def __init__(self, covariance_function, historical_data):
"""Construct a GaussianProcess object that knows how to call C++ for evaluation of member functions.
:param covariance_function: covariance object encoding assumptions about the GP's behavior on our data
:type covariance_function: :class:`moe.optimal_learning.python.interfaces.covariance_interface.CovarianceInterface` subclass
(e.g., from :mod:`moe.optimal_learning.python.cpp_wrappers.covariance`).
:param historical_data: object specifying the already-sampled points, the objective value at those points, and the noise variance associated with each observation
:type historical_data: :class:`moe.optimal_learning.python.data_containers.HistoricalData` object
"""
self._covariance = copy.deepcopy(covariance_function)
self._historical_data = copy.deepcopy(historical_data)
# C++ will maintain its own copy of the contents of hyperparameters and historical_data
self._gaussian_process = C_GP.GaussianProcess(
cpp_utils.cppify_hyperparameters(self._covariance.hyperparameters),
cpp_utils.cppify(historical_data.points_sampled),
cpp_utils.cppify(historical_data.points_sampled_value),
cpp_utils.cppify(historical_data.points_sampled_noise_variance),
self._historical_data.dim,
self._historical_data.num_sampled,
)
def test_exception_thrown_from_cpp(self):
"""Test that a C++ interface function throws the expected type."""
with pytest.raises(C_GP.BoundsException):
C_GP.GaussianProcess([-1.0, [1.0]], [], [], [], 1, 0)