def test_regression_hdmr_case3():
problem = {
'num_vars': 5,
'names': ['x1', 'x2', 'x3', 'x4', 'x5'],
'bounds': [[0, 1] * 5]
}
# Generate correlated samples
mean = np.zeros((problem['num_vars']))
cov = [[1, 0.6, 0.2, 0, 0], [0.6, 1, 0.2, 0, 0], [0.2, 0.2, 1, 0, 0],
[0, 0, 0, 1, 0.2], [0, 0, 0, 0.2, 1]]
X = np.random.multivariate_normal(mean, cov, 10000)
Y = linear_model_2.evaluate(X)
options = {
'maxorder': 2,
'maxiter': 100,
'm': 2,
'K': 1,
'R': 10000,
'alpha': 0.95,
'lambdax': 0.01,
'print_to_console': False
}
Si = hdmr.analyze(problem, X, Y, **options)
assert_allclose(Si['Sa'][0:problem['num_vars']],
[0.28, 0.17, 0.10, 0.04, 0.02],
atol=5e-2,
rtol=1e-1)
assert_allclose(Si['Sb'][0:problem['num_vars']],
[0.16, 0.16, 0.06, 0.00, 0.00],
atol=5e-2,
rtol=1e-1)
def test_regression_hdmr_case1():
problem = {
'num_vars': 5,
'names': ['x1', 'x2', 'x3', 'x4', 'x5'],
'bounds': [[0, 1] * 5]
}
X = latin.sample(problem, 10000)
Y = linear_model_1.evaluate(X)
options = {
'maxorder': 2,
'maxiter': 100,
'm': 2,
'K': 1,
'R': 10000,
'alpha': 0.95,
'lambdax': 0.01,
'print_to_console': False
}
Si = hdmr.analyze(problem, X, Y, **options)
assert_allclose(Si['Sa'][0:problem['num_vars']], [0.20] * 5,
atol=5e-2,
rtol=1e-1)
assert_allclose(Si['ST'][0:problem['num_vars']], [0.20] * 5,
atol=5e-2,
rtol=1e-1)
def test_regression_hdmr_ishigami():
param_file = 'src/SALib/test_functions/params/Ishigami.txt'
problem = read_param_file(param_file)
X = latin.sample(problem, 10000)
Y = Ishigami.evaluate(X)
options = {
'maxorder': 2,
'maxiter': 100,
'm': 4,
'K': 1,
'R': 10000,
'alpha': 0.95,
'lambdax': 0.01,
'print_to_console': False
}
Si = hdmr.analyze(problem, X, Y, **options)
assert_allclose(Si['Sa'][0:problem['num_vars']], [0.31, 0.44, 0.00],
atol=5e-2,
rtol=1e-1)
assert_allclose(Si['ST'][0:problem['num_vars']], [0.55, 0.44, 0.24],
atol=5e-2,
rtol=1e-1)
sigma = np.var(Y) / 100
# SALib-HDMR options
options = {
'maxorder': 2,
'maxiter': 100,
'm': 4,
'K': 30,
'R': 500,
'alpha': 0.95,
'lambdax': 0.01,
'print_to_console': True,
'seed': 101
}
# Run SALib-HDMR
Si = hdmr.analyze(problem, X, Y, **options)
# Displays sensitivity results and HDMR training results
Si.plot()
# Generate samples
X = latin.sample(problem, 5000, seed=int(np.random.random() * 100))
# Run the "model"
Y = Ishigami.evaluate(X)
# Test emulator with new Y values.
# Can call `emulate()` without Y values, which will run the emulator
# Emulation results will be in Si["emulated"]
Si.emulate(X, Y)
# Displays results for both training and testing after emulator is tested.
def test_incorrect_lambdax():
problem, X = setup_samples()
Y = Ishigami.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X, Y, lambdax=11)
def test_dim_mismatch():
problem = {'num_vars': 2, 'names': ['x1', 'x2'], 'bounds': [[0, 1] * 2]}
X = latin.sample(problem, 10000)
Y = linear_model_1.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X, Y[:-2])
def test_incorrect_maxorder_setting():
problem = {'num_vars': 2, 'names': ['x1', 'x2'], 'bounds': [[0, 1] * 2]}
X = latin.sample(problem, 10000)
Y = linear_model_1.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X, Y, maxorder=5)
def test_over_bootstrap_sample_size():
problem, X = setup_samples()
Y = Ishigami.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X, Y, R=10001)
def test_incorrect_maxiter():
problem, X = setup_samples()
Y = Ishigami.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X, Y, maxiter=1005)
def test_bad_conf_level():
problem, X = setup_samples()
Y = Ishigami.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X, Y, alpha=1.02)
def test_insufficient_sample_size():
problem, X = setup_samples()
Y = Ishigami.evaluate(X)
with raises(RuntimeError):
hdmr.analyze(problem, X[:200], Y[:200])
