def test_from_pandas():
"""A test to ensure that data sets may be created from pandas objects."""
thermodynamic_state = ThermodynamicState(temperature=298.15 * unit.kelvin,
pressure=1.0 * unit.atmosphere)
original_data_set = PhysicalPropertyDataSet()
original_data_set.add_properties(
Density(
thermodynamic_state=thermodynamic_state,
phase=PropertyPhase.Liquid,
substance=Substance.from_components("CO", "O"),
value=1.0 * unit.kilogram / unit.meter**3,
uncertainty=1.0 * unit.kilogram / unit.meter**3,
source=MeasurementSource(doi="10.5281/zenodo.596537"),
),
EnthalpyOfVaporization(
thermodynamic_state=thermodynamic_state,
phase=PropertyPhase.from_string("Liquid + Gas"),
substance=Substance.from_components("C"),
value=2.0 * unit.kilojoule / unit.mole,
source=MeasurementSource(reference="2"),
),
DielectricConstant(
thermodynamic_state=thermodynamic_state,
phase=PropertyPhase.Liquid,
substance=Substance.from_components("C"),
value=3.0 * unit.dimensionless,
source=MeasurementSource(reference="3"),
),
)
data_frame = original_data_set.to_pandas()
recreated_data_set = PhysicalPropertyDataSet.from_pandas(data_frame)
assert len(original_data_set) == len(recreated_data_set)
for original_property in original_data_set:
recreated_property = next(x for x in recreated_data_set
if x.id == original_property.id)
assert (original_property.thermodynamic_state ==
recreated_property.thermodynamic_state)
assert original_property.phase == recreated_property.phase
assert original_property.substance == recreated_property.substance
assert numpy.isclose(original_property.value, recreated_property.value)
if original_property.uncertainty == UNDEFINED:
assert original_property.uncertainty == recreated_property.uncertainty
else:
assert numpy.isclose(original_property.uncertainty,
recreated_property.uncertainty)
assert original_property.source.doi == recreated_property.source.doi
assert original_property.source.reference == recreated_property.source.reference
def apply(cls, data_set, schema, n_processes=1):
"""Apply each component of this curation workflow to an initial data set in
sequence.
Parameters
----------
data_set
The data set to apply the workflow to. This may either be a
data set object or it's pandas representation.
schema
The schema which defines the components to apply.
n_processes
The number of processes that each component is allowed to
parallelize across.
Returns
-------
The data set which has had the curation workflow applied to it.
"""
component_classes = CurationComponent.components
data_frame = data_set
if isinstance(data_frame, PhysicalPropertyDataSet):
data_frame = data_frame.to_pandas()
data_frame = data_frame.copy()
data_frame = data_frame.fillna(value=numpy.nan)
for component_schema in schema.component_schemas:
component_class_name = component_schema.__class__.__name__.replace(
"Schema", "")
component_class = component_classes[component_class_name]
logger.info(f"Applying {component_class_name}")
data_frame = component_class.apply(data_frame, component_schema,
n_processes)
logger.info(f"{component_class_name} applied")
data_frame = data_frame.fillna(value=numpy.nan)
if isinstance(data_set, PhysicalPropertyDataSet):
data_frame = PhysicalPropertyDataSet.from_pandas(data_frame)
return data_frame
def apply(cls, data_set, schema, n_processes=1):
"""Apply this curation component to a data set.
Parameters
----------
data_set
The data frame to apply the component to.
schema
The schema which defines how this component should be applied.
n_processes
The number of processes that this component is allowed to
parallelize across.
Returns
-------
The data set which has had the component applied to it.
"""
data_frame = data_set
if isinstance(data_frame, PhysicalPropertyDataSet):
data_frame = data_frame.to_pandas()
modified_data_frame = cls._apply(data_frame, schema, n_processes)
n_data_points = len(data_frame)
n_filtered = len(modified_data_frame)
if n_filtered != n_data_points:
direction = "removed" if n_filtered < n_data_points else "added"
logger.info(
f"{abs(n_filtered - n_data_points)} data points were {direction} after "
f"applying the {cls.__name__} component.")
if isinstance(data_set, PhysicalPropertyDataSet):
modified_data_frame = PhysicalPropertyDataSet.from_pandas(
modified_data_frame)
return modified_data_frame
def data_set(data_frame: pandas.DataFrame) -> PhysicalPropertyDataSet:
return PhysicalPropertyDataSet.from_pandas(data_frame)
