def test_to_from_methods(varied_test_struc):
test_dict = varied_test_struc.as_dict()
assert isinstance(test_dict, dict)
assert (test_dict["forces"] == varied_test_struc.forces).all()
new_struc_1 = Structure.from_dict(test_dict)
new_struc_2 = Structure.from_dict(loads(varied_test_struc.as_str()))
for new_struc in [new_struc_1, new_struc_2]:
assert np.equal(varied_test_struc.positions, new_struc.positions).all()
assert np.equal(varied_test_struc.cell, new_struc.cell).all()
assert np.equal(varied_test_struc.forces, new_struc.forces).all()
def test_load_one_frame_and_run():
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",
)
with open(path.join(TEST_FILE_DIR, "methanol_frames.json"), "r") as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
tt = TrajectoryTrainer(
frames,
gp=the_gp,
shuffle_frames=True,
print_as_xyz=True,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15,
)
tt.run()
for f in glob(f"gp_from_aimd*"):
remove(f)
def test_load_one_frame_and_run():
the_gp = GaussianProcess(kernel=two_plus_three_body_mc,
kernel_grad=two_plus_three_body_mc_grad,
hyps=np.array([
3.75996759e-06, 1.53990678e-02,
2.50624782e-05, 5.07884426e-01, 1.70172923e-03
]),
cutoffs=np.array([7, 7]),
hyp_labels=['l2', 's2', 'l3', 's3', 'n0'],
maxiter=1,
opt_algorithm='L-BFGS-B')
with open('./test_files/methanol_frames.json', 'r') as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
tt = TrajectoryTrainer(frames,
gp=the_gp,
shuffle_frames=True,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15)
tt.run()
os.system('rm ./gp_from_aimd.gp')
os.system('rm ./gp_from_aimd.out')
os.system('rm ./gp_from_aimd.xyz')
os.system('rm ./gp_from_aimd-f.xyz')
def test_pred_on_elements():
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([7, 3]),
hyp_labels=['l2', 's2', 'l3', 's3', 'n0'],
maxiter=1,
opt_algorithm='L-BFGS-B')
with open('./test_files/methanol_frames.json', 'r') as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
with open('./test_files/methanol_envs.json', 'r') as f:
data_dicts = [loads(s) for s in f.readlines()[:6]]
envs = [AtomicEnvironment.from_dict(d) for d in data_dicts]
forces = [np.array(d['forces']) for d in data_dicts]
seeds = list(zip(envs, forces))
all_frames = deepcopy(frames)
tt = TrajectoryTrainer(frames,
gp=the_gp,
shuffle_frames=False,
rel_std_tolerance=0,
abs_std_tolerance=0,
abs_force_tolerance=.001,
skip=5,
min_atoms_per_train=100,
pre_train_seed_envs=seeds,
pre_train_seed_frames=[frames[-1]],
max_atoms_from_frame=4,
output_name='meth_test',
model_format='json',
atom_checkpoint_interval=50,
pre_train_atoms_per_element={'H': 1},
predict_atoms_per_element={
'H': 0,
'C': 1,
'O': 0
})
# Set to predict only on Carbon after training on H to ensure errors are
# high and that they get added to the gp
tt.run()
# Ensure forces weren't written directly to structure
for i in range(len(all_frames)):
assert np.array_equal(all_frames[i].forces, frames[i].forces)
# Assert that Carbon atoms were correctly added
assert the_gp.training_statistics['envs_by_species']['C'] > 2
for f in glob(f"meth_test*"):
remove(f)
for f in glob(f"gp_from_aimd*"):
remove(f)
def md_trajectory_from_file(filename: str):
"""
Read a list of structures from a json file, formatted as in md_trajectory_to_file.
