def augment_the_new_data(self,x_max):
# store X
self.X = np.vstack((self.X, x_max.reshape((1, -1))))
# compute X in original scale
temp_X_new_original=x_max*self.max_min_gap+self.bounds[:,0]
self.X_original=np.vstack((self.X_original, temp_X_new_original))
# evaluate Y using original X
#self.Y = np.append(self.Y, self.f(temp_X_new_original))
self.Y_original = np.append(self.Y_original, self.f(temp_X_new_original))
# update Y after change Y_original
self.Y=(self.Y_original-np.mean(self.Y_original))/np.std(self.Y_original)
# find the maximizer in the GP mean function
try:
len(self.gp)
x_mu_max=[]
for j in range(self.J):
x_mu_max_temp=acq_max_with_name(gp=self.gp[j],scalebounds=self.scalebounds[self.featIdx[j]],acq_name="mu")
x_mu_max=np.hstack((x_mu_max,x_mu_max_temp))
except:
x_mu_max=acq_max_with_name(gp=self.gp,scalebounds=self.scalebounds,acq_name="mu")
x_mu_max_original=x_mu_max*self.max_min_gap+self.bounds[:,0]
# set y_max = mu_max
#mu_max=acq_mu.acq_kind(x_mu_max,gp=self.gp)
self.Y_original_maxGP = np.append(self.Y_original_maxGP, self.f(x_mu_max_original))
self.X_original_maxGP = np.vstack((self.X_original_maxGP, x_mu_max_original))
def acq_utility_cost(self):
# generate a set of x* at T=MaxIter
# instead of running optimization on the whole space, we will only operate on the region of interest
# the region of interest in DRL is where the MaxEpisode
# we find maximum of EI
acq = {}
acq['name'] = self.acq_name
acq['dim'] = self.scaleSearchSpace.shape[0]
acq['scaleSearchSpace'] = self.scaleSearchSpace
if self.acq_name == 'ei_mu_max': # using max of mean(x) as the incumbent
# optimie the GP predictive mean function to find the max of mu
x_mu_max, mu_max_val = acq_max_with_name(
gp=self.gp,
scaleSearchSpace=self.scaleSearchSpace,
acq_name='mu',
IsReturnY=True)
acq['mu_max'] = mu_max_val
myacq = AcquisitionFunction(acq)
x_min = acq_min_scipy_kwargs(myfunc=self.utility_cost_evaluation,
SearchSpace=self.scaleSearchSpace,
acq_func=myacq,
isDebug=False)
if self.verbose == True:
acq_val = self.utility_cost_evaluation(x_min, myacq, isDebug=False)
print("selected point from acq func:", np.round(x_min, decimals=4),
"acq val=log(Utility/Cost)=", (-1) * np.round(
acq_val, decimals=4)) # since we minimize the acq func
if np.round(acq_val, decimals=4) == 0:
print("acq value =0")
return x_min
def suggest_nextpoint(self): # logistic, time-cost, virtual
"""
Main optimization method.
Input parameters
----------
gp_params: parameter for Gaussian Process
Returns
-------
x: recommented point for evaluation
"""
if self.acq_name == 'random':
x_max = [
np.random.uniform(x[0], x[1], size=1) for x in self.SearchSpace
]
x_max = np.asarray(x_max)
x_max = x_max.T
self.X_original = np.vstack((self.X_original, x_max))
# evaluate Y using original X
self.Y_original = np.append(self.Y_original, self.f(x_max))
# update Y after change Y_original
self.Y = (self.Y_original - np.mean(self.Y_original)) / np.std(
self.Y_original)
self.time_opt = np.hstack((self.time_opt, 0))
return
# init a new Gaussian Process
#self.gp=ProductGaussianProcess(self.gp_params)
self.gp = ProductGaussianProcess(self.scaleSearchSpace,
verbose=self.verbose)
self.gp.fit(self.X, self.T, self.Y, self.Y_curves)
# optimize GP parameters after 3*d iterations
if len(self.Y) % (3 * self.dim) == 0:
hyper=[self.gp.hyper['lengthscale_x'],self.gp.hyper['lengthscale_t'], \
self.gp.logistic_hyper['midpoint'],self.gp.logistic_hyper['growth']]
newlengthscale_x, newlengthscale_t, new_midpoint, new_growth = self.gp.optimize_lengthscale_logistic_hyper(
hyper, self.gp.noise_delta)
self.gp.hyper['lengthscale_x'] = newlengthscale_x
self.gp.hyper['lengthscale_t'] = self.gp.hyper['lengthscale_t']
self.gp.logistic_hyper['midpoint'] = new_midpoint
self.gp.logistic_hyper['growth'] = new_growth
if self.verbose:
print("estimated lengthscale_x={}, estimated lengthscale_t={}".
