def test_base_simulation_data_storage():
substance = Substance.from_components("C")
with tempfile.TemporaryDirectory() as base_directory:
data_directory = os.path.join(base_directory, "data_directory")
data_object = create_dummy_simulation_data(data_directory, substance)
backend_directory = os.path.join(base_directory, "storage_dir")
storage = LocalFileStorage(backend_directory)
storage_key = storage.store_object(data_object, data_directory)
# Regenerate the data directory.
os.makedirs(data_directory, exist_ok=True)
assert storage.has_object(data_object)
assert storage_key == storage.store_object(data_object, data_directory)
retrieved_object, retrieved_directory = storage.retrieve_object(
storage_key, StoredSimulationData)
assert backend_directory in retrieved_directory
assert data_object.json() == retrieved_object.json()
def test_base_simulation_data_query():
substance_a = Substance.from_components("C")
substance_b = Substance.from_components("CO")
substance_full = Substance.from_components("C", "CO")
substances = [substance_a, substance_b, substance_full]
with tempfile.TemporaryDirectory() as base_directory:
backend_directory = os.path.join(base_directory, "storage_dir")
storage = LocalFileStorage(backend_directory)
for substance in substances:
data_directory = os.path.join(base_directory,
f"{substance.identifier}")
data_object = create_dummy_simulation_data(data_directory,
substance)
storage.store_object(data_object, data_directory)
for substance in substances:
substance_query = SimulationDataQuery()
substance_query.substance = substance
results = storage.query(substance_query)
assert results is not None and len(results) == 1
assert len(next(iter(results.values()))[0]) == 3
component_query = SimulationDataQuery()
component_query.substance = substance_full
component_query.substance_query = SubstanceQuery()
component_query.substance_query.components_only = True
results = storage.query(component_query)
assert results is not None and len(results) == 2
def test_unpack_stored_simulation_data():
"""A test that compatible simulation data gets merged
together within the`LocalStorage` system."""
with tempfile.TemporaryDirectory() as directory:
force_field_path = os.path.join(directory, "ff.json")
with open(force_field_path, "w") as file:
file.write(build_tip3p_smirnoff_force_field().json())
dummy_substance = create_dummy_substance(1)
dummy_directory_path = os.path.join(directory, "data")
dummy_data_path = os.path.join(directory, "data.json")
data_coordinate_name = "data_1.pdb"
data_object = create_dummy_simulation_data(
directory_path=dummy_directory_path,
substance=dummy_substance,
force_field_id="ff_id_1",
coordinate_file_name=data_coordinate_name,
statistical_inefficiency=1.0,
)
with open(dummy_data_path, "w") as file:
json.dump(data_object, file, cls=TypedJSONEncoder)
unpack_stored_data = UnpackStoredSimulationData("unpack_data")
unpack_stored_data.simulation_data_path = (
dummy_data_path,
dummy_directory_path,
force_field_path,
)
unpack_stored_data.execute(directory, None)
def test_storage_retrieval():
# Create some dummy properties
methane = Substance.from_components("C")
methanol = Substance.from_components("CO")
mixture = Substance.from_components("C", "CO")
# Add extra unused data to make sure the wrong data isn't
# Being retrieved.
unused_pure = Substance.from_components("CCO")
unused_mixture = Substance.from_components("CCO", "CO")
data_to_store = [
(methane, PropertyPhase.Liquid, 1000),
(methanol, PropertyPhase.Liquid, 1000),
(methanol, PropertyPhase.Gas, 1),
(mixture, PropertyPhase.Liquid, 1000),
(unused_pure, PropertyPhase.Liquid, 1000),
(unused_mixture, PropertyPhase.Liquid, 1000),
]
storage_keys = {}
state = ThermodynamicState(temperature=1.0 * unit.kelvin)
