IterativeCompleteDFTvsMLBenchmarkWorkflow#

class autoplex.auto.phonons.flows.IterativeCompleteDFTvsMLBenchmarkWorkflow(name='IterativeCompleteDFTvsMLBenchmarkWorkflow', max_iterations=10, rms_max=0.2, complete_dft_vs_ml_benchmark_workflow_0=<factory>, complete_dft_vs_ml_benchmark_workflow_1=<factory>)[source]#

Bases: object

Iterative Version of CompleteDFTvsMLBenchmarkWorkflow.

Maker to run CompleteDFTvsMLBenchmarkWorkflow in an iterative fashion to ensure convergence of the potentials.

Parameters:
  • name (str) – Name of the flow produced by this maker.

  • max_iterations (int.) – Maximum number of iterations to run.

  • rms_max (float.) – Will stop once the best potential has a max rmse below this value. The RMSE value is in THz.

  • complete_dft_vs_ml_benchmark_workflow_0 (CompleteDFTvsMLBenchmarkWorkflow.) – First Iteration will be performed with this flow.

  • complete_dft_vs_ml_benchmark_workflow_1 (CompleteDFTvsMLBenchmarkWorkflow.) – All Iterations after the first one will be performed with this flow.

make(structure_list, mp_ids=None, dft_references=None, benchmark_structures=None, benchmark_mp_ids=None, pre_database_dir=None, pre_xyz_files=None, rattle_seed=0, fit_kwargs_list=None)[source]#

Make flow for constructing the dataset, fitting the potentials and performing the benchmarks.

Parameters:
  • structure_list (list[Structure]) – List of pymatgen structures.

  • mp_ids (list[str] | None) – Materials Project IDs.

  • dft_references (list[PhononBSDOSDoc] | None) – List of DFT reference files containing the PhononBSDOCDoc object. Reference files have to refer to a finite displacement of 0.01. For benchmarking, only 0.01 is supported

  • benchmark_structures (list[Structure] | None) – The pymatgen structure for benchmarking.

  • benchmark_mp_ids (list[str] | None) – Materials Project ID of the benchmarking structure.

  • pre_xyz_files (list[str] or None) – Names of the pre-database train xyz file and test xyz file.

  • pre_database_dir (str or None) – The pre-database directory.

  • rattle_seed (int | None) – Random seed.

  • fit_kwargs_list (list[dict].) – Dict including MLIP fit keyword args.

Return type:

Flow