format(newlengthscale_x, newlengthscale_t))
# Set acquisition function
start_opt = time.time()
# linear regression is used to fit the cost - alternatively we can use GP
acq = {}
acq['name'] = self.acq_name
acq['dim'] = self.scaleSearchSpace.shape[0]
acq['scaleSearchSpace'] = self.scaleSearchSpace
if self.acq_name == 'ei_mu_max': # using max of mean(x) as the incumbent
# optimie the GP predictive mean function to find the max of mu
x_mu_max, mu_max_val = acq_max_with_name(
gp=self.gp,
scaleSearchSpace=self.scaleSearchSpace,
acq_name='mu',
IsReturnY=True)
acq['mu_max'] = mu_max_val
scaleSearchSpace = np.copy(self.scaleSearchSpace)
scaleSearchSpace[-1, 0] = scaleSearchSpace[
-1, 1] # last dimension, set it to MaxIter
#x_max_temp=acq_max_with_name(gp=self.gp,scaleSearchSpace=scaleSearchSpace,acq_name=self.acq_name)
myacq = AcquisitionFunction(acq)
#x_max = acq_max(ac=self.acq_func.acq_kind,gp=self.gp,bounds=self.scaleSearchSpace,opt_toolbox=self.opt_toolbox,seeds=self.xstars)
x_max_temp = acq_max(ac=myacq.acq_kind,
gp=self.gp,
bounds=self.scaleSearchSpace)
# x_max_temp = acq_min_scipy_kwargs(myfunc=myacq.acq_kind,bounds=self.scaleSearchSpace,
# acq_func=myacq, isDebug=False)
#x_max_temp=self.acq_utility_cost()
x_max = x_max_temp[:-1]
x_max_t = x_max_temp[-1]
# record the optimization time
finished_opt = time.time()
elapse_opt = finished_opt - start_opt
self.time_opt = np.hstack((self.time_opt, elapse_opt))
# store X
self.X = np.vstack((self.X, x_max.reshape((1, -1))))
self.T = np.vstack((self.T, x_max_t.reshape((1, -1))))
# compute X in original scale
temp_X_new_original = x_max * self.max_min_gap[:
-1] + self.SearchSpace[:
-1,
0]
self.X_original = np.vstack((self.X_original, temp_X_new_original))
temp_T_new_original = x_max_t * self.max_min_gap[
-1] + self.SearchSpace[-1, 0]
self.T_original = np.vstack((self.T_original, temp_T_new_original))
# evaluate Y using original X
x_original_to_test = x_max_temp * self.max_min_gap + self.SearchSpace[:,
0]
y_original_curves, y_cost_original = self.f(x_original_to_test)
#y_original_curves= self.f(x_original_to_test)
#y_cost_original=y_original_curves
y_original=transform_logistic(y_original_curves,self.gp.logistic_hyper['midpoint'],\
self.gp.logistic_hyper['growth'],self.SearchSpace[-1,1])
#y_original=y_original_curves
self.Y_curves.append(y_original_curves)
self.Y_original = np.append(self.Y_original, y_original)
self.Y_cost_original = np.append(self.Y_cost_original, y_cost_original)
# update Y after change Y_original
self.Y = (self.Y_original - np.mean(self.Y_original)) / np.std(
self.Y_original)
#self.Y_cost=(self.Y_cost_original-np.mean(self.Y_cost_original))/np.std(self.Y_cost_original)
if self.verbose:
print("x={} t={} current y={:.4f}, ybest={:.4f}".format(
self.X_original[-1], self.T_original[-1], self.Y_original[-1],
self.Y_original.max()))
def maximize_pvrs(self):
"""
Main optimization method.
