def test_quantify_propagate_uncertainty1(self):
'''
It tests the function quantify_propagate_uncertainty with rooney & biegler's model.
'''
from idaes.apps.uncertainty_propagation.examples.rooney_biegler import rooney_biegler_model, rooney_biegler_model_opt
variable_name = ['asymptote', 'rate_constant']
data = pd.DataFrame(data=[[1, 8.3], [2, 10.3], [3, 19.0], [4, 16.0],
[5, 15.6], [7, 19.8]],
columns=['hour', 'y'])
def SSE(model, data):
expr = sum((data.y[i] - model.response_function[data.hour[i]])**2
for i in data.index)
return expr
results = quantify_propagate_uncertainty(rooney_biegler_model,
rooney_biegler_model_opt,
data, variable_name, SSE)
assert results.obj == approx(4.331711213656886)
np.testing.assert_array_almost_equal(
results.theta, [19.142575284617866, 0.53109137696521])
assert list(results.theta.keys()) == ['asymptote', 'rate_constant']
np.testing.assert_array_almost_equal(results.gradient_f,
[0.99506259, 0.945148])
assert list(results.propagation_c) == []
np.testing.assert_array_almost_equal(results.dsdp.toarray(),
[[1., 0.], [0., 1.]])
np.testing.assert_array_almost_equal(
results.cov,
np.array([[6.30579403, -0.4395341], [-0.4395341, 0.04193591]]))
assert results.propagation_f == pytest.approx(5.45439337747349)
def test_quantify_propagate_uncertainty_NRTL(self):
'''
It tests the function quantify_propagate_uncertainty with IDAES NRTL model.
'''
from idaes.apps.uncertainty_propagation.examples.NRTL_model_scripts import NRTL_model, NRTL_model_opt
variable_name = [
"fs.properties.tau['benzene','toluene']",
"fs.properties.tau['toluene','benzene']"
]
current_path = os.path.dirname(os.path.realpath(__file__))
data = pd.read_csv(os.path.join(current_path, 'BT_NRTL_dataset.csv'))
def SSE(model, data):
expr = (
(float(data["vap_benzene"]) -
model.fs.flash.vap_outlet.mole_frac_comp[0, "benzene"])**2 +
(float(data["liq_benzene"]) -
model.fs.flash.liq_outlet.mole_frac_comp[0, "benzene"])**2)
return expr * 1E4
results = quantify_propagate_uncertainty(NRTL_model, NRTL_model_opt,
data, variable_name, SSE)
np.testing.assert_array_almost_equal(results.obj, 5.074968578304798)
np.testing.assert_array_almost_equal(
np.fromiter(results.theta.values(), dtype=float),
[-0.8987624, 1.41048611])
np.testing.assert_array_almost_equal(results.gradient_f[0],
[-0.19649493])
np.testing.assert_almost_equal(
results.cov,
np.array([[0.01194738, -0.02557055], [-0.02557055, 0.05490639]]))
assert results.propagation_f == pytest.approx(0.0021199499778127204)
def test_quantify_propagate_uncertainty2(self):
'''
This is the same test as test_quantify_propagate_uncertainty1,
but with the second argument of quantify_propagate_uncertainty as Pyomo Concrete Model.
'''
from idaes.apps.uncertainty_propagation.examples.rooney_biegler import rooney_biegler_model
variable_name = ['asymptote', 'rate_constant']
data = pd.DataFrame(data=[[1, 8.3], [2, 10.3], [3, 19.0], [4, 16.0],
[5, 15.6], [7, 19.8]],
columns=['hour', 'y'])
def SSE(model, data):
expr = sum((data.y[i] - model.response_function[data.hour[i]])**2
for i in data.index)
return expr
model_uncertain = ConcreteModel()
model_uncertain.asymptote = Var(initialize=15)
model_uncertain.rate_constant = Var(initialize=0.5)
model_uncertain.obj = Objective(
expr=model_uncertain.asymptote *
(1 - exp(-model_uncertain.rate_constant * 10)),
sense=minimize)
results = quantify_propagate_uncertainty(rooney_biegler_model,
model_uncertain, data,
variable_name, SSE)
assert results.obj == approx(4.331711213656886)
np.testing.assert_array_almost_equal(
np.fromiter(results.theta.values(), dtype=float),
[19.142575284617866, 0.53109137696521])
assert list(results.theta.keys()) == ['asymptote', 'rate_constant']
np.testing.assert_array_almost_equal(results.gradient_f,
[0.99506259, 0.945148])
assert list(results.propagation_c) == []
np.testing.assert_array_almost_equal(results.dsdp.toarray(),
[[1., 0.], [0., 1.]])
np.testing.assert_array_almost_equal(
results.cov,
np.array([[6.30579403, -0.4395341], [-0.4395341, 0.04193591]]))
assert results.propagation_f == pytest.approx(5.45439337747349)
def test_Exception1(self):
'''
It tests an ValueError when the tee is not bool for the function quantify_propagate_uncertainty with rooney & biegler's model.
