def test_construct_consistent_error_multiple_units():
# test that construction fails if there's no data about the follower gas in the
# database
aggregate_name = "Emissions|HFC|C5F12"
components = ["Emissions|HFC|C2F6"]
test_db_units = test_db.copy()
test_db_units.data["variable"] = components[0]
error_msg = re.escape(
"Too many units found to make a consistent {}".format(aggregate_name))
with pytest.raises(ValueError, match=error_msg):
_construct_consistent_values(aggregate_name, components, test_db_units)
def test__construct_consistent_values():
test_db_co2 = convert_units_to_MtCO2_equiv(test_db)
aggregate_name = "agg"
assert aggregate_name not in test_db_co2.variables().values
component_ratio = ["Emissions|HFC|C2F6", "Emissions|HFC|C5F12"]
consistent_vals = _construct_consistent_values(aggregate_name,
component_ratio,
test_db_co2)
assert aggregate_name in consistent_vals["variable"].values
consistent_vals = consistent_vals.timeseries()
timeseries_data = test_db_co2.timeseries()
assert all([
np.allclose(
consistent_vals.iloc[0].iloc[ind],
timeseries_data.iloc[0].iloc[ind] +
timeseries_data.iloc[1].iloc[ind],
) for ind in range(len(timeseries_data.iloc[0]))
])
def test__construct_consistent_values_with_equiv():
test_db_co2 = convert_units_to_MtCO2_equiv(test_db)
test_db_co2.data["unit"].loc[0:1] = "Mt CO2/yr"
aggregate_name = "agg"
assert aggregate_name not in test_db_co2.variables().values
component_ratio = ["Emissions|HFC|C2F6", "Emissions|HFC|C5F12"]
consistent_vals = _construct_consistent_values(aggregate_name,
component_ratio,
test_db_co2)
assert aggregate_name in consistent_vals["variable"].values
consistent_vals = consistent_vals.timeseries()
timeseries_data = test_db_co2.timeseries()
assert all([
np.allclose(
consistent_vals.iloc[0].iloc[ind],
timeseries_data.iloc[0].iloc[ind] +
timeseries_data.iloc[1].iloc[ind],
) for ind in range(len(timeseries_data.iloc[0]))
])
# We also require that the output units are '-equiv'
assert all(y == "Mt CO2-equiv/yr"
for y in consistent_vals.index.get_level_values("unit"))
def infill_composite_values(df, composite_dic=None):
"""
Constructs a series of aggregate variables, calculated as the sums of variables
that have been reported. If given factors terms too, the terms will be multiplied
by the factors before summing.
Parameters
----------
df : :obj:`pyam.IamDataFrame`
Input data from which to construct consistent values. This is assumed to be
fully infilled. This will not be checked.
composite_dic : dict {str: list[str] or dict{str: float}}
Key: The variable names of the composite. Value: The variable names of the
constituents, which may include wildcards ('*'). Optionally, these may be
dictionaries of the names to factors, which we multiply the numbers by before
summing them. Defaults to a list of PFC, HFC, F-Gases, CO2 and Kyoto gases.
Returns
-------
:obj:`pyam.IamDataFrame`
:obj:`pyam.IamDataFrame` containing the composite values.
"""
if composite_dic is None:
composite_dic = {
"Emissions|PFC": [
"Emissions*|CF4",
"Emissions*|C2F6",
"Emissions*|C3F8",
"Emissions*|C4F10",
"Emissions*|C5F12",
"Emissions*|C6F14",
"Emissions*|C7F16",
"Emissions*|C8F18",
],
"Emissions|HFC": ["Emissions|HFC*"],
"Emissions|F-Gases": ["Emissions|PFC", "Emissions|HFC", "Emissions|SF6",],
"Emissions|Kyoto Gases (AR5-GWP100)": [
"Emissions|CO2",
"Emissions|CH4",
"Emissions|N2O",
"Emissions|F-Gases",
],
}
# Do a simple test to ensure we have any relevant data. This does not prevent
# problems from missing subsets of data.
to_delete = []
# Disable core logging to prevent warnings about empty filters
logging.getLogger("pyam.core").setLevel(logging.CRITICAL)
for composite, composite_variables in composite_dic.items():
if df.filter(variable=composite_variables).data.empty:
logger.warning("No data found for {}".format(composite_variables))
to_delete.append(composite)
logging.getLogger("pyam.core").setLevel(logging.WARNING)
for x in to_delete:
composite_dic.pop(x)
# If the composite variables already exist, remove them first
df = df.filter(variable=composite_dic.keys(), keep=False)
for composite, composite_variables in composite_dic.items():
if isinstance(composite_variables, dict):
temp_df = df.filter(variable=[composite] + list(composite_variables.keys()))
for contributor, factor in composite_variables.items():
temp_df.data.loc[
temp_df.data["variable"] == contributor, "value"
] *= factor
composite_df = _construct_consistent_values(
composite, composite_variables, temp_df
)
else:
composite_df = _construct_consistent_values(
composite, composite_variables, df
)
try:
to_return.append(composite_df)
except NameError:
to_return = composite_df
return to_return