def _optimize_objective(self, fun_acquisition, X_train, Y_train, X_test,
cov_X_X, inv_cov_X_X, hyps):
X_test = np.atleast_2d(X_test)
pred_mean, pred_std = gp.predict_test_(X_train,
Y_train,
X_test,
cov_X_X,
inv_cov_X_X,
hyps,
str_cov=self.str_cov,
prior_mu=self.prior_mu,
debug=self.debug)
# no matter which acquisition functions are given, we input pred_mean, pred_std, and Y_train.
acquisitions = fun_acquisition(pred_mean=pred_mean.flatten(),
pred_std=pred_std.flatten(),
Y_train=Y_train)
return acquisitions
def main():
str_acq = 'aei'
num_iter = 10
X_train = np.array([
[-5],
[-1],
[1],
[2],
])
num_init = X_train.shape[0]
model_bo = bo.BO(np.array([[-6., 6.]]), str_acq=str_acq)
X_test = np.linspace(-6, 6, 400)
X_test = np.reshape(X_test, (400, 1))
for ind_ in range(1, num_iter + 1):
Y_train = fun_target(X_train)
next_x, _, _, cov_X_X, inv_cov_X_X, hyps = model_bo.optimize(
X_train, fun_target(X_train), str_initial_method='uniform')
mu_test, sigma_test = gp.predict_test_(X_train, Y_train, X_test,
cov_X_X, inv_cov_X_X, hyps)
acq_test = acquisition.aei(mu_test.flatten(), sigma_test.flatten(),
Y_train, hyps['noise'])
acq_test = np.expand_dims(acq_test, axis=1)
X_train = np.vstack((X_train, next_x))
Y_train = fun_target(X_train)
utils_plotting.plot_bo_step(X_train,
Y_train,
X_test,
fun_target(X_test),
mu_test,
sigma_test,
path_save=PATH_SAVE,
str_postfix='bo_{}_'.format(str_acq) +
str(ind_),
int_init=num_init)
utils_plotting.plot_bo_step_acq(X_train,
Y_train,
X_test,
fun_target(X_test),
mu_test,
sigma_test,
acq_test,
path_save=PATH_SAVE,
str_postfix='bo_{}_'.format(str_acq) +
str(ind_),
int_init=num_init,
is_acq_axis_small=True)
def _optimize_objective(self, fun_acquisition, X_train, Y_train, X_test,
cov_X_X, inv_cov_X_X, hyps):
"""
It returns acquisition function values over `X_test`.
:param fun_acquisition: acquisition function.
:type fun_acquisition: function
:param X_train: inputs. Shape: (n, d) or (n, m, d).
:type X_train: numpy.ndarray
:param Y_train: outputs. Shape: (n, 1).
:type Y_train: numpy.ndarray
:param X_test: inputs. Shape: (l, d) or (l, m, d).
:type X_test: numpy.ndarray
:param cov_X_X: kernel matrix over `X_train`. Shape: (n, n).
:type cov_X_X: numpy.ndarray
:param inv_cov_X_X: kernel matrix inverse over `X_train`. Shape: (n, n).
:type inv_cov_X_X: numpy.ndarray
:param hyps: dictionary of hyperparameters for Gaussian process.
:type hyps: dict.
:returns: acquisition function values over `X_test`. Shape: (l, ).
:rtype: numpy.ndarray
"""
X_test = np.atleast_2d(X_test)
pred_mean, pred_std, _ = gp.predict_test_(X_train,
Y_train,
X_test,
cov_X_X,
inv_cov_X_X,
hyps,
str_cov=self.str_cov,
prior_mu=self.prior_mu,
debug=self.debug)
# no matter which acquisition functions are given, we input pred_mean, pred_std, and Y_train.
acquisitions = fun_acquisition(pred_mean=pred_mean.flatten(),
pred_std=pred_std.flatten(),
Y_train=Y_train)
return acquisitions
def test_predict_test_():
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
cov_X_X, inv_cov_X_X, hyps = gp.get_optimized_kernel(X, Y, prior_mu, 'se')
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu='abc')
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, cov_X_X, inv_cov_X_X, hyps, str_cov=1, prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, cov_X_X, inv_cov_X_X, 1, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, cov_X_X, 1, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, 1, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, 1, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, 1, X_test, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(1, Y, X_test, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(np.random.randn(num_X, 1), Y, X_test, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(np.random.randn(10, dim_X), Y, X_test, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, np.random.randn(10, 1), X_test, cov_X_X, inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, np.random.randn(3, 3), inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, np.random.randn(10), inv_cov_X_X, hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, cov_X_X, np.random.randn(10), hyps, str_cov='se', prior_mu=prior_mu)
with pytest.raises(AssertionError) as error:
gp.predict_test_(X, Y, X_test, np.random.randn(10), np.random.randn(10), hyps, str_cov='se', prior_mu=prior_mu)
