pyiron_contrib.atomistics.ml.potentialfit module
Abstract base class for fitting interactomic potentials.
- class pyiron_contrib.atomistics.ml.potentialfit.PotentialFit[source]
Bases:
ABC
Abstract mixin that defines a general interface to potential fitting codes.
Training data can be added to the job with :method:`~.add_training_data`. This should be atom structures with (at least) corresponding energies and forces, but additional (per structure or atom) maybe added. Subclasses of
TrainingContainer
that define and handle such data are explicitly allowed.:property:`~.training_data` and :property:`~.predicted_data` can be used to access the initial training data and the predicted data on them after the fit.
- add_training_data(container: TrainingContainer) None [source]
Add data to the fit.
Calling this multiple times appends data to internal storage.
- Parameters
container (
TrainingContainer
) – container holding data to fit
- abstract get_lammps_potential() DataFrame [source]
Return a pyiron compatible dataframe that defines a potential to be used with a Lammps job (or subclass thereof).
- Returns
contains potential information to be used with a Lammps job.
- Return type
DataFrame
- property plot
Plots correlation and (training) error histograms.
- property predicted_data: FlattenedStorage
Predicted properties of the training data after the fit.
In contrast to :property:`~.training_data` this may not contain the original atomic structures, but must be in the same order. Certain properties in the training data may be omitted from this data set, if the inconvenient or impossible to predict. This should be documented on the subclass for each specific code.
- Returns
- container holding all predictions of the fitted potential on the
training data
- Return type
pyiron_base.FlattenedStorage
- property training_data: TrainingStorage
Return all training data added so far.
- Returns
container holding all training data
- Return type
pyiron_contrib.atomistics.atomistics.job.trainingcontainer.TrainingStorage