def estimated_reference_sets():
estimated_density = Density(
thermodynamic_state=ThermodynamicState(298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=Substance.from_components("O", "CC=O"),
value=1.0 * unit.kilogram / unit.meter**3,
uncertainty=0.1 * unit.kilogram / unit.meter**3,
)
estimated_density.id = "1"
estimated_enthalpy = EnthalpyOfMixing(
thermodynamic_state=ThermodynamicState(298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=Substance.from_components("O", "CC=O"),
value=1.0 * unit.kilocalorie / unit.mole,
uncertainty=0.1 * unit.kilojoule / unit.mole,
)
estimated_enthalpy.id = "2"
estimated_data_set = PhysicalPropertyDataSet()
estimated_data_set.add_properties(estimated_density, estimated_enthalpy)
reference_density = DataSetEntry(
id=1,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=0.001,
std_error=0.0001,
doi=" ",
components=[
Component(smiles="O", mole_fraction=0.5),
Component(smiles="CC=O", mole_fraction=0.5),
],
)
reference_enthalpy = DataSetEntry(
id=2,
property_type="EnthalpyOfMixing",
temperature=298.15,
pressure=101.325,
value=4.184,
std_error=0.1,
doi=" ",
components=[
Component(smiles="O", mole_fraction=0.5),
Component(smiles="CC=O", mole_fraction=0.5),
],
)
reference_data_set = DataSet(
id="ref",
description=" ",
authors=[Author(name=" ", email="*****@*****.**", institute=" ")],
entries=[reference_density, reference_enthalpy],
)
return estimated_data_set, reference_data_set
def test_reindex_data_set_no_mole_fraction():
"""Tests that the ``reindex_data_set`` function behaves as expected
when exact amounts are present."""
setup_timestamp_logging(logging.INFO)
substance = substances.Substance()
substance.add_component(substances.Component(smiles="O"),
amount=substances.MoleFraction(1.0))
substance.add_component(
substances.Component(smiles="CO",
role=substances.Component.Role.Solute),
amount=substances.ExactAmount(1),
)
evaluator_data_set = PhysicalPropertyDataSet()
evaluator_data_set.add_properties(
SolvationFreeEnergy(
thermodynamic_state=ThermodynamicState(
temperature=298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=substance,
value=1.0 * SolvationFreeEnergy.default_unit(),
uncertainty=1.0 * SolvationFreeEnergy.default_unit(),
), )
data_set = DataSet(
id="data-set",
description=" ",
authors=[Author(name=" ", email="*****@*****.**", institute=" ")],
entries=[
DataSetEntry(
id=1,
property_type="SolvationFreeEnergy",
temperature=298.15,
pressure=101.325,
value=1.0,
std_error=1.0,
doi=" ",
components=[
Component(smiles="O", mole_fraction=1.0),
Component(smiles="CO",
mole_fraction=0.0,
exact_amount=1,
role="Solute"),
],
)
],
)
reindex_data_set(evaluator_data_set, data_set)
assert evaluator_data_set.properties[0].id == "1"
def test_three_components_to_categories():
with pytest.raises(NotImplementedError):
components_to_categories(
[Component(smiles="C", mole_fraction=1.0)] * 3,
[ChemicalEnvironment.Alkane],
)
def analyze(
cls,
optimization: Optimization,
target: RechargeTarget,
target_directory: str,
result_directory: str,
) -> Optional[RechargeTargetResult]:
residuals_path = os.path.join(result_directory, "residuals.json")
if not os.path.isfile(residuals_path):
return None
# Load in the residuals
with open(residuals_path) as file:
squared_residuals = json.load(file)
# Categorize the smiles
smiles_per_category = defaultdict(list)
smiles_per_category[None] = [*squared_residuals]
for smiles in squared_residuals:
categories = components_to_categories(
[Component(smiles=smiles, mole_fraction=0.0, exact_amount=1)],
optimization.analysis_environments,
)
for category in categories:
smiles_per_category[category].append(smiles)
# Compute RMSE statistics for this target.
statistic_entries = []
for category in smiles_per_category:
category_residuals = [
squared_residuals[smiles]
for smiles in smiles_per_category[category]
]
rmse, rmse_std, rmse_ci = bootstrap_residuals(category_residuals)
statistic_entry = Statistic(
statistic_type=StatisticType.RMSE,
category=category,
value=rmse,
lower_95_ci=rmse_ci[0],
upper_95_ci=rmse_ci[1],
)
statistic_entries.append(statistic_entry)
objective_function = cls._read_objective_function(result_directory)
return RechargeTargetResult(
objective_function=target.weight * objective_function,
statistic_entries=statistic_entries,
)
def create_data_set(data_set_id: str, entry_id: Optional[int] = None):
"""Creates a single author data set which contains a single
density data entry. The entry contains two components, an
aqueous solvent (x=1) and a methanol solute (n=1).
Parameters
----------
data_set_id: str
The id to assign to the data set.
entry_id
The id to assign to the one data entry.
