def do_xgb_MOE(num_points_to_sample, X_train, y_train, verbose=True, **kwargs):
# Finding Best XGB parameters using MOE
xgb_parameters = {}
# Range of XGBoost parameters that are optimized
exp_xgb = Experiment([[0.1, 1], [0.002, 1]], [0.01, 1]) # learning_rate_range = [0.1, 1]; n_estimators_range = [2, 1000] is normalized
# max_depth_range = [1, 100] is normalized
n_folds = 10
cv_folds = cross_validation.StratifiedKFold(y_train, n_folds=n_folds)
best_point = []
best_point_value = 0.
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp_xgb, rest_host='localhost', rest_port=6543, **kwargs)[0] # By default we only ask for one point
# Sample the point from objective function
xgb_parameters['learning_rate'] = next_point_to_sample[0]
xgb_parameters['n_estimators'] = int(round(next_point_to_sample[1]*1000))
xgb_parameters['max_depth'] = int(round(next_point_to_sample[2]*100))
acc_cv, prec_cv, rec_cv, cm_cv, cm_full_cv = xgboost_cross_validation(X_train, y_train, xgb_parameters, cv_folds)
value_of_next_point = acc_cv
if value_of_next_point > best_point_value:
best_point_value = value_of_next_point
best_point = next_point_to_sample
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp_xgb.historical_data.append_sample_points([SamplePoint(next_point_to_sample, -value_of_next_point, 0.0001)]) # We can add some noise
best_point[1] = int(round(best_point[1] * 1000))
best_point[2] = int(round(best_point[2] * 100))
return best_point, best_point_value
def do_rfc_MOE(num_points_to_sample, X_train, y_train, verbose=True, **kwargs):
exp_rfc = Experiment([[0.005, 1], [0.04, 1], [0.1, 1], [0.1, 1]]) # n_estimators_range = [5, 1000] and max_features_range = [2, 24] are normalized
# max_depth_range = [1, 10] & min_samples_leaf_range = [1, 10] are normalized
best_point = []
best_point_value = 0.
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp_rfc, rest_host='localhost', rest_port=6543, **kwargs)[0] # By default we only ask for one point
# Sample the point from objective function
n_estimators = int(round(next_point_to_sample[0] * 1000.0))
max_features = int(round(next_point_to_sample[1] * 50))
max_depth = int(round(next_point_to_sample[2] * 10))
min_samples_leaf = int(round(next_point_to_sample[3] * 10))
rfc = RandomForestClassifier(n_estimators=n_estimators, criterion='gini',
max_depth=max_depth, min_samples_split=2, min_samples_leaf=min_samples_leaf, min_weight_fraction_leaf=0.0,
max_features=max_features, max_leaf_nodes=None, bootstrap=True, oob_score=False, n_jobs=-1,
random_state=None, verbose=0, warm_start=False, class_weight=None)
score_cv = cross_validation.cross_val_score(rfc, X_train, y_train, cv=10, scoring='accuracy')
value_of next_point = np.mean(score_cv)
if value_of_next_point > best_point_value:
best_point_value = value_of_next_point
best_point = next_point_to_sample
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp_rfc.historical_data.append_sample_points([SamplePoint(next_point_to_sample, -value_of_next_point, 0.0001)]) # We can add some noise
def find_new_points_to_sample(experiment, num_points=1, verbose=False):
"""Find the optimal next point(s) to sample using expected improvement (via MOE).
