def main():
num_points = 100
fix_noise = False
bounds = obj_fun.get_bounds()
model_bo = bo.BO(bounds, debug=True)
X_init = model_bo.get_initials('uniform', num_points)
X_test = utils_common.get_grids(bounds, 50)
mu, sigma, Sigma = gp.predict_with_optimized_hyps(
X_init,
fun_target(X_init),
X_test,
str_optimizer_method='Nelder-Mead',
fix_noise=fix_noise,
debug=True)
def main():
num_train = 200
num_test = 1000
X_train = np.random.randn(num_train, 1) * 5.0
Y_train = np.cos(X_train) + 10.0
X_test = np.linspace(-10, 10, num_test)
X_test = X_test.reshape((num_test, 1))
Y_test = np.cos(X_test) + 10.0
mu, sigma, Sigma = gp.predict_with_optimized_hyps(X_train,
Y_train,
X_test,
debug=True)
utils_plotting.plot_gp_via_distribution(X_train, Y_train, X_test, mu,
sigma, Y_test,
'test_optimized_many_points')
def main(str_cov):
np.random.seed(42)
X_train = np.array([
[-3.0],
[-1.0],
[3.0],
[1.0],
[2.0],
])
Y_train = np.cos(X_train) + np.random.randn(X_train.shape[0], 1) * 0.2
num_test = 200
X_test = np.linspace(-3, 3, num_test)
X_test = X_test.reshape((num_test, 1))
Y_test = np.cos(X_test)
mu, sigma, Sigma = gp.predict_with_optimized_hyps(X_train, Y_train, X_test, str_cov=str_cov, fix_noise=False, debug=True)
utils_plotting.plot_gp_via_distribution(X_train, Y_train, X_test, mu, sigma, Y_test, path_save=PATH_SAVE, str_postfix='cos_' + str_cov)
def main(fun_prior, str_prior):
X_train = np.array([
[-3.0],
[-2.0],
[-1.0],
])
Y_train = np.cos(X_train) + 2.0
num_test = 200
X_test = np.linspace(-3, 6, num_test)
X_test = X_test.reshape((num_test, 1))
Y_test = np.cos(X_test) + 2.0
mu, sigma, Sigma = gp.predict_with_optimized_hyps(X_train,
Y_train,
X_test,
prior_mu=fun_prior)
utils_plotting.plot_gp_via_distribution(
X_train, Y_train, X_test, mu, sigma, Y_test, PATH_SAVE,
'optimized_prior_{}'.format(str_prior))
def main(scale, str_postfix):
X_train = np.array([
[-3.0],
[-2.0],
[-1.0],
[2.0],
[1.2],
[1.1],
])
Y_train = np.cos(X_train) * scale
num_test = 200
X_test = np.linspace(-3, 3, num_test)
X_test = X_test.reshape((num_test, 1))
Y_test = np.cos(X_test) * scale
mu, sigma, Sigma = gp.predict_with_optimized_hyps(X_train,
Y_train,
X_test,
fix_noise=False,
debug=True)
utils_plotting.plot_gp_via_distribution(
X_train, Y_train, X_test, mu, sigma, Y_test, PATH_SAVE,
'test_optimized_{}_y'.format(str_postfix))
def thompson_sampling_gp_iteration(range_X: np.ndarray,
X: np.ndarray, Y: np.ndarray,
normalize_Y: bool=constants.NORMALIZE_RESPONSE,
str_sampling_method: str='sobol',
num_samples: int=200,
debug: bool=False,
) -> np.ndarray:
"""
It chooses the next query point via Thompson sampling.
:param range_X: bounds for a search space. Shape: (d, 2).
:type range_X: numpy.ndarray
:param X: inputs. Shape: (n, d).
:type X: numpy.ndarray
:param Y: outputs. Shape: (n, 1).
:type Y: numpy.ndarray
:param normalize_Y: flag for normalizing responses.
:type normalize_Y: bool., optional
:param str_sampling_method: the name of sampling method.
:type str_sampling_method: str., optional
:param num_samples: the number of samples.
:type num_samples: int., optional
:param debug: flag for a debug option.
:type debug: bool., optional
:returns: the next point. Shape: (d, ).
:rtype: numpy.ndarray
:raises: AssertionError, ValueError
"""
assert isinstance(range_X, np.ndarray)
assert isinstance(X, np.ndarray)
assert isinstance(Y, np.ndarray)
assert isinstance(normalize_Y, bool)
assert isinstance(str_sampling_method, str)
assert isinstance(num_samples, int)
assert isinstance(debug, bool)
assert len(range_X.shape) == 2
assert len(X.shape) == 2
assert len(Y.shape) == 2
assert X.shape[0] == Y.shape[0]
assert range_X.shape[0] == X.shape[1]
assert range_X.shape[1] == 2
str_cov = 'matern52'
prior_mu = None
str_optimizer_method_gp = 'BFGS'
# use_ard = True
if normalize_Y:
if debug:
logger.debug('Responses are normalized.')
Y = utils_bo.normalize_min_max(Y)
model_bo = bo.BOwGP(range_X)
X_test = model_bo.get_samples(str_sampling_method, num_samples=num_samples)
mu_Xs, _, Sigma_Xs = gp.predict_with_optimized_hyps(X, Y, X_test,
str_cov=str_cov, str_optimizer_method=str_optimizer_method_gp,
prior_mu=prior_mu, debug=debug)
mu_Xs = np.squeeze(mu_Xs, axis=1)
Y_sampled = None
list_jitters = [0.0, 1e-4, 1e-2, 1e0, 1e1, 1e2, 1e3, 1e4]
for jitter_cov in list_jitters:
try:
Sigma_Xs_ = Sigma_Xs + jitter_cov * np.eye(Sigma_Xs.shape[0])
Y_sampled = gp.sample_functions(mu_Xs, Sigma_Xs_, num_samples=1)
break
except ValueError: # pragma: no cover
pass
if Y_sampled is None: # pragma: no cover
raise ValueError('jitter_cov is not large enough.')
ind_min = np.argmin(Y_sampled[:, 0])
next_point = X_test[ind_min]
return next_point
def test_predict_with_optimized_hyps():
np.random.seed(42)
dim_X = 2
num_X = 5
num_X_test = 20
X = np.random.randn(num_X, dim_X)
Y = np.random.randn(num_X, 1)
X_test = np.random.randn(num_X_test, dim_X)
prior_mu = None
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X,
Y,
X_test,
str_cov='se',
prior_mu='abc')
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X,
Y,
X_test,
str_cov=1,
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X,
Y,
1,
str_cov='se',
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X,
1,
X_test,
str_cov='se',
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(1,
Y,
X_test,
str_cov='se',
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(np.random.randn(num_X, 1),
Y,
X_test,
str_cov='se',
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(np.random.randn(10, dim_X),
Y,
X_test,
str_cov='se',
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X,
np.random.randn(10, 1),
X_test,
str_cov='se',
prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X,
Y,
X_test,
str_optimizer_method=1)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X, Y, X_test, fix_noise=1)
with pytest.raises(AssertionError) as error:
package_target.predict_with_optimized_hyps(X, Y, X_test, debug=1)
mu_test, sigma_test, Sigma_test = package_target.predict_with_optimized_hyps(
X, Y, X_test, debug=True)
print(mu_test)
print(sigma_test)
print(Sigma_test)