Input parameters
----------
gp_params: parameter for Gaussian Process
Returns
-------
x: recommented point for evaluation
"""
if self.stop_flag == 1:
return
if 'n_xstars' in self.acq:
numXstar = self.acq['n_xstars']
else:
numXstar = 10 * self.dim
# Set acquisition function
start_opt = time.time()
y_max = self.Y.max()
# run the acquisition function for the first time to get xstar
self.xstars = []
# finding the xt of UCB
numTheta = len(self.theta_vector)
temp = []
# finding the xt of Thompson Sampling
for ii in range(numXstar):
if self.theta_vector != []:
# since the numXstar > len(theta_vector)
index = np.random.randint(numTheta)
#print index
gp_params['theta'] = self.theta_vector[index]
# init a new Gaussian Process
self.gp = GaussianProcess(self.gp_params)
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
xt_TS, y_xt_TS = acq_max_with_name(gp=self.gp,
scalebounds=self.scalebounds,
acq_name="thompson",
IsReturnY=True)
temp.append(xt_TS)
# check if f* > y^max and ignore xt_TS otherwise
#if y_xt_TS>=y_max:
#self.xstars.append(xt_TS)
if self.xstars == []:
#print 'xt_suggestion is empty'
# again perform TS and take all of them
self.xstars = temp
# check predictive variance before adding a new data points
var_before = self.gp.compute_var(self.gp.X, self.xstars)
var_before = np.mean(var_before)
if self.xstar_accumulate == []:
self.xstar_accumulate = np.asarray(self.xstars)
else:
self.xstar_accumulate = np.vstack(
(self.xstar_accumulate, np.asarray(self.xstars)))
accum_var_before = [
self.gp.compute_var(self.gp.X, val)
for idx, val in enumerate(self.xstar_accumulate)
]
accum_var_before = np.mean(accum_var_before)
self.gp.lengthscale_vector = self.theta_vector
self.acq['xstars'] = self.xstars
self.acq_func = AcquisitionFunction(self.acq)
x_max = acq_max(ac=self.acq_func.acq_kind,
gp=self.gp,
bounds=self.scalebounds,
opt_toolbox=self.opt_toolbox,
seeds=self.xstars)
#xstars_array=np.asarray(self.acq_func.object.xstars)
val_acq = -self.acq_func.acq_kind(x_max, self.gp)
# check predictive variance after
temp = np.vstack((self.gp.X, x_max))
var_after = self.gp.compute_var(temp, self.xstars)
var_after = np.mean(var_after)
accum_var_after = [
self.gp.compute_var(temp, val)
for idx, val in enumerate(self.xstar_accumulate)
]
accum_var_after = np.mean(accum_var_after)
if self.PVRS_before_after == []:
self.PVRS_before_after = np.asarray([var_before, var_after])
self.accummulate_PVRS_before_after = np.asarray(
[accum_var_before, accum_var_after])
else:
self.PVRS_before_after = np.vstack(
(self.PVRS_before_after, np.asarray([var_before, var_after])))
self.accummulate_PVRS_before_after = np.vstack(
(self.accummulate_PVRS_before_after,
np.asarray([accum_var_before, accum_var_after])))
#print "predictive variance before={:.12f} after={:.12f} val_acq={:.12f}".format(var_before,var_after,np.asscalar(val_acq))
# check maximum variance
var_acq = {}
var_acq['name'] = 'pure_exploration'
var_acq['dim'] = self.dim
var_acq['scalebounds'] = self.scalebounds
acq_var = AcquisitionFunction(var_acq)
temp = acq_max(ac=acq_var.acq_kind,
gp=self.gp,
bounds=self.scalebounds,
opt_toolbox='scipy')
# get the value f*
#max_var_after=acq_var.acq_kind(temp,self.gp,y_max=y_max)
#print "max predictive variance ={:.8f}".format(np.asscalar(max_var_after))
if self.stopping_criteria != 0 and val_acq < self.stopping_criteria:
val_acq = self.acq_func.acq_kind(x_max, self.gp)
self.stop_flag = 1
print(
"Stopping Criteria is violated. Stopping Criteria is {:.15f}".
format(self.stopping_criteria))
#mean,var=self.gp.predict(x_max, eval_MSE=True)
#var.flags['WRITEABLE']=True
#var[var<1e-20]=0
#self.Tau_Xt= np.append(self.Tau_Xt,val_acq/var)
# record the optimization time
finished_opt = time.time()
elapse_opt = finished_opt - start_opt
self.time_opt = np.hstack((self.time_opt, elapse_opt))
super(BayesOpt, self).augment_the_new_data(x_max)
def maximize_e3i(self):
"""
Main optimization method.