:param experiment: an Experiment object containing the historical data and metadata MOE
needs to optimize
:type experiment: :class:`moe.easy_interface.experiment.Experiment`
:param num_points: number of new points (experiments) that we want MOE to suggest
:type num_points: int >= 1
:param verbose: whether to print status messages to stdout
:type verbose: bool
:return: the next point(s) to sample
:rtype: list of length ``num_points`` of coordinates (list of length ``dim``)
"""
if verbose:
print("Getting {0} new suggested point(s) to sample from MOE...".format(num_points))
# Query MOE for the next points to sample
next_points_to_sample = gp_next_points(
experiment,
method_route_name=GP_NEXT_POINTS_KRIGING_ROUTE_NAME,
covariance_info=COVARIANCE_INFO,
num_to_sample=num_points,
optimizer_info={
'optimizer_type': GRADIENT_DESCENT_OPTIMIZER,
},
)
if verbose:
print("Optimal points to sample next: {0}".format(next_points_to_sample))
return next_points_to_sample
def find_fastest_policy(trials, alpha_0=10, beta_0=10, ex_cutoff=250, perf_thresh=0.93,
students=None, test_path=TEST_PATH, make_plot=True):
"""
Find the best alpha/beta for the teaching policy.
Args:
trials: Number of teaching plans to try out (including first plan).
alpha_0: Starting alpha.
beta_0: Starting beta.
ex_cutoff: Max number of examples to show.
perf_thresh: The threshold of what is considered perfect.
students: The students to teach, will default to STUDENTS if non given.
test_path: The path of the file with test qs/answers.
make_plot: Whether to make a scatter plot of the history.
Returns: The best alpha/beta found.
"""
if students is None:
students = STUDENTS
test_qs, test_ans = plan_eval.read_test(test_path)
history = []
eval_policy = _create_perf_evaluator(ex_cutoff, perf_thresh, students, test_qs, test_ans, history)
experiment = Experiment([[0, ALPHA_MAX], [0, BETA_MAX]])
# Run the start experiment and evaluate.
experiment.historical_data.append_sample_points([eval_policy(alpha_0, beta_0)])
for i in xrange(trials-1):
print '--------TRIAL %d DONE--------' % (i + 1)
alpha, beta = gp_next_points(experiment)[0]
experiment.historical_data.append_sample_points([eval_policy(alpha, beta)])
best = min(history)
print len(history)
print len(history)
if make_plot:
plot_history(min(history), history)
return best
def find_accurate_policy(trials, alpha_0=10, beta_0=10, num_exs=250, students=None,
test_path=TEST_PATH, make_plot=False):
"""
Find the best alpha/beta for the teaching policy.
Args:
trials: Number of teaching plans to try out (including first plan).
alpha_0: Starting alpha.
beta_0: Starting beta.
num_exs: The number of examples given to students per teaching plan.
students: The students to teach, will default to STUDENTS if non given.
test_path: The path of the file with test qs/answers.
make_plot: Whether to make a scatter plot of the history.
Returns: The best alpha/beta found.
"""
if students is None:
students = STUDENTS
test_qs, test_ans = plan_eval.read_test(test_path)
history = []
eval_policy = _create_evaluator(num_exs, students, test_qs, test_ans, history)
experiment = Experiment([[0, ALPHA_MAX], [0, BETA_MAX]])
# Run the start experiment and evaluate.
experiment.historical_data.append_sample_points([eval_policy(alpha_0, beta_0)])
for i in xrange(trials-1):
print '--------TRIAL %d DONE--------' % (i + 1)
alpha, beta = gp_next_points(experiment)[0]
experiment.historical_data.append_sample_points([eval_policy(alpha, beta)])
best = max(history)
if make_plot:
plot_history(max(history), history)
return best
def run_example(num_points_to_sample=20, verbose=True, **kwargs):
"""Run the example, aksing MOE for ``num_points_to_sample`` optimal points to sample."""
exp = Experiment([[0, 2],
[0,
4]]) # 2D experiment, we build a tensor product domain
# Bootstrap with some known or already sampled point(s)
exp.historical_data.append_sample_points([
SamplePoint(
[0, 0], function_to_minimize([0, 0]), 0.05
), # Iterables of the form [point, f_val, f_var] are also allowed
])
# Sample num_points_to_sample points
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(
exp, **kwargs)[0] # By default we only ask for one point
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(
str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points(
[SamplePoint(next_point_to_sample, value_of_next_point,
0.01)]) # We can add some noise
def find_new_points_to_sample(experiment, num_points=1, verbose=False):
"""Find the optimal next point(s) to sample using expected improvement (via MOE).
