ML_Testing module

MLTestingTask

class esteem.tasks.ml_testing.MLTestingTask(**kwargs)

run()

Main routine for the ML_Testing task

subtract_reference_energies(trajin, trajout_file)

Subtract reference energies from a trajectory to just get energy above reference zero

Task Arguments

usage: __main__.py [-h] [--seed SEED] [--calc_seed CALC_SEED]
                   [--calc_suffix CALC_SUFFIX]
                   [--calc_dir_suffix CALC_DIR_SUFFIX]
                   [--calc_prefix CALC_PREFIX] [--target TARGET]
                   [--output_traj OUTPUT_TRAJ] [--plotfile [PLOTFILE]]
                   [--plotfunc PLOTFUNC] [--cleanup CLEANUP]
                   [--traj_prefix TRAJ_PREFIX] [--traj_suffix TRAJ_SUFFIX]
                   [--ntraj NTRAJ] [--which_trajs WHICH_TRAJS]
                   [--which_trajs_valid WHICH_TRAJS_VALID]
                   [--which_trajs_test WHICH_TRAJS_TEST]
                   [--traj_links TRAJ_LINKS]
                   [--traj_links_valid TRAJ_LINKS_VALID]
                   [--traj_links_test TRAJ_LINKS_TEST]
                   [--ref_mol_seed_dict REF_MOL_SEED_DICT]
                   [--ref_mol_dir REF_MOL_DIR]

Named Arguments

--seed, -s	Base name stem for the calculation (often the name of the molecule)
--calc_seed, -Z
	Seed name for the calculator
--calc_suffix, -S
	Suffix for the calculator (often specifies ML hyperparameters) Default: “”
--calc_dir_suffix, -D
	Suffix for the calculator (often specifies ML hyperparameters)
--calc_prefix, -P
	Prefix for the calculator (often specifies directory) Default: “”
--target, -t	Excited state index, zero for ground state Default: 0
--output_traj, -o
	Filename to which to write the calculated trajectory
--plotfile, -p	Image file to which to write comparison plot
--plotfunc, -F	Function for plotting
--cleanup, -C	Remove reference-corrected test and merged trajectory files after finishing Default: True
--traj_prefix, -Q
	Prefix for the trajectory files being tested Default: “”
--traj_suffix, -T
	Suffix for the trajectory files being tested Default: “training”
--ntraj, -n	How many total trajectories (A,B,C…) with this naming are present Default: 1
--which_trajs, -w
	Which trajectories (A,B,C…) with this naming are to be trained against
--which_trajs_valid, -v
	Which trajectories (A,B,C…) with this naming are to be validated against
--which_trajs_test, -u
	Which trajectories (A,B,C…) with this naming are to be tested against
--traj_links, -L
	Targets for links to create for training trajectories
--traj_links_valid, -V
	Targets for links to create for validation trajectories
--traj_links_test, -U
	Targets for links to create for testing trajectories
--ref_mol_seed_dict, -z
	Dictionary of seeds, for trajectory sets with varying seed names Default: {}
--ref_mol_dir, -r
	Location of output of solutes run from which to find reference energies

Standalone module routines

Defines a task to test a Machine Learning calculator by comparing its results to those of an existing trajectory or set of trajectories

esteem.tasks.ml_testing.compare_wrapper_to_traj(wrapper, calc_params, trajin, trajout_file)

Compare the energy and force predictions of a calculator to results in an existing trajectory