def test_interface_returns_same_as_cpp(self):
"""Test that the /gp/ei endpoint does the same thing as the C++ interface."""
tolerance = 1.0e-11
for test_case in self.gp_test_environments:
python_domain, python_gp = test_case
python_cov, historical_data = python_gp.get_core_data_copy()
cpp_cov = SquareExponential(python_cov.hyperparameters)
cpp_gp = GaussianProcess(cpp_cov, historical_data)
points_to_evaluate = python_domain.generate_uniform_random_points_in_domain(10)
# EI from C++
expected_improvement_evaluator = ExpectedImprovement(cpp_gp, None)
# TODO(GH-99): Change test case to have the right shape:
# (num_to_evaluate, num_to_sample, dim)
# Here we assume the shape is (num_to_evaluate, dim) so we insert an axis, making num_to_sample = 1.
# Also might be worth testing more num_to_sample values (will require manipulating C++ RNG state).
cpp_expected_improvement = expected_improvement_evaluator.evaluate_at_point_list(
points_to_evaluate[:, numpy.newaxis, :]
)
# EI from REST
json_payload = self._build_json_payload(
python_domain, python_cov, historical_data, points_to_evaluate.tolist()
)
resp = self.testapp.post(self.endpoint, json_payload)
resp_schema = GpEiResponse()
resp_dict = resp_schema.deserialize(json.loads(resp.body))
rest_expected_improvement = numpy.asarray(resp_dict.get("expected_improvement"))
self.assert_vector_within_relative(rest_expected_improvement, cpp_expected_improvement, tolerance)
def gen_sample_from_qei(gp,search_domain,sgd_params,num_samples, num_mc=1e4, lhc_iter=2e4):
qEI = ExpectedImprovement(gaussian_process=gp, num_mc_iterations=int(num_mc))
optimizer = cGDOpt(search_domain, qEI, sgd_params, int(lhc_iter))
points_to_sample = meio(optimizer, None, num_samples, use_gpu=False, which_gpu=0,
max_num_threads=8)
qEI.set_current_point(points_to_sample[0])
return points_to_sample, qEI.compute_expected_improvement()
def gp_ei_view(self):
"""Endpoint for gp_ei POST requests.
.. http:post:: /gp/ei
Calculates the Expected Improvement (EI) of a set of points, given historical data.
:input: :class:`moe.views.schemas.GpEiRequest`
:output: :class:`moe.views.schemas.GpEiResponse`
:status 201: returns a response
:status 500: server error
"""
params = self.get_params_from_request()
# TODO(GH-99): Change REST interface to give points_to_evaluate with shape
# (num_to_evaluate, num_to_sample, dim)
# Here we assume the shape is (num_to_evaluate, dim) so we insert an axis, making num_to_sample = 1.
points_to_evaluate = numpy.array(params.get('points_to_evaluate'))[:, numpy.newaxis, :]
points_being_sampled = numpy.array(params.get('points_being_sampled'))
num_mc_iterations = params.get('mc_iterations')
max_num_threads = params.get('max_num_threads')
gaussian_process = _make_gp_from_params(params)
expected_improvement_evaluator = ExpectedImprovement(
gaussian_process,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
with timing_context(EI_COMPUTATION_TIMING_LABEL):
expected_improvement = expected_improvement_evaluator.evaluate_at_point_list(
points_to_evaluate,
max_num_threads=max_num_threads,
)
return self.form_response({
'endpoint': self._route_name,
'expected_improvement': expected_improvement.tolist(),
})
def gp_ei_view(self):
"""Endpoint for gp_ei POST requests.
.. http:post:: /gp/ei
Calculates the Expected Improvement (EI) of a set of points, given historical data.
:input: :class:`moe.views.schemas.rest.GpEiRequest`
:output: :class:`moe.views.schemas.rest.GpEiResponse`
:status 200: returns a response
:status 500: server error
"""
params = self.get_params_from_request()
# TODO(GH-99): Change REST interface to give points_to_evaluate with shape
# (num_to_evaluate, num_to_sample, dim)
# Here we assume the shape is (num_to_evaluate, dim) so we insert an axis, making num_to_sample = 1.
points_to_evaluate = numpy.array(params.get('points_to_evaluate'))[:, numpy.newaxis, :]
points_being_sampled = numpy.array(params.get('points_being_sampled'))
num_mc_iterations = params.get('mc_iterations')
max_num_threads = params.get('max_num_threads')
gaussian_process = _make_gp_from_params(params)
expected_improvement_evaluator = ExpectedImprovement(
gaussian_process,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
with timing_context(EI_COMPUTATION_TIMING_LABEL):
expected_improvement = expected_improvement_evaluator.evaluate_at_point_list(
points_to_evaluate,
max_num_threads=max_num_threads,
)
return self.form_response({
'endpoint': self._route_name,
'expected_improvement': expected_improvement.tolist(),
})
def test_interface_returns_same_as_cpp(self):
"""Test that the /gp/ei endpoint does the same thing as the C++ interface."""