:param experiment: an Experiment object containing the historical data and metadata MOE
needs to optimize
:type experiment: :class:`moe.easy_interface.experiment.Experiment`
:param num_points: number of new points (experiments) that we want MOE to suggest
:type num_points: int >= 1
:param verbose: whether to print status messages to stdout
:type verbose: bool
:return: the next point(s) to sample
:rtype: list of length ``num_points`` of coordinates (list of length ``dim``)
"""
if verbose:
print "Getting {0} new suggested point(s) to sample from MOE...".format(num_points)
# Query MOE for the next points to sample
next_points_to_sample = gp_next_points(
experiment,
method_route_name=GP_NEXT_POINTS_KRIGING_ROUTE_NAME,
covariance_info=COVARIANCE_INFO,
num_to_sample=num_points,
optimizer_info={
'optimizer_type': GRADIENT_DESCENT_OPTIMIZER,
},
)
if verbose:
print "Optimal points to sample next: {0}".format(next_points_to_sample)
return next_points_to_sample
def UnifiedBOExp(iter):
#bounds = [ [-3,.5], [-3,.5], [0,1], [0,1], [0,1] ]
#reduce dof for BO. Let's set hard threshold 0.95 and hard p(i) as 0.05
bounds = [ [-3,.5], [-3,.5], [0,1] ]
exp = Experiment(bounds)
objs = []
for c in range(iter):
#get list of next params
x = gp_next_points(exp, num_to_sample=1, covariance_info=moe_sq_exp)[0]
#put into dict
params = {'pg':x[0], 'ps':x[1], 'pi':0.05, 'pt':x[2], 'threshold':0.95}
#setup trial
student = Simulator(True)
trial = UnifiedTrial(student, params)
y = trial.run()
exp.historical_data.append_sample_points([SamplePoint(x, y, NOISE_VAL)])
objs.append(y)
print "x is: "
print x
print "objective: "
print y
print "predicted best point: "
#print moe_compute_best_pt_info(exp, moe_covariance_info)[0]
print ["%0.2f" % i for i in moe_compute_best_pt_info(exp, moe_covariance_info)[0]]
def BO_sample(self):
x = gp_next_points(self.exp)[0]
y = self.model.evaluate_params_from_BO(x)
np.set_printoptions(3)
print np.array(x)
print y
self.exp.historical_data.append_sample_points([SamplePoint(x,y,0.001)])
#print gp_hyper_opt(self.exp.historical_data.points_sampled)
"""pts = self.exp.historical_data.points_sampled
def _getNextParamFromMOE(self):
while True:
try:
next_points_to_sample = simple_endpoint.gp_next_points(self.moe)[0]
self._updateSettings(next_points_to_sample)
break
except:
pass
print "Error connecting to MOE. Retrying..."
time.sleep(2.0)
def _getNextParamFromMOE(self):
while True:
try:
next_points_to_sample = simple_endpoint.gp_next_points(
self.moe)[0]
self._updateSettings(next_points_to_sample)
break
except:
pass
print "Error connecting to MOE. Retrying..."
time.sleep(2.0)
def run_example(num_points_to_sample=200, verbose=False, **kwargs):
b = Branin()
bounds = b.get_meta_information()['bounds']
dimensions = len(bounds)
lower =np.array([i[0] for i in bounds])
upper =np.array([i[1] for i in bounds])
start_point = (upper-lower)/2
exp = Experiment([lower,upper])
exp.historical_data.append_sample_points([
SamplePoint(start_point, wrapper(start_point,b), 0.6)])
for _ in range(num_points_to_sample):
next_point_to_sample = gp_next_points(exp, **kwargs)[0]
value_of_next_point = wrapper(next_point_to_sample,b)
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
exp.historical_data.append_sample_points([SamplePoint(next_point_to_sample, value_of_next_point, 0.6)])
def do_xgb_train_MOE(num_points_to_sample,
X_train,
y_train,
verbose=True,
**kwargs):
# Finding Best XGB parameters using MOE
xgb_parameters = {}
xgb_parameters['objective'] = 'multi:softmax'
xgb_parameters['silent'] = 1
xgb_parameters['nthread'] = 4
xgb_parameters['num_class'] = 6
# Range of XGBoost parameters that are optimized
exp_xgb = Experiment([
[0.1, 1], [0.02, 1]
]) # eta_range = [0.1, 1]; max_depth_range = [2, 100] but it is normalized
num_round = 5
n_folds = 10
cv_folds = cross_validation.StratifiedKFold(y_train, n_folds=n_folds)
best_point = []
best_point_value = 0.