Input parameters
----------
gp_params: parameter for Gaussian Process
Returns
-------
x: recommented point for evaluation
"""
if self.stop_flag == 1:
return
# Set acquisition function
start_opt = time.time()
y_max = self.Y.max()
# run the acquisition function for the first time to get xstar
self.xstars = []
# finding the xt of UCB
y_max = np.max(self.Y)
numXtar = 50 * self.dim
#numXtar=20
y_stars = []
temp = []
# finding the xt of Thompson Sampling
for ii in range(numXtar):
xt_TS, y_xt_TS = acq_max_with_name(gp=self.gp,
scalebounds=self.scalebounds,
acq_name="thompson",
IsReturnY=True)
y_stars.append(y_xt_TS)
temp.append(xt_TS)
# check if f* > y^max and ignore xt_TS otherwise
#if y_xt_TS>=y_max:
self.xstars.append(xt_TS)
#y_stars=y_stars*np.std(self.Y_original)+np.mean(self.Y_original)
#print "{:.5f} {:.6f}".format(np.mean(y_stars),np.std(y_stars))
#print "ymax={:.5f}".format(np.max(self.Y))
if self.acq['debug'] == 1:
print('mean y*={:.4f}({:.8f}) y+={:.4f}'.format(
np.mean(y_xt_TS), np.std(y_xt_TS), y_max))
if self.xstars == []:
#print 'xt_suggestion is empty'
# again perform TS and take all of them
self.xstars = temp
self.acq['xstars'] = self.xstars
self.acq['ystars'] = y_stars
self.acq_func = AcquisitionFunction(self.acq)
x_max = acq_max(ac=self.acq_func.acq_kind,
gp=self.gp,
bounds=self.scalebounds,
opt_toolbox=self.opt_toolbox,
seeds=self.xstars)
#xstars_array=np.asarray(self.acq_func.object.xstars)
val_acq = self.acq_func.acq_kind(x_max, self.gp)
if self.stopping_criteria != 0 and val_acq < self.stopping_criteria:
val_acq = self.acq_func.acq_kind(x_max, self.gp)
self.stop_flag = 1
print(
"Stopping Criteria is violated. Stopping Criteria is {:.15f}".
format(self.stopping_criteria))
# record the optimization time
finished_opt = time.time()
elapse_opt = finished_opt - start_opt
self.time_opt = np.hstack((self.time_opt, elapse_opt))
super(BayesOpt, self).augment_the_new_data(x_max)
def maximize(self):
"""
Main optimization method.