Returns
-------
DataSet
"""
author = create_author()
data_entry = DataSetEntry(
id=entry_id,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=1.0,
std_error=0.1,
doi=" ",
components=[
Component(smiles="O",
mole_fraction=1.0,
exact_amount=0,
role="Solvent"),
Component(smiles="CO",
mole_fraction=0.0,
exact_amount=1,
role="Solute"),
],
)
data_set = DataSet(id=data_set_id,
description=" ",
authors=[author],
entries=[data_entry])
return data_set
def test_analysed_result_from_evaluator():
"""Tests the `AnalysedResult.from_evaluator` function."""
expected_mean = 0.0
expected_std = numpy.random.rand() + 1.0
values = numpy.random.normal(expected_mean, expected_std, 1000)
estimated_properties = []
reference_entries = []
for index, value in enumerate(values):
property_id = index + 1
estimated_density = Density(
thermodynamic_state=ThermodynamicState(298.15 * unit.kelvin,
pressure=1.0 *
unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=Substance.from_components("O"),
value=value * Density.default_unit(),
uncertainty=0.0 * Density.default_unit(),
)
estimated_density.id = str(property_id)
estimated_properties.append(estimated_density)
reference_density = DataSetEntry(
id=property_id,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=expected_mean,
std_error=None,
doi=" ",
components=[Component(smiles="O", mole_fraction=1.0)],
)
reference_entries.append(reference_density)
estimated_data_set = PhysicalPropertyDataSet()
estimated_data_set.add_properties(*estimated_properties)
reference_data_set = DataSet(
id="ref",
description=" ",
authors=[Author(name=" ", email="*****@*****.**", institute=" ")],
entries=reference_entries,
)
analysis_environments = [ChemicalEnvironment.Aqueous]
analysed_results = DataSetResult.from_evaluator(
reference_data_set=reference_data_set,
estimated_data_set=estimated_data_set,
analysis_environments=analysis_environments,
statistic_types=[StatisticType.RMSE],
bootstrap_iterations=1000,
)
assert len(analysed_results.result_entries) == len(estimated_properties)
full_statistics = next(
iter(x for x in analysed_results.statistic_entries
if x.category is None))
assert full_statistics.property_type == "Density"
assert full_statistics.n_components == 1
assert full_statistics.statistic_type == StatisticType.RMSE
assert numpy.isclose(full_statistics.value, expected_std, rtol=0.10)
def test_components_to_categories_empty():
assert (components_to_categories(
[Component(smiles="C", mole_fraction=1.0)], []) == [])
def test_analyse_functional_groups(smiles, expected_environment):
"""Performs a simple test of the analyse_functional_groups function."""
chemical_moieties = analyse_functional_groups(smiles)
assert expected_environment in chemical_moieties
def test_analyse_functional_groups_error():
"""Tests the the function returns None when an unknown
smiles pattern is passed."""
assert analyse_functional_groups("[Ar]") is None
@pytest.mark.parametrize(
"components, expected_categories",
[
([Component(smiles="CC(O)CC", mole_fraction=1.0)], ["Alcohol"]),
([Component(smiles="CC(=O)CC", mole_fraction=1.0)], ["Ketone"]),
([Component(smiles="C(=O)CC", mole_fraction=1.0)], ["Other"]),
([Component(smiles="CC(=O)CO", mole_fraction=1.0)
], ["Alcohol", "Ketone"]),
(
[
Component(smiles="CC(O)CC", mole_fraction=0.5),
Component(smiles="CC(O)C", mole_fraction=0.5),
],
["Alcohol + Alcohol"],
),
(
[
Component(smiles="CC(O)CC", mole_fraction=0.5),
Component(smiles="CC(=O)CO", mole_fraction=0.5),
def test_reindex_data_set():
"""Tests that the ``reindex_data_set`` function behaves as expected."""
setup_timestamp_logging(logging.INFO)
evaluator_data_set = PhysicalPropertyDataSet()
evaluator_data_set.add_properties(
Density(
thermodynamic_state=ThermodynamicState(
temperature=298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=substances.Substance.from_components("O"),
value=1.0 * Density.default_unit(),
uncertainty=1.0 * Density.default_unit(),
),
Density(
thermodynamic_state=ThermodynamicState(
temperature=298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=substances.Substance.from_components("C", "O"),
value=1.0 * Density.default_unit(),
uncertainty=1.0 * Density.default_unit(),
),
Density(
thermodynamic_state=ThermodynamicState(
temperature=300.0 * unit.kelvin,
pressure=1.0 * unit.atmosphere),
phase=PropertyPhase.Liquid,
substance=substances.Substance.from_components("C", "O"),
value=1.0 * Density.default_unit(),
uncertainty=1.0 * Density.default_unit(),
),
)
data_set = DataSet(
id="data-set",
description=" ",
authors=[Author(name=" ", email="*****@*****.**", institute=" ")],
entries=[
DataSetEntry(
id=1,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=1.0,
std_error=1.0,
doi=" ",
components=[
Component(smiles="O", mole_fraction=0.5),
Component(smiles="C", mole_fraction=0.5),
],
),
DataSetEntry(
id=2,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=1.0,
std_error=1.0,
doi=" ",
components=[Component(smiles="O", mole_fraction=1.0)],
),
],
)
un_indexed_id = evaluator_data_set.properties[2].id
reindex_data_set(evaluator_data_set, data_set)
assert evaluator_data_set.properties[0].id == "2"
assert evaluator_data_set.properties[1].id == "1"
assert evaluator_data_set.properties[2].id == un_indexed_id
data_set_collection = DataSetCollection(data_sets=[
DataSet(
id="0",
description=" ",
authors=[Author(name=" ", email="*****@*****.**", institute=" ")],
entries=[
DataSetEntry(
id=3,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=1.0,
std_error=1.0,
doi=" ",
components=[
Component(smiles="O", mole_fraction=0.5),
Component(smiles="C", mole_fraction=0.5),
],
)
],
),
DataSet(
id="1",
description=" ",
authors=[Author(name=" ", email="*****@*****.**", institute=" ")],
entries=[
DataSetEntry(
id=4,
property_type="Density",
temperature=298.15,
pressure=101.325,
value=1.0,
std_error=1.0,
doi=" ",
components=[Component(smiles="O", mole_fraction=1.0)],
)
],
),
])
reindex_data_set(evaluator_data_set, data_set_collection)
assert evaluator_data_set.properties[0].id == "4"
assert evaluator_data_set.properties[1].id == "3"
assert evaluator_data_set.properties[2].id == un_indexed_id