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(
exp_xgb, rest_host='localhost', rest_port=6543,
**kwargs)[0] # By default we only ask for one point
# Sample the point from objective function
xgb_parameters['eta'] = next_point_to_sample[0]
xgb_parameters['max_depth'] = int(round(next_point_to_sample[1] * 100))
acc_cv, prec_cv, rec_cv, cm_cv, cm_full_cv = xgboost_train_cross_validation(
X_train, y_train, xgb_parameters, num_round, cv_folds)
value_of_next_point = acc_cv
if value_of_next_point > best_point_value:
best_point_value = value_of_next_point
best_point = next_point_to_sample
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(
str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp_xgb.historical_data.append_sample_points(
[SamplePoint(next_point_to_sample, -value_of_next_point,
0.0001)]) # We can add some noise
best_point[1] = int(round(best_point[1] * 100))
return best_point, best_point_value
def search(self, num_hyperparameter_trials):
for trial in range(num_hyperparameter_trials):
# Select next hyperparameters with MOE, rounding hyperparameters that are integers
raw_hyperparameters = gp_next_points(self.experiment)[0]
hyperparameters = {name: int(round(value)) if isinstance(bounds[0], int) else value
for (name, bounds), value in
zip(self.grid.items(), raw_hyperparameters)}
# Try these hyperparameters
model = self.model_class(**ChainMap(hyperparameters, self.fixed_hyperparameters))
model.train(self.X_train, self.y_train, validation_data=self.validation_data)
score = model.score(self.metric, *self.validation_data)
# Record hyperparameters and validation loss
self.experiment.historical_data.append_sample_points(
[SamplePoint(point=hyperparameters.values(), value=score)])
# If these hyperparameters were the best so far, store this model
if self.maximize == (score > self.best_score):
self.best_score = score
self.best_model = model
self.best_hyperparameters = hyperparameters
def itterate():
print str(datetime.datetime.now())
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp)[0]
print next_point_to_sample
# By default we only ask for one point
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
print next_point_to_sample, value_of_next_point
# Store the sample
with open('TreeNode.csv', 'a') as csvfile:
csvfile.write(", ".join([str(k)for k in next_point_to_sample + [value_of_next_point]] ) +"\n")
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([SamplePoint(next_point_to_sample, offset + value_of_next_point * scale, variance)])
def run_example(num_to_sample=20, verbose=True, testapp=None, **kwargs):
"""Run the combined example."""
exp = Experiment([[0, 2], [0, 4]])
# Bootstrap with some known or already sampled point(s)
exp.historical_data.append_sample_points([
[[0, 0], function_to_minimize([0, 0]), 0.01], # sampled points have the form [point_as_a_list, objective_function_value, value_variance]
])
# Sample points
for i in range(num_to_sample):
covariance_info = {}
if i > 0 and i % 5 == 0:
covariance_info = gp_hyper_opt(exp.historical_data.to_list_of_sample_points(), testapp=testapp, **kwargs)
if verbose:
print "Updated covariance_info with {0:s}".format(str(covariance_info))
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(
exp,
covariance_info=covariance_info,
testapp=testapp,
**kwargs
)[0] # By default we only ask for one point
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([[next_point_to_sample, value_of_next_point, 0.01]]) # We can add some noise
points_to_evaluate = [[x, x] for x in numpy.arange(0, 1, 0.1)] # uniform grid of points
mean, var = gp_mean_var(
exp.historical_data.to_list_of_sample_points(), # Historical data to inform Gaussian Process
points_to_evaluate, # We will calculate the mean and variance of the GP at these points
testapp=testapp,
**kwargs
)
if verbose:
print "GP mean at (0, 0), (0.1, 0.1), ...: {0:s}".format(str(mean))
def run_example(num_points_to_sample=20, verbose=True, **kwargs):
"""Run the example, aksing MOE for ``num_points_to_sample`` optimal points to sample."""