Input parameters
----------
gp_params: parameter for Gaussian Process
Returns
-------
x: recommented point for evaluation
"""
if self.stop_flag == 1:
return
if self.acq['name'] == 'random':
super(BayesOpt, self).generate_random_point()
return
# init a new Gaussian Process
self.gp = GaussianProcess(self.gp_params)
if self.gp.KK_x_x_inv == []:
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
acq = self.acq
# optimize GP parameters after 10 iterations
if len(self.Y) % (2 * self.dim) == 0:
self.gp, self.gp_params = super(BayesOpt,
self).optimize_gp_hyperparameter()
if self.acq['name'] == 'mes':
self.maximize_mes()
return
if self.acq['name'] == 'pvrs':
self.maximize_pvrs()
return
if self.acq['name'] == 'e3i':
self.maximize_e3i()
return
if self.acq['name'] == 'ei_kov' or self.acq[
'name'] == 'poi_kov' or self.acq['name'] == 'ei_fstar':
self.acq['fstar_scaled'] = (self.acq['fstar'] - np.mean(
self.Y_original)) / np.std(self.Y_original)
# Set acquisition function
start_opt = time.time()
#y_max = self.Y.max()
if 'xstars' not in globals():
xstars = []
self.xstars = xstars
self.acq['xstars'] = xstars
self.acq_func = AcquisitionFunction(self.acq)
if acq['name'] == "ei_mu":
#find the maximum in the predictive mean
x_mu_max, y_max = acq_max_with_name(gp=self.gp,
scalebounds=self.scalebounds,
acq_name='mu',
IsReturnY=True)
x_max = acq_max(ac=self.acq_func.acq_kind,
gp=self.gp,
bounds=self.scalebounds,
opt_toolbox=self.opt_toolbox,
seeds=self.xstars)
val_acq = self.acq_func.acq_kind(x_max, self.gp)
if self.stopping_criteria != 0 and val_acq < self.stopping_criteria:
#val_acq=self.acq_func.acq_kind(x_max,self.gp)
self.stop_flag = 1
#print "Stopping Criteria is violated. Stopping Criteria is {:.15f}".format(self.stopping_criteria)
self.alpha_Xt = np.append(self.alpha_Xt, val_acq)
mean, var = self.gp.predict(x_max, eval_MSE=True)
var.flags['WRITEABLE'] = True
var[var < 1e-20] = 0
#self.Tau_Xt= np.append(self.Tau_Xt,val_acq/var)
# record the optimization time
finished_opt = time.time()
elapse_opt = finished_opt - start_opt
self.time_opt = np.hstack((self.time_opt, elapse_opt))
super(BayesOpt, self).augment_the_new_data(x_max)
def maximize_with_lengthscale_derived_by_fstar(self, gp_params):
"""
Main optimization method.
Input parameters
----------
gp_params: parameter for Gaussian Process
Returns
-------
x: recommented point for evaluation
"""
if self.stop_flag == 1:
return
if self.acq['name'] == 'random':
x_max = [
np.random.uniform(x[0], x[1], size=1) for x in self.bounds
]
x_max = np.asarray(x_max)
x_max = x_max.T
self.X_original = np.vstack((self.X_original, x_max))
# evaluate Y using original X
#self.Y = np.append(self.Y, self.f(temp_X_new_original))
self.Y_original = np.append(self.Y_original, self.f(x_max))
# update Y after change Y_original
self.Y = (self.Y_original - np.mean(self.Y_original)) / np.std(
self.Y_original)
self.time_opt = np.hstack((self.time_opt, 0))
return
# init a new Gaussian Process
self.gp = GaussianProcess(gp_params)
if self.gp.KK_x_x_inv == []:
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
acq = self.acq
# optimize GP parameters after 10 iterations
if len(self.Y) % (3 * self.dim) == 0:
fstar_scaled = (self.acq['fstar'] -
np.mean(self.Y_original)) / np.std(self.Y_original)
newlengthscale = self.gp.optimize_lengthscale_SE_fstar(
self.gp_params['lengthscale'], self.gp_params['noise_delta'],
fstar_scaled)
self.gp_params['lengthscale'] = newlengthscale
print("estimated lengthscale =", newlengthscale)
# init a new Gaussian Process after optimizing hyper-parameter
self.gp = GaussianProcess(gp_params)
