def test_file_load():
struct1, forces = get_random_structure(cell=np.eye(3),
unique_species=[1, 2],
noa=2)
struct2, forces = get_random_structure(cell=np.eye(3),
unique_species=[1, 2],
noa=2)
with open("test_write.json",'w') as f:
f.write(dumps(struct1.as_dict(),cls=NumpyEncoder))
with pytest.raises(NotImplementedError):
Structure.from_file(file_name='test_write.json', format='xyz')
struct1a = Structure.from_file('test_write.json')
assert dumpcompare(struct1.as_dict() , struct1a.as_dict())
os.remove('test_write.json')
with open("test_write_set.json", 'w') as f:
f.write(dumps(struct1.as_dict(), cls=NumpyEncoder)+'\n')
f.write(dumps(struct2.as_dict(), cls=NumpyEncoder)+'\n')
structs = Structure.from_file('test_write_set.json')
for struc in structs:
assert isinstance(struc, Structure)
assert len(structs) == 2
assert dumpcompare(structs[0].as_dict(), struct1.as_dict())
assert dumpcompare(structs[1].as_dict(), struct2.as_dict())
os.remove('test_write_set.json')
with pytest.raises(FileNotFoundError):
Structure.from_file('fhqwhgads')
vasp_struct = Structure.from_file('./test_files/test_POSCAR')
assert isinstance(vasp_struct, Structure)
assert len(vasp_struct) == 6
def test_file_load():
pmgstruc = pytest.importorskip("pymatgen.core.structure")
struct1, forces = get_random_structure(cell=np.eye(3),
unique_species=[1, 2],
noa=2)
struct2, forces = get_random_structure(cell=np.eye(3),
unique_species=[1, 2],
noa=2)
with open("test_write.json", "w") as f:
f.write(dumps(struct1.as_dict(), cls=NumpyEncoder))
with pytest.raises(NotImplementedError):
Structure.from_file(file_name="test_write.json", format="xyz")
struct1a = Structure.from_file("test_write.json")
assert dumpcompare(struct1.as_dict(), struct1a.as_dict())
os.remove("test_write.json")
with open("test_write_set.json", "w") as f:
f.write(dumps(struct1.as_dict(), cls=NumpyEncoder) + "\n")
f.write(dumps(struct2.as_dict(), cls=NumpyEncoder) + "\n")
structs = Structure.from_file("test_write_set.json")
for struc in structs:
assert isinstance(struc, Structure)
assert len(structs) == 2
assert dumpcompare(structs[0].as_dict(), struct1.as_dict())
assert dumpcompare(structs[1].as_dict(), struct2.as_dict())
os.remove("test_write_set.json")
with pytest.raises(FileNotFoundError):
Structure.from_file("fhqwhgads")
vasp_struct = Structure.from_file("./test_files/test_POSCAR")
assert isinstance(vasp_struct, Structure)
assert len(vasp_struct) == 6
from flare.rbcm import RobustBayesianCommitteeMachine
from flare.gp import GaussianProcess
import os as os
import numpy as np
from flare.struc import Structure
from flare.env import AtomicEnvironment
from flare.gp_algebra import get_kernel_vector
TEST_DIR = os.path.dirname(__file__)
TEST_FILE_DIR = os.path.join(TEST_DIR, "test_files")
methanol_frames = Structure.from_file(
os.path.join(TEST_FILE_DIR, "methanol_frames.json"))
methanol_envs = AtomicEnvironment.from_file(
os.path.join(TEST_FILE_DIR, "methanol_envs.json"))
def test_basic():
rbcm = RobustBayesianCommitteeMachine()
assert isinstance(rbcm, RobustBayesianCommitteeMachine)
def test_expert_growth_and_training():
"""
Test that as data is added the data is allocated to experts correctly
and that various training algorithms can run correctly on it
:return:
"""
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