exp = Experiment([[0, 2], [0, 4]]) # 2D experiment, we build a tensor product domain
# Bootstrap with some known or already sampled point(s)
exp.historical_data.append_sample_points([
SamplePoint([0, 0], function_to_minimize([0, 0]), 0.05), # Iterables of the form [point, f_val, f_var] are also allowed
])
# Sample num_points_to_sample points
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp, **kwargs)[0] # By default we only ask for one point
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([SamplePoint(next_point_to_sample, value_of_next_point, 0.01)]) # We can add some noise
def do_svc_linear_MOE(num_points_to_sample, X_train, y_train, verbose=True, **kwargs):
exp_svc_linear = Experiment([[1.0000e-05, 1.0]]) # C_range = [0.1, 10000] is divided to be in [0.1, 1] range
best_point = []
best_point_value = 0.
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with hnighest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp_svc_linear, rest_host='localhost', rest_port=6543, **kwargs)[0] # By default we only ask for one point
# Sample the point from objective function
C = next_point_to_sample[0] * 10000.0
svc_linear = svm.LinearSVC(penalty='l2', loss='squared_hinge', dual=True, tol=0.0001, C=C, multi_class='ovr',
fit_intercept=True, intercept_scaling=1, class_weight=None, verbose=0, random_state=None, max_iter=1000)
score_cv = cross_validation.cross_val_score(svc_linear, X_train, y_train, cv=10, scoring='accuracy')
value_of_next_point = np.mean(score_cv)
if value_of_next_point > best_point_value:
best_point_value = value_of_next_point
best_point = next_point_to_sample
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP;
# - infront of value_of_next_point is due to fact that moe minimize and max accuracy is of interest in HAR classification
exp_svc_linear.historical_data.append_sample_points([SamplePoint(next_point_to_sample, -value_of_next_point, .000001)]) # We can add some noise
def do_svc_rbf_MOE(num_points_to_sample, X_train, y_train, verbose=True, **kwargs):
exp_svc_rbf = Experiment([[1.0000e-05, 1], [1.0000e-08, 1]]) # C_range = [0.1, 10000] is divided to be in [0.1, 1] range
best_point = []
best_point_value = 0.
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp_svc_rbf, rest_host='localhost', rest_port=6543, **kwargs)[0] # By default we only ask for one point
# Sample the point from objective function
C = next_point_to_sample[0] * 10000.0
gamma = next_point_to_sample[1]
svc_rbf = svm.SVC(C=C, kernel='rbf', degree=3, gamma=gamma, coef0=0.0, shrinking=True, probability=False, tol=0.001, cache_size=200,
class_weight=None, verbose=False, max_iter=-1, random_state=None)
score_cv = cross_validation.cross_val_score(svc_rbf, X_train, y_train, cv=10, scoring='accuracy')
value_of_next_point = np.mean(score_cv)
if value_of_next_point > best_point_value:
best_point_value = value_of_next_point
best_point = next_point_to_sample
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp_svc_rbf.historical_data.append_sample_points([SamplePoint(next_point_to_sample, -value_of_next_point, 0.0001)]) # We can add some noise
def do_abc_MOE(num_points_to_sample, X_train, y_train, verbose=True, **kwargs):
exp_abc = Experiment([[0.005, 1], [0.1, 1]]) # n_estimators_range = [5, 1000] is normalized
best_point = []
best_point_value = 0.