tolerance = 1.0e-11
for test_case in self.gp_test_environments:
python_domain, python_gp = test_case
python_cov, historical_data = python_gp.get_core_data_copy()
cpp_cov = SquareExponential(python_cov.hyperparameters)
cpp_gp = GaussianProcess(cpp_cov, historical_data)
points_to_evaluate = python_domain.generate_uniform_random_points_in_domain(
10)
# EI from C++
expected_improvement_evaluator = ExpectedImprovement(
cpp_gp,
None,
)
# TODO(GH-99): Change test case to have the right shape:
# (num_to_evaluate, num_to_sample, dim)
# Here we assume the shape is (num_to_evaluate, dim) so we insert an axis, making num_to_sample = 1.
# Also might be worth testing more num_to_sample values (will require manipulating C++ RNG state).
cpp_expected_improvement = expected_improvement_evaluator.evaluate_at_point_list(
points_to_evaluate[:, numpy.newaxis, :], )
# EI from REST
json_payload = self._build_json_payload(
python_domain, python_cov, historical_data,
points_to_evaluate.tolist())
resp = self.testapp.post(self.endpoint, json_payload)
resp_schema = GpEiResponse()
resp_dict = resp_schema.deserialize(json.loads(resp.body))
rest_expected_improvement = numpy.asarray(
resp_dict.get('expected_improvement'))
self.assert_vector_within_relative(
rest_expected_improvement,
cpp_expected_improvement,
tolerance,
)
def compute_next_points_to_sample_response(self, params, optimizer_method_name, route_name, *args, **kwargs):
"""Compute the next points to sample (and their expected improvement) using optimizer_method_name from params in the request.
.. Warning:: Attempting to find ``num_to_sample`` optimal points with
``num_sampled < num_to_sample`` historical points sampled can cause matrix issues under
some conditions. Try requesting ``num_to_sample < num_sampled`` points for better
performance. To bootstrap more points try sampling at random, or from a grid.
:param request_params: the deserialized REST request, containing ei_optimizer_parameters and gp_historical_info
:type request_params: a deserialized self.request_schema object as a dict
:param optimizer_method_name: the optimization method to use
:type optimizer_method_name: string in :const:`moe.views.constant.NEXT_POINTS_OPTIMIZER_METHOD_NAMES`
:param route_name: name of the route being called
:type route_name: string in :const:`moe.views.constant.ALL_REST_ROUTES_ROUTE_NAME_TO_ENDPOINT`
:param ``*args``: extra args to be passed to optimization method
:param ``**kwargs``: extra kwargs to be passed to optimization method
"""
points_being_sampled = numpy.array(params.get('points_being_sampled'))
num_to_sample = params.get('num_to_sample')
num_mc_iterations = params.get('mc_iterations')
max_num_threads = params.get('max_num_threads')
gaussian_process = _make_gp_from_params(params)
expected_improvement_evaluator = ExpectedImprovement(
gaussian_process,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
ei_opt_status = {}
# TODO(GH-89): Make the optimal_learning library handle this case 'organically' with
# reasonable default behavior and remove hacks like this one.
if gaussian_process.num_sampled == 0:
# If there is no initial data we bootstrap with random points
py_domain = _make_domain_from_params(params, python_version=True)
next_points = py_domain.generate_uniform_random_points_in_domain(num_to_sample)
ei_opt_status['found_update'] = True
else:
# Calculate the next best points to sample given the historical data
domain = _make_domain_from_params(params)
optimizer_class, optimizer_parameters, num_random_samples = _make_optimizer_parameters_from_params(params)
expected_improvement_optimizer = optimizer_class(
domain,
expected_improvement_evaluator,
optimizer_parameters,
num_random_samples=num_random_samples,
)
opt_method = getattr(moe.optimal_learning.python.cpp_wrappers.expected_improvement, optimizer_method_name)
with timing_context(EPI_OPTIMIZATION_TIMING_LABEL):
next_points = opt_method(
expected_improvement_optimizer,
optimizer_parameters.num_multistarts,
num_to_sample,
max_num_threads=max_num_threads,
status=ei_opt_status,
*args,
**kwargs
)
# TODO(GH-285): Use analytic q-EI here
# TODO(GH-314): Need to resolve poential issue with NaNs before using q-EI here
# It may be sufficient to check found_update == False in ei_opt_status
# and then use q-EI, else set EI = 0.
expected_improvement_evaluator.current_point = next_points
# The C++ may fail to compute EI with some ``next_points`` inputs (e.g.,
# ``points_to_sample`` and ``points_begin_sampled`` are too close
# together or too close to ``points_sampled``). We catch the exception when this happens
# and attempt a more numerically robust option.
try:
expected_improvement = expected_improvement_evaluator.compute_expected_improvement()
except Exception as exception:
self.log.info('EI computation failed, probably b/c GP-variance matrix is singular. Error: {0:s}'.format(exception))
# ``_compute_expected_improvement_monte_carlo`` in
# :class:`moe.optimal_learning.python.python_version.expected_improvement.ExpectedImprovement`
# has a more reliable (but very expensive) way to deal with singular variance matrices.
python_ei_eval = PythonExpectedImprovement(
expected_improvement_evaluator._gaussian_process,
points_to_sample=next_points,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
expected_improvement = python_ei_eval.compute_expected_improvement(force_monte_carlo=True)
return self.form_response({
'endpoint': route_name,
'points_to_sample': next_points.tolist(),
'status': {
'expected_improvement': expected_improvement,
'optimizer_success': ei_opt_status,
},
})
def compute_next_points_to_sample_response(self, params,
optimizer_method_name,
route_name, *args, **kwargs):
"""Compute the next points to sample (and their expected improvement) using optimizer_method_name from params in the request.
