters:

crystal (pymatgen.core.structure) – a pymatgen structure object.

Returns:

index of senders
index of receivers
a list of distance between senders and receivers

get_1NN_pairs_distance(self, crystal)¶

Find the index of senders, receivers, and distance between them based on the distance_matrix of pymargen crystal object.

Parameters:

crystal (pymargen.core.structure) – pymargen crystal object

Returns:

index of senders
index of receivers
a list of distance between senders and receivers

get_1NN_pairs_ase_distance(self, ase_atoms)¶

Parameters:

ase_atoms (ase.atoms) – ase.atoms object.

Returns:

index of senders
index of receivers
a list of distance between senders and receivers

get_ndata(self, crystal)¶

Parameters:: crystal (pymargen.core.structure) – a pymatgen crystal object.
Returns:: ndata: the atomic representations of a crystal graph.
Return type:: numpy.ndarray

get_graph_from_ase(self, fname, include_forces=False)¶

Build graphs with ase.

Parameters:

fname (str/ase.Atoms) – File name or ase.Atoms object.
include_forces (bool) – Include forces into graphs or not.

Returns:

A bidirectional graph with self-loop connection.

get_graph_from_pymatgen(self, crystal_fname, super_cell=True, include_forces=False)¶

Build graphs with pymatgen.

Parameters:

crystal_fname (str) – File name.
super_cell (bool) – repeat small cell or not.
include_forces (bool) – Include forces into graphs or not.

Returns:

A bidirectional graph with self-loop connection.

get_graph(self, crystal_fname, super_cell=False, include_forces=True)¶

This method can choose which graph-construction method is used, according to the mode_of_NN attribute.

Hint

You can call this method to build one graph.

Parameters:

crystal_fname (str) – File name.
super_cell (bool) – repeat small cell or not.
include_forces (bool) – Include forces into graphs or not.

Returns:

A bidirectional graph with self-loop connection.

class ReadGraphs¶

This object is used to build a list of graphs.

__init__(self, **data_config)¶

Parameters:

**data_config (dict) –

Configuration file for building database. See https://jzhang-github.github.io/AGAT/Default%20parameters.html#default-data-config for the detailed info.

Hint

Mode of how to get the neighbors, which can be:

'voronoi': consider Voronoi neighbors only.
'pymatgen_dist': build graph based on a constant distance using pymatgen module.
'ase_dist': build graph based on a constant distance using ase module.
'ase_natural_cutoffs': build graph from ase which has a dynamic cutoff scheme. In this case, the cutoff is deprecated because ase will use the dynamic cutoffs in ase.neighborlist.natural_cutoffs().

read_batch_graphs(self, batch_index_list, batch_num)¶

Read graphs with batches.

Note

The loaded graphs are saved under the attribute of dataset_path.

Parameters:

batch_index_list (list) – a list of graph index.
batch_num (str) – number the graph batches.

read_all_graphs(self, scale_prop=False, ckpt_path='.')¶

Read all graphs specified in the csv file.

Note

The loaded graphs are saved under the attribute of dataset_path.

Danger

Do not scale the label if you don’t know what are you doing.

Parameters:

scale_prop (bool) – scale the label or not. DO NOT scale unless you know what you are doing.
ckpt_path (str) – checkpoint directory of the well-trained model.

Returns:

graph_list： a list of DGL graph.
graph_labels： a list of labels.

class TrainValTestSplit(object)¶: Split the dataset.

Note

This object is deprecated.

class ExtractVaspFiles(object)¶

Extract VASP outputs for building AGAT database.

Parameters:: data_config['dataset_path'] (str) – Absolute path where the collected data to save.

Note

Always save the property per node as the label. For example: energy per atom (eV/atom).

__init__(self, **data_config)¶

Parameters:

**data_config (dict) –

Configuration file for building database. See https://jzhang-github.github.io/AGAT/Default%20parameters.html#default-data-config for the detailed info.

read_oszicar(self, fname='OSZICAR')¶

Get the electronic steps of a VASP run.

Parameters:: fname (str, optional) – file name, defaults to ‘OSZICAR’
Returns:: electronic steps of a VASP run.
Return type:: list

split_output(self, process_index)¶

Parameters:: process_index (int.) – A number to index the process.

__call__(self)¶: The __call__ function

class BuildDatabase¶

Build a database. Detailed information: https://jzhang-github.github.io/AGAT/Tutorial/Build_database.html

__init__(self, **data_config)¶

Parameters:

**data_config (dict) –

Configuration file for building database. See https://jzhang-github.github.io/AGAT/Default%20parameters.html#default-data-config for the detailed info.

build(self)¶: Run the construction process.

concat_graphs(*list_of_bin)¶

Concat binary graph files.

Parameters:

*list_of_bin –

input file names of binary graphs.

Returns:

A new file is saved to the current directory: concated_graphs.bin.

Return type:

None. A new file.

Example:

concat_graphs('graphs1.bin', 'graphs2.bin', 'graphs3.bin')