for _ in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp_abc, rest_host='localhost', rest_port=6543, **kwargs)[0] # By default we only ask for one point
# Sample the point from objective function
n_estimators = int(round(next_point_to_sample[0] * 1000.0))
learning_rate = next_point_to_sample[1]
abc = AdaBoostClassifier((DecisionTreeClassifier(max_depth=2)),n_estimators=n_estimators, learning_rate=learning_rate)
score_cv = cross_validation.cross_val_score(abc, X_train, y_train, cv=10, scoring='accuracy')
value_of next_point = np.mean(score_cv)
if value_of_next_point > best_point_value:
best_point_value = value_of_next_point
best_point = next_point_to_sample
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp_abc.historical_data.append_sample_points([SamplePoint(next_point_to_sample, -value_of_next_point, 0.0001)]) # We can add some noise
best_point[0] = int(round(best_point[0] * 1000))
return best_point, best_point_value
def itterate():
print str(datetime.datetime.now())
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(exp)[0]
print next_point_to_sample
# By default we only ask for one point
x = [(n - argoffset) / argscale for n in next_point_to_sample]
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
print x, value_of_next_point
# Store the sample
with open('moveheuristic.csv', 'a') as csvfile:
csvfile.write(", ".join([str(k)
for k in x + [value_of_next_point]]) + "\n")
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([
SamplePoint(next_point_to_sample, offset + value_of_next_point * scale,
variance)
])
def run_example(num_points_to_sample=1000, verbose=True, **kwargs):
"""Run the example, asking MOE for ``num_points_to_sample`` optimal points to sample."""
exp = Experiment([[1, 52], [0, 6], [1, 52]]) # 2D experiment, we build a tensor product domain
# Bootstrap with some known or already sampled point(s)
exp.historical_data.append_sample_points([
SamplePoint([26, 2, 46], get_fitness([26, 2, 35]), 0.5), # Iterables of the form [point, f_val, f_var] are also allowed
])
# Sample num_points_to_sample points
for i in range(num_points_to_sample):
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = map(round, gp_next_points(exp, **kwargs)[0]) # in [A, X, B] form, rounded integers
value_of_next_point = get_fitness(next_point_to_sample)
if verbose:
if in_results(next_point_to_sample):
print '***', "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point), '***'
else:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
bank[i,0:3] = next_point_to_sample
bank[i,3] = value_of_next_point
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([SamplePoint(next_point_to_sample, value_of_next_point, 0.01)]) # We can add some noise
def get_next_hyperparameters(self):
try:
return gp_next_points(self.experiment)[0]
except BadStatusLine:
raise RuntimeError('MOE server is not running!')
def run_example(num_to_sample=20, verbose=True, testapp=None, gp_next_points_kwargs=None, gp_hyper_opt_kwargs=None, gp_mean_var_kwargs=None, **kwargs):
"""Run the combined example.
:param num_to_sample: Number of points for MOE to suggest and then sample [20]
:type num_to_sample: int > 0
:param verbose: Whether to print information to the screen [True]
:type verbose: bool
:param testapp: Whether to use a supplied test pyramid application or a rest server [None]
:type testapp: Pyramid test application
:param gp_next_points_kwargs: Optional kwargs to pass to gp_next_points endpoint