:param filename:
"""
with open(filename, 'r') as f:
structure_list = load(f)
structures = \
[Structure.from_dict(dictionary) for dictionary in structure_list]
return structures
def test_seed_and_run():
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",
)
with open(path.join(TEST_FILE_DIR, "methanol_frames.json"), "r") as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
with open(path.join(TEST_FILE_DIR, "methanol_envs.json"), "r") as f:
data_dicts = [loads(s) for s in f.readlines()[:6]]
envs = [AtomicEnvironment.from_dict(d) for d in data_dicts]
forces = [np.array(d["forces"]) for d in data_dicts]
seeds = list(zip(envs, forces))
tt = TrajectoryTrainer(
frames,
gp=the_gp,
shuffle_frames=True,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=10,
pre_train_seed_envs=seeds,
pre_train_seed_frames=[frames[-1]],
max_atoms_from_frame=4,
output_name="meth_test",
model_format="pickle",
train_checkpoint_interval=1,
pre_train_atoms_per_element={"H": 1},
)
tt.run()
with open("meth_test_model.pickle", "rb") as f:
new_gp = pickle.load(f)
test_env = envs[0]
for d in [1, 2, 3]:
assert np.all(
the_gp.predict(x_t=test_env, d=d) == new_gp.predict(x_t=test_env,
d=d))
for f in glob(f"meth_test*"):
remove(f)
def test_load_trained_gp_and_run(methanol_gp):
with open('./test_files/methanol_frames.json', 'r') as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
tt = TrajectoryTrainer(frames,
gp=methanol_gp,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15)
tt.run()
os.system('rm ./gp_from_aimd*')
def test_seed_and_run():
the_gp = GaussianProcess(kernel=two_plus_three_body_mc,
kernel_grad=two_plus_three_body_mc_grad,
hyps=np.array([
3.75996759e-06, 1.53990678e-02,
2.50624782e-05, 5.07884426e-01, 1.70172923e-03
]),
cutoffs=np.array([7, 7]),
hyp_labels=['l2', 's2', 'l3', 's3', 'n0'],
maxiter=1,
opt_algorithm='L-BFGS-B')
with open('./test_files/methanol_frames.json', 'r') as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
with open('./test_files/methanol_envs.json', 'r') as f:
data_dicts = [loads(s) for s in f.readlines()[:6]]
envs = [AtomicEnvironment.from_dict(d) for d in data_dicts]
forces = [np.array(d['forces']) for d in data_dicts]
seeds = list(zip(envs, forces))
tt = TrajectoryTrainer(frames,
gp=the_gp,
shuffle_frames=True,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15,
pre_train_seed_envs=seeds,
pre_train_seed_frames=[frames[-1]],
max_atoms_from_frame=4,
model_write='meth_test.pickle',
model_format='pickle',
checkpoint_interval=1,
pre_train_atoms_per_element={'H': 1})
tt.run()
with open('meth_test.pickle', 'rb') as f:
new_gp = pickle.load(f)
test_env = envs[0]
for d in [0, 1, 2]:
assert np.all(
the_gp.predict(x_t=test_env, d=d) == new_gp.predict(x_t=test_env,
d=d))
os.system('rm ./gp_from_aimd.out')
os.system('rm ./gp_from_aimd.xyz')
os.system('rm ./gp_from_aimd-f.xyz')
os.system('rm ./meth_test.pickle')
def test_load_trained_gp_and_run(methanol_gp):
with open('./test_files/methanol_frames.json', 'r') as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
tt = TrajectoryTrainer(frames,
gp=methanol_gp,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15,
train_checkpoint_interval=10)
tt.run()
for f in glob(f"gp_from_aimd*"):
remove(f)
def test_load_trained_gp_and_run(methanol_gp):
with open(path.join(TEST_FILE_DIR, "methanol_frames.json"), "r") as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
tt = TrajectoryTrainer(
frames,
gp=methanol_gp,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15,
train_checkpoint_interval=10,
)
tt.run()
for f in glob(f"gp_from_aimd*"):
remove(f)
def test_load_one_frame_and_run():
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([7, 7]),
hyp_labels=['l2', 's2', 'l3', 's3', 'n0'],
maxiter=1,
opt_algorithm='L-BFGS-B')
with open('./test_files/methanol_frames.json', 'r') as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
tt = TrajectoryTrainer(frames,
gp=the_gp,
shuffle_frames=True,
rel_std_tolerance=0,
abs_std_tolerance=0,
skip=15)
tt.run()
for f in glob(f"gp_from_aimd*"):
remove(f)
def test_pred_on_elements():
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",
)
with open(path.join(TEST_FILE_DIR, "methanol_frames.json"), "r") as f:
frames = [Structure.from_dict(loads(s)) for s in f.readlines()]
with open(path.join(TEST_FILE_DIR, "methanol_envs.json"), "r") as f:
data_dicts = [loads(s) for s in f.readlines()[:6]]
envs = [AtomicEnvironment.from_dict(d) for d in data_dicts]
forces = [np.array(d["forces"]) for d in data_dicts]
seeds = list(zip(envs, forces))
all_frames = deepcopy(frames)
tt = TrajectoryTrainer(
frames,
gp=the_gp,
shuffle_frames=False,
rel_std_tolerance=0,
abs_std_tolerance=0,
abs_force_tolerance=0.001,
skip=5,
min_atoms_per_train=100,
pre_train_seed_envs=seeds,
pre_train_seed_frames=[frames[-1]],
max_atoms_from_frame=4,
output_name="meth_test",
print_as_xyz=True,
model_format="json",
atom_checkpoint_interval=50,
pre_train_atoms_per_element={"H": 1},
predict_atoms_per_element={
"H": 0,
"C": 1,
"O": 0
},
)
# Set to predict only on Carbon after training on H to ensure errors are
# high and that they get added to the gp
tt.run()
# Ensure forces weren't written directly to structure
for i in range(len(all_frames)):
assert np.array_equal(all_frames[i].forces, frames[i].forces)
# Assert that Carbon atoms were correctly added
assert the_gp.training_statistics["envs_by_species"]["C"] > 2
for f in glob(f"meth_test*"):
remove(f)
for f in glob(f"gp_from_aimd*"):
remove(f)
