def test_serialization():
"""A test to ensure that data sets are JSON serializable."""
data_set = PhysicalPropertyDataSet()
data_set.add_properties(create_dummy_property(Density))
data_set_json = data_set.json()
parsed_data_set = PhysicalPropertyDataSet.parse_json(data_set_json)
assert len(data_set) == len(parsed_data_set)
parsed_data_set_json = parsed_data_set.json()
assert parsed_data_set_json == data_set_json
def main():
# Set up logging
logging.basicConfig(level=logging.INFO)
output_directory = "training_sets"
os.makedirs(output_directory, exist_ok=True)
rho_pure_h_vap = PhysicalPropertyDataSet.from_json(
"../../../pure_optimisation/data_set_generation/expanded_set/training_set.json"
)
rho_pure = PhysicalPropertyDataSet.from_json(
"../../../pure_optimisation/data_set_generation/expanded_set/training_set.json"
)
rho_pure.filter_by_property_types("Density")
h_mix_rho_x = PhysicalPropertyDataSet.from_json(
"../../../mixture_optimisation/data_set_generation/"
"expanded_set/training_sets/h_mix_rho_x_training_set.json")
h_mix_rho_x_rho_pure = PhysicalPropertyDataSet()
h_mix_rho_x_rho_pure.merge(rho_pure)
h_mix_rho_x_rho_pure.merge(h_mix_rho_x)
h_mix_rho_x_rho_pure.json(
os.path.join(output_directory, "h_mix_rho_x_rho_pure.json"))
h_mix_rho_x_rho_pure.to_pandas().to_csv(
os.path.join(output_directory, "h_mix_rho_x_rho_pure.csv"))
h_mix_rho_x_rho_pure_h_vap = PhysicalPropertyDataSet()
h_mix_rho_x_rho_pure_h_vap.merge(rho_pure_h_vap)
h_mix_rho_x_rho_pure_h_vap.merge(h_mix_rho_x)
h_mix_rho_x_rho_pure_h_vap.json(
os.path.join(output_directory, "h_mix_rho_x_rho_pure_h_vap.json"))
h_mix_rho_x_rho_pure_h_vap.to_pandas().to_csv(
os.path.join(output_directory, "h_mix_rho_x_rho_pure_h_vap.csv"))
def main():
training_set_smiles = [
"CCO",
"CC(=O)O",
"COC=O",
"CC(C)(C)O",
"CC(C)O",
"CO",
"CCOC(C)=O",
"CCOC(=O)CC(=O)OCC",
"CC(C)CO",
"CCCCO",
"CCCCOC(C)=O",
"CCCOC(C)=O",
]
# Ensure the smiles patterns are standardized.
smiles = [Component(x).smiles for x in training_set_smiles]
# Load in the Hvap data
h_vap_data_frame = pandas.read_csv(
os.path.join(
"..",
"..",
"..",
"data_availability",
"sourced_h_vap_data",
"enthalpy_of_vaporization_pure.csv",
))
h_vap_data_frame = filter_by_smiles(h_vap_data_frame,
smiles_to_include=smiles,
smiles_to_exclude=None)
h_vap_data_set = data_set_from_data_frame(h_vap_data_frame)
# # Load in the density data
density_data_frame = pandas.read_csv(
os.path.join(
"..",
"..",
"..",
"data_availability",
"data_by_environments",
"alcohol_ester",
"all_data",
"density_pure.csv",
))
density_data_frame = filter_by_smiles(density_data_frame,
smiles_to_include=smiles,
smiles_to_exclude=None)
density_data_set = data_set_from_data_frame(density_data_frame)
# Retain the density measurements which were made closest to 298.15K and 1 atm.
target_state_point = StatePoint(
temperature=298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere,
mole_fractions=(1.0, ),
)
final_data_set = PhysicalPropertyDataSet()
for substance in density_data_set.substances:
properties_per_state = defaultdict(list)
# Refactor the properties into more convenient data structures.
for physical_property in density_data_set.properties_by_substance(
substance):
state_point = StatePoint.from_physical_property(physical_property)
properties_per_state[state_point].append(physical_property)
# Sort the state points based on their distance to the target state.
sorted_states_points = list(
sorted(
properties_per_state.keys(),
key=functools.partial(StatePoint.individual_distances,
target_state_point),
))
final_data_set.add_properties(
properties_per_state[sorted_states_points[0]][0])
final_data_set.merge(h_vap_data_set)
final_data_set.json("training_set.json", format=True)
final_data_set.to_pandas().to_csv("training_set.csv", index=False)
def main():
# Set up logging
logging.basicConfig(level=logging.INFO)
output_directory = "training_sets"
os.makedirs(output_directory, exist_ok=True)
pure_density_h_vap = PhysicalPropertyDataSet.from_json(
"../../pure_optimisation/data_set_generation/training_set.json"
)
pure_density = PhysicalPropertyDataSet.from_json(
"../../pure_optimisation/data_set_generation/training_set.json"
)
pure_density.filter_by_property_types("Density")
h_mix_v_excess = PhysicalPropertyDataSet.from_json(
"../../mixture_optimisation/data_set_generation/"
"training_sets/h_mix_v_excess_training_set.json"
)
h_mix_binary_density = PhysicalPropertyDataSet.from_json(
"../../mixture_optimisation/data_set_generation/"
"training_sets/h_mix_density_training_set.json"
)
h_mix_binary_density_pure_density = PhysicalPropertyDataSet()
h_mix_binary_density_pure_density.merge(pure_density)
h_mix_binary_density_pure_density.merge(h_mix_binary_density)
h_mix_binary_density_pure_density.json(
os.path.join(output_directory, "h_mix_binary_density_pure_density.json")
)
h_mix_binary_density_pure_density.to_pandas().to_csv(
os.path.join(output_directory, "h_mix_binary_density_pure_density.csv")
)
h_mix_v_excess_pure_density = PhysicalPropertyDataSet()
h_mix_v_excess_pure_density.merge(pure_density)
h_mix_v_excess_pure_density.merge(h_mix_v_excess)
h_mix_v_excess_pure_density.json(
os.path.join(output_directory, "h_mix_v_excess_pure_density.json")
)
h_mix_v_excess_pure_density.to_pandas().to_csv(
os.path.join(output_directory, "h_mix_v_excess_pure_density.csv")
)
h_mix_binary_density_pure_density_h_vap = PhysicalPropertyDataSet()
h_mix_binary_density_pure_density_h_vap.merge(pure_density_h_vap)
h_mix_binary_density_pure_density_h_vap.merge(h_mix_binary_density)
h_mix_binary_density_pure_density_h_vap.json(
os.path.join(output_directory, "h_mix_binary_density_pure_density_h_vap.json")
)
h_mix_binary_density_pure_density_h_vap.to_pandas().to_csv(
os.path.join(output_directory, "h_mix_binary_density_pure_density_h_vap.csv")
)
h_mix_v_excess_pure_density_h_vap = PhysicalPropertyDataSet()
h_mix_v_excess_pure_density_h_vap.merge(pure_density_h_vap)
h_mix_v_excess_pure_density_h_vap.merge(h_mix_v_excess)
h_mix_v_excess_pure_density_h_vap.json(
os.path.join(output_directory, "h_mix_v_excess_pure_density_h_vap.json")
)
h_mix_v_excess_pure_density_h_vap.to_pandas().to_csv(
os.path.join(output_directory, "h_mix_v_excess_pure_density_h_vap.csv")
)