:type gp_next_points_kwargs: dict
:param gp_hyper_opt_kwargs: Optional kwargs to pass to gp_hyper_opt_kwargs endpoint
:type gp_hyper_opt_kwargs: dict
:param gp_mean_var_kwargs: Optional kwargs to pass to gp_mean_var_kwargs endpoint
:type gp_mean_var_kwargs: dict
:param kwargs: Optional kwargs to pass to all endpoints
:type kwargs: dict
"""
# Set and combine all optional kwargs
# Note that the more specific kwargs take precedence (and will override general kwargs)
if gp_next_points_kwargs is None:
gp_next_points_kwargs = {}
else:
gp_next_points_kwargs = dict(kwargs.items() + gp_next_points_kwargs.items())
if gp_hyper_opt_kwargs is None:
gp_hyper_opt_kwargs = {}
else:
gp_hyper_opt_kwargs = dict(kwargs.items() + gp_hyper_opt_kwargs.items())
if gp_mean_var_kwargs is None:
gp_mean_var_kwargs = {}
else:
gp_mean_var_kwargs = dict(kwargs.items() + gp_mean_var_kwargs.items())
exp = Experiment([[0, 2], [0, 4]])
# Bootstrap with some known or already sampled point(s)
exp.historical_data.append_sample_points([
[[0, 0], function_to_minimize([0, 0]), 0.01], # sampled points have the form [point_as_a_list, objective_function_value, value_variance]
])
# Sample points
for i in range(num_to_sample):
covariance_info = {}
if i > 0 and i % 5 == 0:
covariance_info = gp_hyper_opt(exp.historical_data.to_list_of_sample_points(), testapp=testapp, **gp_hyper_opt_kwargs)
if verbose:
print "Updated covariance_info with {0:s}".format(str(covariance_info))
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(
exp,
covariance_info=covariance_info,
testapp=testapp,
**gp_next_points_kwargs
)[0] # By default we only ask for one point
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([[next_point_to_sample, value_of_next_point, 0.01]]) # We can add some noise
points_to_evaluate = [[x, x] for x in numpy.arange(0, 1, 0.1)] # uniform grid of points
mean, var = gp_mean_var(
exp.historical_data.to_list_of_sample_points(), # Historical data to inform Gaussian Process
points_to_evaluate, # We will calculate the mean and variance of the GP at these points
testapp=testapp,
**gp_mean_var_kwargs
)
if verbose:
print "GP mean at (0, 0), (0.1, 0.1), ...: {0:s}".format(str(mean))
print(sigma0.value)
for k, temperature in enumerate(temperatures):
observed = measurements[k]
predicted = indexed_data.density.ix[(q0_val, sigma0_val, temperature)]
tau = (observed * relative_error) ** -2.
var = pymc.Normal("obs_%d" % k, mu=predicted, tau=tau, observed=True, value=observed)
print(predicted, observed, tau, var.logp)
variables.append(var)
model = pymc.MCMC(variables)
return model.logp
a, b = data[keys].iloc[0].values
logp = objective(a, b)
get_bounds = lambda variable: (variable.parents["lower"], variable.parents["upper"])
experiment_bounds = [get_bounds(q0), get_bounds(sigma0)]
exp = Experiment(experiment_bounds)
for (q0_val, sigma0_val) in data.set_index(keys).index:
value = objective(q0_val, sigma0_val)
print(q0_val, sigma0_val, value)
error = 0.001
exp.historical_data.append_sample_points([[(q0_val, sigma0_val), value, error]])
covariance_info = gp_hyper_opt(exp.historical_data.to_list_of_sample_points())
next_point_to_sample = gp_next_points(exp, covariance_info=covariance_info)
print next_point_to_sample
def run_example(
num_to_sample=20,
verbose=True,
testapp=None,
gp_next_points_kwargs=None,
gp_hyper_opt_kwargs=None,
gp_mean_var_kwargs=None,
**kwargs
):
"""Run the combined example.