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
if self.acq['name'] == 'mes':
self.maximize_mes(gp_params)
return
if self.acq['name'] == 'pvrs':
self.maximize_pvrs(gp_params)
return
if self.acq['name'] == 'e3i':
self.maximize_e3i(gp_params)
return
if self.acq['name'] == 'ei_kov' or self.acq[
'name'] == 'poi_kov' or self.acq['name'] == 'ei_fstar':
self.acq['fstar_scaled'] = (self.acq['fstar'] - np.mean(
self.Y_original)) / np.std(self.Y_original)
# Set acquisition function
start_opt = time.time()
y_max = self.Y.max()
if 'xstars' not in globals():
xstars = []
self.xstars = xstars
self.acq['xstars'] = xstars
self.acq_func = AcquisitionFunction(self.acq)
if acq['name'] == "ei_mu":
#find the maximum in the predictive mean
x_mu_max, y_max = acq_max_with_name(gp=self.gp,
scalebounds=self.scalebounds,
acq_name='mu',
IsReturnY=True)
x_max = acq_max(ac=self.acq_func.acq_kind,
gp=self.gp,
bounds=self.scalebounds,
opt_toolbox=self.opt_toolbox,
seeds=self.xstars)
val_acq = self.acq_func.acq_kind(x_max, self.gp)
if self.stopping_criteria != 0 and val_acq < self.stopping_criteria:
val_acq = self.acq_func.acq_kind(x_max, self.gp)
self.stop_flag = 1
#print "Stopping Criteria is violated. Stopping Criteria is {:.15f}".format(self.stopping_criteria)
self.alpha_Xt = np.append(self.alpha_Xt, val_acq)
mean, var = self.gp.predict(x_max, eval_MSE=True)
var.flags['WRITEABLE'] = True
var[var < 1e-20] = 0
#self.Tau_Xt= np.append(self.Tau_Xt,val_acq/var)
# record the optimization time
finished_opt = time.time()
elapse_opt = finished_opt - start_opt
self.time_opt = np.hstack((self.time_opt, elapse_opt))
# store X
self.X = np.vstack((self.X, x_max.reshape((1, -1))))
# compute X in original scale
temp_X_new_original = x_max * self.max_min_gap + self.bounds[:, 0]
self.X_original = np.vstack((self.X_original, temp_X_new_original))
# evaluate Y using original X
#self.Y = np.append(self.Y, self.f(temp_X_new_original))
self.Y_original = np.append(self.Y_original,
self.f(temp_X_new_original))
# update Y after change Y_original
self.Y = (self.Y_original - np.mean(self.Y_original)) / np.std(
self.Y_original)
if self.gp.flagIncremental == 1:
self.gp.fit_incremental(x_max, self.Y[-1])
def maximize_batch_greedy_PVRS(self,B=5):
"""
Finding a batch of points using Peak Suppression / Constant Liar approach
Input Parameters
----------
gp_params: Parameters to be passed to the Gaussian Process class
kappa: constant value in UCB
Returns
-------
X: a batch of [x_1..x_Nt]
"""
y_max = self.Y.max()
# Set parameters if any was passed
self.gp=GaussianProcess(self.gp_params)
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
start_opt=time.time()
if 'n_xstars' in self.acq:
numXtar=self.acq['n_xstars']
else:
numXtar=30*self.dim
#temp=[]
# finding the xt of Thompson Sampling
xstars=[]
for ii in range(numXtar):
mu_acq={}
mu_acq['name']='thompson'
mu_acq['dim']=self.dim
mu_acq['scalebounds']=self.scalebounds
acq_mu=AcquisitionFunction(mu_acq)
xt_TS = acq_max(ac=acq_mu.acq_kind,gp=self.gp,bounds=self.scalebounds,opt_toolbox='scipy')
#temp.append(xt_TS)
xstars.append(xt_TS)
self.xstars=xstars
# Set acquisition function
myacq={}
myacq['name']='pvrs'
myacq['dim']=self.acq['dim']
myacq['xstars']=xstars
acq_func = AcquisitionFunction(myacq)
# copy GP, X and Y
temp_gp=copy.deepcopy(self.gp)
temp_X=copy.deepcopy(self.X)
temp_Y=copy.deepcopy(self.Y)
#temp_Y_original=self.Y_original
start_batch=time.time()
# check predictive variance before adding a new data points
var_before=self.gp.compute_var(temp_X,xstars)
var_before=np.mean(var_before)
#store new_x
new_X=np.empty((0,self.dim),float)
for ii in range(B):
