def test_active_learning_simple_run():
"""
Test simple mechanics of active learning method.
:return:
"""
the_gp = GaussianProcess(
kernel_name="2+3_mc",
hyps=np.array([
3.75996759e-06,
1.53990678e-02,
2.50624782e-05,
5.07884426e-01,
1.70172923e-03,
]),
cutoffs=np.array([5, 3]),
hyp_labels=["l2", "s2", "l3", "s3", "n0"],
maxiter=1,
opt_algorithm="L-BFGS-B",
)
frames = Structure.from_file(
path.join(TEST_FILE_DIR, "methanol_frames.json"))
# Assign fake energies to structures
for frame in frames:
frame.energy = np.random.random()
tt = TrajectoryTrainer(gp=the_gp, include_energies=True)
tt.run_passive_learning(
frames=frames[:1],
max_elts_per_frame={
"C": 1,
"O": 1,
"H": 1
},
post_training_iterations=0,
post_build_matrices=True,
)
assert len(the_gp.training_structures) == 1
prev_gp_len = len(the_gp)
prev_gp_stats = the_gp.training_statistics
tt.run_active_learning(frames[:2],
rel_std_tolerance=0,
abs_std_tolerance=0,
abs_force_tolerance=0)
assert len(the_gp) == prev_gp_len
# Try on a frame where the Carbon atom is guaranteed to trip the
# abs. force tolerance condition.
# Turn off include energies so that the number of training structures
# does not change.
tt.include_energies = False
tt.run_active_learning(
frames[1:2],
rel_std_tolerance=0,
abs_std_tolerance=0,
abs_force_tolerance=0.1,
max_elts_per_frame={
"H": 0,
"O": 0
},
max_model_elts={"C": 2},
)
assert len(the_gp) == prev_gp_len + 1
assert len(the_gp.training_structures) == 1
prev_carbon_atoms = prev_gp_stats["envs_by_species"]["C"]
assert the_gp.training_statistics["envs_by_species"][
"C"] == prev_carbon_atoms + 1
prev_gp_len = len(the_gp)
tt.run_active_learning(
frames[3:4],
rel_std_tolerance=0,
abs_std_tolerance=0,
abs_force_tolerance=0.1,
max_model_size=prev_gp_len,
)
assert len(the_gp) == prev_gp_len
# Test that model doesn't add atoms
prev_gp_len = len(the_gp)
tt.run_active_learning(
frames[5:6],
rel_std_tolerance=0,
abs_std_tolerance=0,
abs_force_tolerance=0.1,
max_model_elts={
"C": 2,
"H": 1,
"O": 1
},
)
assert len(the_gp) == prev_gp_len
for f in glob(f"gp_from_aimd*"):
remove(f)
def test_passive_learning():
the_gp = GaussianProcess(
kernel_name="2+3_mc",
hyps=np.array([
3.75996759e-06,
1.53990678e-02,
2.50624782e-05,
5.07884426e-01,
1.70172923e-03,
]),
cutoffs=np.array([5, 3]),
hyp_labels=["l2", "s2", "l3", "s3", "n0"],
maxiter=1,
opt_algorithm="L-BFGS-B",
)
frames = Structure.from_file(
path.join(TEST_FILE_DIR, "methanol_frames.json"))
envs = AtomicEnvironment.from_file(
path.join(TEST_FILE_DIR, "methanol_envs.json"))
cur_gp = deepcopy(the_gp)
tt = TrajectoryTrainer(frames=None, gp=cur_gp)
# TEST ENVIRONMENT ADDITION
envs_species = set(Z_to_element(env.ctype) for env in envs)
tt.run_passive_learning(environments=envs, post_build_matrices=False)
assert cur_gp.training_statistics["N"] == len(envs)
assert set(cur_gp.training_statistics["species"]) == envs_species
# TEST FRAME ADDITION: ALL ARE ADDED
cur_gp = deepcopy(the_gp)
tt.gp = cur_gp
tt.run_passive_learning(frames=frames, post_build_matrices=False)
assert len(cur_gp.training_data) == sum([len(fr) for fr in frames])
# TEST FRAME ADDITION: MAX OUT MODEL SIZE AT 1
cur_gp = deepcopy(the_gp)
tt.gp = cur_gp
tt.run_passive_learning(frames=frames,
max_model_size=1,
post_training_iterations=1)
assert len(cur_gp.training_data) == 1
# TEST FRAME ADDITION: EXCLUDE OXYGEN, LIMIT CARBON TO 1, 1 H PER FRAME
cur_gp = deepcopy(the_gp)
tt.gp = cur_gp
tt.run_passive_learning(
frames=frames,
max_model_elts={
"O": 0,
"C": 1,
"H": 5
},
max_elts_per_frame={"H": 1},
post_build_matrices=False,
)
assert "O" not in cur_gp.training_statistics["species"]
assert cur_gp.training_statistics["envs_by_species"]["C"] == 1
assert cur_gp.training_statistics["envs_by_species"]["H"] == 5