PropertyDatasetBase

class hdnnpy.dataset.property.property_dataset_base.PropertyDatasetBase(order, structures)

Bases: abc.ABC

Base class of atomic structure based property dataset.

Common instance variables for property datasets are initialized.

Parameters:

• order (int) – Derivative order of property to calculate.
• structures (list [AtomicStructure]) – Properties are calculated for these atomic structures.

__getitem__(item)

Return property data this instance has.

If item is string, it returns corresponding property. Available keys can be obtained by properties attribute. Otherwise, it returns a list of property sliced by item.

__len__()

Number of atomic structures given at initialization.

calculate_properties(structure)

Calculate required properties for a structure data.

This is abstract method. Subclass of this base class have to override.

Parameters:structure (AtomicStructure) – A structure data to calculate properties. Returns:Calculated properties. The length is the same as order given at initialization. Return type:list [ndarray]

clear()

Clear up instance variables to initial state.

load(file_path, verbose=True, remake=False)

Load dataset from .npz format file.

Only root MPI process load dataset.

It validates following compatibility between loaded dataset and atomic structures given at initialization.

• length of data
• elemental composition
• elements
• tag

It also validates that loaded dataset satisfies requirements.

• order

Parameters:

• file_path (Path) – File path to load dataset.
• verbose (bool, optional) – Print log to stdout.
• remake (bool, optional) – If loaded dataset is lacking in any property, recalculate dataset from scratch and overwrite it to file_path. Otherwise, it raises ValueError.

Raises:

• AssertionError – If loaded dataset is incompatible with atomic structures given at initialization.
• ValueError – If loaded dataset is lacking in any property and remake=False.

make(verbose=True)

Calculate & retain property dataset

It calculates property dataset by data-parallel using MPI communication.

The calculated dataset is retained in only root MPI process.

Each property values are divided by COEFFICIENTS which is unique to each property dataset class.

Parameters:verbose (bool, optional) – Print log to stdout.

save(file_path, verbose=True)

Save dataset to .npz format file.

Only root MPI process save dataset.

Parameters:

• file_path (Path) – File path to save dataset.
• verbose (bool, optional) – Print log to stdout.

Raises:

RuntimeError – If this instance do not have any data.

COEFFICIENTS = []

Coefficient values of each properties.

Type:list [float]

PROPERTIES = []

Names of properties for each derivative order.

Type:list [str]

UNITS = []

Units of properties for each derivative order.

Type:list [str]

coefficients

Coefficient values this instance have.

Type:list [float]

elemental_composition

Elemental composition of atomic structures given at initialization.

Type:list [str]

elements

Elements of atomic structures given at initialization.

Type:list [str]

has_data

True if success to load or make dataset, False otherwise.

Type:bool

n_property = None

Number of dimensions of 0th property.

Type:int

name = None

Name of this property class.

Type:str

order

Derivative order of property to calculate.

Type:int

properties

Names of properties this instance have.

Type:list [str]

tag

Unique tag of atomic structures given at initialization.

Usually, it is a form like <any prefix> <chemical formula>. (ex. CrystalGa2N2)

Type:str

units

Units of properties this instance have.

Type:list [str]