# Finding argmax of the acquisition function.
x_max = acq_max(ac=acq_func.acq_kind,gp=temp_gp, bounds=self.scalebounds)
new_X= np.vstack((new_X, x_max.reshape((1, -1))))
temp_X = np.vstack((temp_X, x_max.reshape((1, -1))))
# check predictive variance after
var_after=self.gp.compute_var(temp_X,xstars)
var_after=np.mean(var_after)
if self.PVRS_before_after==[]:
self.PVRS_before_after=np.asarray([var_before,var_after])
else:
temp_var=np.asarray([var_before,var_after])
self.PVRS_before_after=np.vstack((self.PVRS_before_after, temp_var))
var_before=var_after
const_liar,const_liar_variance=temp_gp.predict(x_max,eval_MSE=1)
const_liar=np.random.rand()
temp_Y = np.append(temp_Y, const_liar )
temp_gp.fit(temp_X,temp_Y)
# for debug
finish_batch=time.time()-start_batch
#return new_X,new_X_original
self.NumPoints=np.append(self.NumPoints,new_X.shape[0])
self.X=np.vstack((self.X,new_X))
# convert back to original scale
temp_X_new_original=[val*self.max_min_gap+self.bounds[:,0] for idx, val in enumerate(new_X)]
temp_X_new_original=np.asarray(temp_X_new_original)
self.X_original=np.vstack((self.X_original, temp_X_new_original))
# evaluate y=f(x)
temp=self.f(temp_X_new_original)
temp=np.reshape(temp,(-1,1))
self.Y_original=np.append(self.Y_original,temp)
self.Y=(self.Y_original-np.mean(self.Y_original))/(np.max(self.Y_original)-np.min(self.Y_original))
# find the maximizer in the GP mean function
try:
len(self.gp)
x_mu_max=[]
for j in range(self.J):
x_mu_max_temp=acq_max_with_name(gp=self.gp[j],scalebounds=self.scalebounds[self.featIdx[j]],acq_name="mu")
x_mu_max=np.hstack((x_mu_max,x_mu_max_temp))
except:
x_mu_max=acq_max_with_name(gp=self.gp,scalebounds=self.scalebounds,acq_name="mu")
x_mu_max_original=x_mu_max*self.max_min_gap+self.bounds[:,0]
# set y_max = mu_max
#mu_max=acq_mu.acq_kind(x_mu_max,gp=self.gp)
self.Y_original_maxGP = np.append(self.Y_original_maxGP, self.f(x_mu_max_original))
self.X_original_maxGP = np.vstack((self.X_original_maxGP, x_mu_max_original))
return new_X
def select_informative_location_by_uncertainty(self, n_virtual_obs, x_max,
t_max):
# this function will select a list of informative locations to place a virtual obs
# x_max is the selected hyperparameter
# t_max is the selected number of epochs to train
SearchSpace = np.copy(self.scaleSearchSpace)
for dd in range(self.dim - 1):
SearchSpace[dd, 0], SearchSpace[dd, 1] = x_max[dd], x_max[dd]
SearchSpace[-1, 1] = t_max
temp_X, temp_T = self.X.copy(), self.T.copy()
temp_gp = copy.deepcopy(self.gp)
temp_Y = np.random.random(size=(len(temp_T), 1))
temp_gp.fit(temp_X, temp_T, temp_Y, self.Y_curves)
new_batch_T = None
pred_var_value = [0] * n_virtual_obs
for ii in range(n_virtual_obs):
x_max_pred_variance, pred_var_value[ii] = acq_max_with_name(
gp=temp_gp,
scaleSearchSpace=SearchSpace,
acq_name='pure_exploration',
IsReturnY=True)
# stop augmenting if the uncertainty is smaller than a threshold
# or stop augmenting if the uncertainty is smaller than a threshold
log_cond = np.log(temp_gp.compute_condition_number())
if log_cond > self.threshold_cond or pred_var_value[ii] < (
self.gp.noise_delta + 1e-3):
break
if x_max_pred_variance[-1] in temp_T[
-ii:]: # if repetition, stop augmenting
break
temp_X = np.vstack((temp_X, x_max.reshape(
(1, -1)))) # append new x
temp_T = np.vstack((temp_T, x_max_pred_variance[-1].reshape(
(1, -1)))) # append new t
temp_gp.X, temp_gp.T = temp_X, temp_T
temp_Y = np.random.random(size=(len(temp_T), 1))
temp_gp.fit(temp_X, temp_T, temp_Y, self.Y_curves)
if new_batch_T is None:
new_batch_T = x_max_pred_variance[-1].reshape((1, -1))
else:
new_batch_T = np.vstack(
(new_batch_T, x_max_pred_variance[-1].reshape((1, -1))))
# if self.verbose:
# print("pred_var_value at the augmented points:",np.round( pred_var_value,decimals=4))
if new_batch_T is None:
return [], 0
else:
output = np.sort(new_batch_T.ravel()).tolist()
return output, len(output)
def maximize(self):
"""
Main optimization method.