properties = [
# Properties with a full system query.
Density(
value=1.0 * unit.gram / unit.litre,
substance=methanol,
thermodynamic_state=state,
),
DielectricConstant(
value=1.0 * unit.dimensionless, substance=methane, thermodynamic_state=state
),
# Properties with a multi-component query.
EnthalpyOfVaporization(
value=1.0 * unit.joule / unit.mole,
substance=methanol,
thermodynamic_state=state,
),
# Property with a multi-phase query.
EnthalpyOfMixing(
value=1.0 * unit.joule / unit.mole,
substance=mixture,
thermodynamic_state=state,
),
ExcessMolarVolume(
value=1.0 * unit.meter ** 3, substance=mixture, thermodynamic_state=state
),
]
expected_data_per_property = {
Density: {"full_system_data": [(methanol, PropertyPhase.Liquid, 1000)]},
DielectricConstant: {
"full_system_data": [(methane, PropertyPhase.Liquid, 1000)]
},
EnthalpyOfVaporization: {
"liquid_data": [(methanol, PropertyPhase.Liquid, 1000)],
"gas_data": [(methanol, PropertyPhase.Gas, 1)],
},
EnthalpyOfMixing: {
"full_system_data": [(mixture, PropertyPhase.Liquid, 1000)],
"component_data": [
[(methane, PropertyPhase.Liquid, 1000)],
[(methanol, PropertyPhase.Liquid, 1000)],
],
},
ExcessMolarVolume: {
"full_system_data": [(mixture, PropertyPhase.Liquid, 1000)],
"component_data": [
[(methane, PropertyPhase.Liquid, 1000)],
[(methanol, PropertyPhase.Liquid, 1000)],
],
},
}
force_field = SmirnoffForceFieldSource.from_path("smirnoff99Frosst-1.1.0.offxml")
with tempfile.TemporaryDirectory() as base_directory:
# Create a storage backend with some dummy data.
backend_directory = os.path.join(base_directory, "storage_dir")
storage_backend = LocalFileStorage(backend_directory)
force_field_id = storage_backend.store_force_field(force_field)
for substance, phase, n_mol in data_to_store:
data_directory = os.path.join(base_directory, substance.identifier)
data = create_dummy_simulation_data(
data_directory,
substance=substance,
force_field_id=force_field_id,
phase=phase,
number_of_molecules=n_mol,
)
storage_key = storage_backend.store_object(data, data_directory)
storage_keys[(substance, phase, n_mol)] = storage_key
for physical_property in properties:
schema = registered_calculation_schemas["ReweightingLayer"][
physical_property.__class__.__name__
]
if callable(schema):
schema = schema()
# noinspection PyProtectedMember
metadata = ReweightingLayer._get_workflow_metadata(
base_directory,
physical_property,
"",
[],
storage_backend,
schema,
)
assert metadata is not None
expected_data_list = expected_data_per_property[physical_property.__class__]
for data_key in expected_data_list:
assert data_key in metadata
stored_metadata = metadata[data_key]
expected_metadata = expected_data_list[data_key]
assert len(stored_metadata) == len(expected_metadata)
if isinstance(stored_metadata[0], list):
# Flatten any lists of lists.
stored_metadata = [
item for sublist in stored_metadata for item in sublist
]
expected_metadata = [
item for sublist in expected_metadata for item in sublist
]
metadata_storage_keys = [
os.path.basename(x) for x, _, _ in stored_metadata
]
expected_storage_keys = [storage_keys[x] for x in expected_metadata]
assert sorted(metadata_storage_keys) == sorted(expected_storage_keys)
def test_duplicate_simulation_data_storage(reverse_order):
substance = Substance.from_components("CO")
with tempfile.TemporaryDirectory() as base_directory_path:
storage_directory = os.path.join(base_directory_path, "storage")
local_storage = LocalFileStorage(storage_directory)
# Construct some data to store with increasing
# statistical inefficiencies.
data_to_store = []
for index in range(3):
data_directory = os.path.join(base_directory_path, f"data_{index}")
coordinate_name = f"data_{index}.pdb"
data_object = create_dummy_simulation_data(
directory_path=data_directory,
substance=substance,
force_field_id="ff_id_1",
coordinate_file_name=coordinate_name,
statistical_inefficiency=float(index),
calculation_id="id",
)
data_to_store.append((data_object, data_directory))
# Keep a track of the storage keys.
all_storage_keys = set()
iterator = enumerate(data_to_store)
if reverse_order:
iterator = reversed(list(iterator))
# Store the data
for index, data in iterator:
data_object, data_directory = data
storage_key = local_storage.store_object(data_object,
data_directory)
all_storage_keys.add(storage_key)
retrieved_object, stored_directory = local_storage.retrieve_object(
storage_key)
# Handle the case where we haven't reversed the order of
# the data to store. Here only the first object in the list
# should be stored an never replaced as it has the lowest
# statistical inefficiency.
if not reverse_order:
expected_index = 0
# Handle the case where we have reversed the order of
# the data to store. Here only the each new piece of
# data should replace the last, as it will have a lower
# statistical inefficiency.
else:
expected_index = index
assert retrieved_object.json(
) == data_to_store[expected_index][0].json()
# Make sure the directory has been correctly overwritten / retained
# depending on the data order.
coordinate_path = os.path.join(stored_directory,
f"data_{expected_index}.pdb")
assert os.path.isfile(coordinate_path)
# Make sure all pieces of data got assigned the same key if
# reverse order.
assert len(all_storage_keys) == 1