:param num_to_sample: Number of points for MOE to suggest and then sample [20]
:type num_to_sample: int > 0
:param verbose: Whether to print information to the screen [True]
:type verbose: bool
:param testapp: Whether to use a supplied test pyramid application or a rest server [None]
:type testapp: Pyramid test application
:param gp_next_points_kwargs: Optional kwargs to pass to gp_next_points endpoint
:type gp_next_points_kwargs: dict
:param gp_hyper_opt_kwargs: Optional kwargs to pass to gp_hyper_opt_kwargs endpoint
:type gp_hyper_opt_kwargs: dict
:param gp_mean_var_kwargs: Optional kwargs to pass to gp_mean_var_kwargs endpoint
:type gp_mean_var_kwargs: dict
:param kwargs: Optional kwargs to pass to all endpoints
:type kwargs: dict
"""
# Set and combine all optional kwargs
# Note that the more specific kwargs take precedence (and will override general kwargs)
if gp_next_points_kwargs is None:
gp_next_points_kwargs = {}
gp_next_points_kwargs = dict(kwargs.items() + gp_next_points_kwargs.items())
if gp_hyper_opt_kwargs is None:
gp_hyper_opt_kwargs = {}
gp_hyper_opt_kwargs = dict(kwargs.items() + gp_hyper_opt_kwargs.items())
if gp_mean_var_kwargs is None:
gp_mean_var_kwargs = {}
gp_mean_var_kwargs = dict(kwargs.items() + gp_mean_var_kwargs.items())
exp = Experiment([[0, 2], [0, 4]])
# Bootstrap with some known or already sampled point(s)
exp.historical_data.append_sample_points([
[[0, 0], function_to_minimize([0, 0]), 0.01], # sampled points have the form [point_as_a_list, objective_function_value, value_variance]
])
# Sample points
for i in range(num_to_sample):
covariance_info = {}
if i > 0 and i % 5 == 0:
covariance_info = gp_hyper_opt(exp.historical_data.to_list_of_sample_points(), testapp=testapp, **gp_hyper_opt_kwargs)
if verbose:
print "Updated covariance_info with {0:s}".format(str(covariance_info))
# Use MOE to determine what is the point with highest Expected Improvement to use next
next_point_to_sample = gp_next_points(
exp,
covariance_info=covariance_info,
testapp=testapp,
**gp_next_points_kwargs
)[0] # By default we only ask for one point
# Sample the point from our objective function, we can replace this with any function
value_of_next_point = function_to_minimize(next_point_to_sample)
if verbose:
print "Sampled f({0:s}) = {1:.18E}".format(str(next_point_to_sample), value_of_next_point)
# Add the information about the point to the experiment historical data to inform the GP
exp.historical_data.append_sample_points([[next_point_to_sample, value_of_next_point, 0.01]]) # We can add some noise
points_to_evaluate = [[x, x] for x in numpy.arange(0, 1, 0.1)] # uniform grid of points
mean, var = gp_mean_var(
exp.historical_data.to_list_of_sample_points(), # Historical data to inform Gaussian Process
points_to_evaluate, # We will calculate the mean and variance of the GP at these points
testapp=testapp,
**gp_mean_var_kwargs
)
if verbose:
print "GP mean at (0, 0), (0.1, 0.1), ...: {0:s}".format(str(mean))
mu=predicted,
tau=tau,
observed=True,
value=observed)
print(predicted, observed, tau, var.logp)
variables.append(var)
model = pymc.MCMC(variables)
return model.logp
a, b = data[keys].iloc[0].values
logp = objective(a, b)
get_bounds = lambda variable: (variable.parents["lower"], variable.parents[
"upper"])
experiment_bounds = [get_bounds(q0), get_bounds(sigma0)]
exp = Experiment(experiment_bounds)
for (q0_val, sigma0_val) in data.set_index(keys).index:
value = objective(q0_val, sigma0_val)
print(q0_val, sigma0_val, value)
error = 0.001
exp.historical_data.append_sample_points([[(q0_val, sigma0_val), value,
error]])
covariance_info = gp_hyper_opt(exp.historical_data.to_list_of_sample_points())
next_point_to_sample = gp_next_points(exp, covariance_info=covariance_info)
print next_point_to_sample
from moe.easy_interface.experiment import Experiment
from moe.easy_interface.simple_endpoint import gp_next_points
from moe.optimal_learning.python.data_containers import SamplePoint
import math
def f(v,w,x,y,z):
return (x+y)**2 + 4*x -2*y + math.sin(v) + 0.3 * math.cos(z) + (w-3)**2
exp = Experiment([[-10,10],[-10,10],[-10,10],[-10,10],[-10,10]])
for c in range(100):
try:
x = gp_next_points(exp)
except:
print "500"
continue
y = f(x[0][0], x[0][1], x[0][2], x[0][3], x[0][4])
print x, y
exp.historical_data.append_sample_points([SamplePoint(x,y,0.001)])