'''
from idaes.apps.uncertainty_propagation.examples.rooney_biegler import rooney_biegler_model, rooney_biegler_model_opt
variable_name = ['asymptote', 'rate_constant']
data = pd.DataFrame(data=[[1, 8.3], [2, 10.3], [3, 19.0], [4, 16.0],
[5, 15.6], [7, 19.8]],
columns=['hour', 'y'])
def SSE(model, data):
expr = sum((data.y[i] - model.response_function[data.hour[i]])**2
for i in data.index)
return expr
tee = 1
with pytest.raises(TypeError):
results = quantify_propagate_uncertainty(rooney_biegler_model,
rooney_biegler_model_opt,
data, variable_name, SSE,
tee)
def test_quantify_propagate_uncertainty_NRTL_exception(self):
'''
It tests an exception error when the ipopt fails for the function quantify_propagate_uncertainty with IDAES NRTL model.
'''
from idaes.apps.uncertainty_propagation.examples.NRTL_model_scripts import NRTL_model, NRTL_model_opt_infeasible
variable_name = [
"fs.properties.tau['benzene','toluene']",
"fs.properties.tau['toluene','benzene']"
]
current_path = os.path.dirname(os.path.realpath(__file__))
data = pd.read_csv(os.path.join(current_path, 'BT_NRTL_dataset.csv'))
def SSE(model, data):
expr = (
(float(data["vap_benzene"]) -
model.fs.flash.vap_outlet.mole_frac_comp[0, "benzene"])**2 +
(float(data["liq_benzene"]) -
model.fs.flash.liq_outlet.mole_frac_comp[0, "benzene"])**2)
return expr * 1E4
with pytest.raises(Exception):
results = quantify_propagate_uncertainty(
NRTL_model, NRTL_model_opt_infeasible, data, variable_name,
SSE)
# Solutions of Sandia, LLC, Carnegie Mellon University, West Virginia
# University Research Corporation, et al. All rights reserved.
#
# Please see the files COPYRIGHT.txt and LICENSE.txt for full copyright and
# license information, respectively. Both files are also available online
# at the URL "https://github.com/IDAES/idaes-pse".
##############################################################################
import sys
import os
sys.path.append(os.path.abspath('..')) # current folder is ~/examples
from idaes.apps.uncertainty_propagation.uncertainties import quantify_propagate_uncertainty
import pandas as pd
from idaes.apps.uncertainty_propagation.examples.rooney_biegler import rooney_biegler_model,rooney_biegler_model_opt
variable_name = ['asymptote', 'rate_constant']
data = pd.DataFrame(data=[[1,8.3],
[2,10.3],
[3,19.0],
[4,16.0],
[5,15.6],
[7,19.8]],
columns=['hour', 'y'])
def SSE(model, data):
expr = sum((data.y[i] - model.response_function[data.hour[i]])**2 for i in data.index)
return expr
results = quantify_propagate_uncertainty(rooney_biegler_model,rooney_biegler_model_opt, data, variable_name, SSE)
# Please see the files COPYRIGHT.txt and LICENSE.txt for full copyright and
# license information, respectively. Both files are also available online
# at the URL "https://github.com/IDAES/idaes-pse".
##############################################################################
import sys
import os
sys.path.append(os.path.abspath('..')) # current folder is ~/examples
from idaes.apps.uncertainty_propagation.uncertainties import quantify_propagate_uncertainty
import pandas as pd
from idaes.apps.uncertainty_propagation.examples.NRTL_model_scripts import NRTL_model, NRTL_model_opt
variable_name = [
"fs.properties.tau['benzene', 'toluene']",
"fs.properties.tau['toluene','benzene']"
]
current_path = os.path.dirname(os.path.realpath(__file__))
data = pd.read_csv(os.path.join(current_path, 'BT_NRTL_dataset.csv'))
def SSE(model, data):
expr = ((float(data["vap_benzene"]) -
model.fs.flash.vap_outlet.mole_frac_comp[0, "benzene"])**2 +
(float(data["liq_benzene"]) -
model.fs.flash.liq_outlet.mole_frac_comp[0, "benzene"])**2)
return expr * 1E4
results = quantify_propagate_uncertainty(NRTL_model, NRTL_model_opt, data,
variable_name, SSE)