.. Warning:: Attempting to find ``num_to_sample`` optimal points with
``num_sampled < num_to_sample`` historical points sampled can cause matrix issues under
some conditions. Try requesting ``num_to_sample < num_sampled`` points for better
performance. To bootstrap more points try sampling at random, or from a grid.
:param request_params: the deserialized REST request, containing ei_optimizer_parameters and gp_historical_info
:type request_params: a deserialized self.request_schema object as a dict
:param optimizer_method_name: the optimization method to use
:type optimizer_method_name: string in :const:`moe.views.constant.NEXT_POINTS_OPTIMIZER_METHOD_NAMES`
:param route_name: name of the route being called
:type route_name: string in :const:`moe.views.constant.ALL_REST_ROUTES_ROUTE_NAME_TO_ENDPOINT`
:param ``*args``: extra args to be passed to optimization method
:param ``**kwargs``: extra kwargs to be passed to optimization method
"""
points_being_sampled = numpy.array(params.get('points_being_sampled'))
num_to_sample = params.get('num_to_sample')
num_mc_iterations = params.get('mc_iterations')
max_num_threads = params.get('max_num_threads')
gaussian_process = _make_gp_from_params(params)
ei_opt_status = {}
# TODO(GH-89): Make the optimal_learning library handle this case 'organically' with
# reasonable default behavior and remove hacks like this one.
if gaussian_process.num_sampled == 0:
# If there is no initial data we bootstrap with random points
py_domain = _make_domain_from_params(params, python_version=True)
next_points = py_domain.generate_uniform_random_points_in_domain(
num_to_sample)
ei_opt_status['found_update'] = True
expected_improvement_evaluator = PythonExpectedImprovement(
gaussian_process,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
else:
# Calculate the next best points to sample given the historical data
optimizer_class, optimizer_parameters, num_random_samples = _make_optimizer_parameters_from_params(
params)
if optimizer_class == python_optimization.LBFGSBOptimizer:
domain = RepeatedDomain(
num_to_sample,
_make_domain_from_params(params, python_version=True))
expected_improvement_evaluator = PythonExpectedImprovement(
gaussian_process,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
mvndst_parameters=_make_mvndst_parameters_from_params(
params))
opt_method = getattr(
moe.optimal_learning.python.python_version.
expected_improvement, optimizer_method_name)
else:
domain = _make_domain_from_params(params, python_version=False)
expected_improvement_evaluator = ExpectedImprovement(
gaussian_process,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
opt_method = getattr(
moe.optimal_learning.python.cpp_wrappers.
expected_improvement, optimizer_method_name)
expected_improvement_optimizer = optimizer_class(
domain,
expected_improvement_evaluator,
optimizer_parameters,
num_random_samples=num_random_samples,
)
with timing_context(EPI_OPTIMIZATION_TIMING_LABEL):
next_points = opt_method(
expected_improvement_optimizer,
params.get('optimizer_info')
['num_multistarts'], # optimizer_parameters.num_multistarts,
num_to_sample,
max_num_threads=max_num_threads,
status=ei_opt_status,
*args,
**kwargs)
# TODO(GH-285): Use analytic q-EI here
# TODO(GH-314): Need to resolve poential issue with NaNs before using q-EI here
# It may be sufficient to check found_update == False in ei_opt_status
# and then use q-EI, else set EI = 0.
expected_improvement_evaluator.current_point = next_points
# The C++ may fail to compute EI with some ``next_points`` inputs (e.g.,
# ``points_to_sample`` and ``points_begin_sampled`` are too close
# together or too close to ``points_sampled``). We catch the exception when this happens
# and attempt a more numerically robust option.
try:
expected_improvement = expected_improvement_evaluator.compute_expected_improvement(
)
except Exception as exception:
self.log.info(
'EI computation failed, probably b/c GP-variance matrix is singular. Error: {0:s}'
.format(exception))
# ``_compute_expected_improvement_monte_carlo`` in
# :class:`moe.optimal_learning.python.python_version.expected_improvement.ExpectedImprovement`
# has a more reliable (but very expensive) way to deal with singular variance matrices.
python_ei_eval = PythonExpectedImprovement(
expected_improvement_evaluator._gaussian_process,
points_to_sample=next_points,
points_being_sampled=points_being_sampled,
num_mc_iterations=num_mc_iterations,
)
expected_improvement = python_ei_eval.compute_expected_improvement(
force_monte_carlo=True)
return self.form_response({
'endpoint': route_name,
'points_to_sample': next_points.tolist(),
'status': {
'expected_improvement': expected_improvement,
'optimizer_success': ei_opt_status,
},
})