Input parameters
----------
gp_params: parameter for Gaussian Process
Returns
-------
x: recommented point for evaluation
"""
if self.stop_flag == 1:
return
if self.acq['name'] == 'random':
x_max = generate_random_points(bounds=self.scalebounds, size=1)
self.X_original = np.vstack((self.X_original, x_max))
# evaluate Y using original X
#self.Y = np.append(self.Y, self.f(temp_X_new_original))
self.Y_original = np.append(self.Y_original, self.f(x_max))
# update Y after change Y_original
self.Y = (self.Y_original - np.mean(self.Y_original)) / np.std(
self.Y_original)
self.time_opt = np.hstack((self.time_opt, 0))
return
fstar_scaled = (self.fstar - np.mean(self.Y_original)) / np.std(
self.Y_original)
# init a new Gaussian Process
if self.isTGP == 1:
self.gp = TransformedGP(self.gp_params)
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur], fstar_scaled)
else:
self.gp = GaussianProcess(self.gp_params)
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
# optimize GP parameters after 10 iterations
newlengthscale = None
# we donot optimize lengthscale for the setting of gp_lengthscale
if len(self.Y) % (4 * self.dim) == 0:
if self.optimize_gp == 'maximize':
newlengthscale = self.gp.optimize_lengthscale_SE_maximizing(
self.gp_params['lengthscale'],
self.gp_params['noise_delta'])
self.gp_params['lengthscale'] = newlengthscale
elif self.optimize_gp == 'loo':
newlengthscale = self.gp.optimize_lengthscale_SE_loo(
self.gp_params['lengthscale'],
self.gp_params['noise_delta'])
self.gp_params['lengthscale'] = newlengthscale
if self.verbose == 1:
print("estimated lengthscale =", newlengthscale)
# init a new Gaussian Process after optimizing hyper-parameter
if self.isTGP == 1:
self.gp = TransformedGP(self.gp_params)
# Find unique rows of X to avoid GP from breaking
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur], fstar_scaled)
else:
self.gp = GaussianProcess(self.gp_params)
ur = unique_rows(self.X)
self.gp.fit(self.X[ur], self.Y[ur])
# Set acquisition function
start_opt = time.time()
# run the acquisition function for the first time to get xstar
self.xstars = []
fstar_scaled = (self.fstar - np.mean(self.Y_original)) / np.std(
self.Y_original)
fstar_scaled = (self.fstar - np.mean(self.Y_original)) / np.std(
self.Y_original)
self.acq['fstar_scaled'] = np.asarray([fstar_scaled])
x_max = acq_max_with_name(gp=self.gp,
scalebounds=self.scalebounds,
acq_name=self.acq['name'],
fstar_scaled=fstar_scaled)
"""
self.acq_func = AcquisitionFunction(self.acq)
x_max = acq_max(ac=self.acq_func.acq_kind,gp=self.gp,bounds=self.scalebounds,
opt_toolbox=self.opt_toolbox)
"""
# record the optimization time
finished_opt = time.time()
elapse_opt = finished_opt - start_opt
self.time_opt = np.hstack((self.time_opt, elapse_opt))
# store X
self.X = np.vstack((self.X, x_max.reshape((1, -1))))
# compute X in original scale
temp_X_new_original = x_max * self.max_min_gap + self.bounds[:, 0]
self.X_original = np.vstack((self.X_original, temp_X_new_original))
# evaluate Y using original X
#self.Y = np.append(self.Y, self.f(temp_X_new_original))
y_original = self.f(temp_X_new_original)
self.Y_original = np.append(self.Y_original, y_original)
# update Y after change Y_original
self.Y = (self.Y_original - np.mean(self.Y_original)) / np.std(
self.Y_original)
if self.gp.flagIncremental == 1:
self.gp.fit_incremental(x_max, self.Y[-1])
