def assign_samples(self):
self.sampled_X = [v[:-1] for v in self.historical]
self.sampled_names = [
pal_strings.parseNum(v,
self.solvents,
mixed_halides=self.mixed_halides,
sort=True,
num_has_IS=True) for v in self.sampled_X
]
self.sampled_indices = [
self.combinations.index(v) for v in self.sampled_names
]
assert len(self.sampled_indices) == len(
list(set(self.sampled_indices)
)), "Error - Sampled indices contain duplicates!"
self.sampled_solvent_properties = np.array(
[np.array(v[-4:-2]) for v in self.historical])
self.sampled_objectives = [v[-1] for v in self.historical]
def sample(self,
specify=None,
debug=False,
MAX_LOOP=10,
allow_reduced=False):
'''
This function will run, in parallel, N_samples of the objective functions for
historical data generation. Note, these are run for EVERY information source.
'''
if debug:
print("Collecting LHS samples...")
if specify is None:
counter, samples = 0, []
while len(
samples) != self.historical_nsample and counter < MAX_LOOP:
# Grab a latin hypercube sample
samples = doe_lhs.lhs(
int(self.mixed_halides) * 2 + 2, self.historical_nsample)
# Round the LHS and figure out the samples
solvent_ranges = [
i * 1.0 / len(self.S)
for i in range(1,
len(self.solvents) + 1)
]
solv = lambda v: self.S[[v <= s
for s in solvent_ranges].index(True)]
trio = lambda v: [
int(v > (chk - 1.0 / 3.0) and v <= chk)
for chk in [1. / 3., 2. / 3., 1.0]
]
# Grab our samples
if self.mixed_halides:
halides = [sorted([s[0], s[1], s[2]]) for s in samples]
halides = [[trio(h) for h in hh] for hh in halides]
samples = [
h[0] + h[1] + h[2] + trio(s[3]) + [
self.solvents[solv(s[-1])]["density"],
self.solvents[solv(s[-1])]["dielectric"],
self.solvents[solv(s[-1])]["index"]
] for h, s in zip(halides, samples)
]
else:
samples = [
trio(s[0]) + trio(s[1]) + [
self.solvents[solv(s[-1])]["density"],
self.solvents[solv(s[-1])]["dielectric"],
self.solvents[solv(s[-1])]["index"]
] for s in samples
]
# Ensure no duplicates
samples = sorted(samples, key=lambda x: x[-1])
samples = [tuple(s) for s in samples]
samples = [list(s) for s in set(samples)]
counter += 1
else:
if isinstance(specify, int):
specify = [specify]
self.historical_nsample = len(specify)
samples = [self.combinations[i] for i in specify]
samples = pal_strings.alphaToNum(samples,
solvents,
mixed_halides=self.mixed_halides,
name_has_IS=True)
samples = [s[1:] for s in samples
] # Remove the IS label from the descriptor
if allow_reduced:
print(
"Warning - Will sample from subspace due to duplicates (%d instead of %d)."
% (len(samples), self.historical_nsample))
self.historical_nsample = len(samples)
elif specify is None:
assert counter < MAX_LOOP, "Error - Unable to sample from space without duplicates!"
if debug:
print("Will sample %s" % str(samples))
# Now, run these simulations to get the sample points
jobs = []
for i, sample in enumerate(samples):
if debug:
print "Running %s..." % sample
s = pal_strings.parseNum(sample,
self.solvents,
mixed_halides=self.mixed_halides,
num_has_IS=False)
hat, cat, _, solv, _ = pal_strings.parseName(s, name_has_IS=False)
cat = cat[0]
if not self.mixed_halides:
hat = hat[0]
if debug:
print("\tAdding %s to sample runs..." % s)
for j, obj in enumerate(self.IS):
jobs.append([[j] + copy.deepcopy(sample), obj(hat, cat, solv)])
# Now, get results from each simulation
samples = []
for sample, j in jobs:
if not isinstance(j, float):
j.wait()
samples.append(sample + [j.get_result()])
# In special situations, when we are reading from a list for example, we don't need to worry
# about a job object, and can just assign the value directly.
else:
samples.append(sample + [j])
s = pal_strings.parseNum(samples[-1][:-1],
self.solvents,
mixed_halides=self.mixed_halides,
num_has_IS=True)
if debug:
print("\t%s was found as %lg" % (s, samples[-1][-1]))
# Save the sampled data
fptr = open(self.fname_historical, "w")
pickle.dump(samples, fptr)
fptr.close()
self.historical = samples
if debug:
print("Done Collecting Samples\n")
sim.combinations = [k[1] + "Pb" + k[0] + "_" + k[2] + "_" + str(IS) for k in [key.split() for key in IS0.keys()] for IS in range(len(sim.IS))]
combos_no_IS = [k[1] + "Pb" + k[0] + "_" + k[2] for k in [key.split() for key in IS0.keys()]]
# Because we do this, we should also generate our own historical sample
sim.historical_nsample = len(combos_no_IS)
choices = combos_no_IS
tmp_data = pal_strings.alphaToNum(
choices,
solvents,
mixed_halides=True,
name_has_IS=False)
data = []
for IS in range(len(sim.IS)):
for i, d in enumerate(tmp_data):
h, c, _, s, _ = pal_strings.parseName(pal_strings.parseNum(d, solvents, mixed_halides=True, num_has_IS=False), name_has_IS=False)
c = c[0]
data.append([IS] + d + [sim.IS[IS](h, c, s)])
IS0 = np.array([x[-1] for x in data if x[0] == 0])
IS1 = np.array([x[-1] * 1.8 for x in data if x[0] == 1])
IS0, IS1 = zip(*sorted(zip(IS0, IS1)))
# IS0 = IS0 / np.linalg.norm(IS0)
# IS1 = IS1 / np.linalg.norm(IS1)
# print IS0
# print IS1
import matplotlib.pyplot as plt
def run_misokg(run_index):
# Store data for debugging
IS0 = pickle.load(open("enthalpy_N1_R3_Ukcal-mol", 'r'))
IS1 = pickle.load(open("enthalpy_N1_R2_Ukcal-mol", 'r'))
# Generate the main object
sim = Optimizer()
# Assign simulation properties
#sim.hyperparameter_objective = MAP
sim.hyperparameter_objective = MLE
###################################################################################################
# File names
sim.fname_out = "enthalpy_misokg.dat"
sim.fname_historical = None
# Information sources, in order from expensive to cheap
sim.IS = [
lambda h, c, s: -1.0 * IS0[' '.join([''.join(h), c, s])],
lambda h, c, s: -1.0 * IS1[' '.join([''.join(h), c, s])]
]
sim.costs = [1.0, 0.1]
sim.logger_fname = "data_dumps/%d_misokg.log" % run_index
if os.path.exists(sim.logger_fname):
os.system("rm %s" % sim.logger_fname)
os.system("touch %s" % sim.logger_fname)
sim.obj_vs_cost_fname = "data_dumps/%d_misokg.dat" % run_index
sim.mu_fname = "data_dumps/%d_mu_misokg.dat" % run_index
sim.sig_fname = "data_dumps/%d_sig_misokg.dat" % run_index
sim.combos_fname = "data_dumps/%d_combos_misokg.dat" % run_index
sim.hp_fname = "data_dumps/%d_hp_misokg.dat" % run_index
sim.acquisition_fname = "data_dumps/%d_acq_misokg.dat" % run_index
sim.save_extra_files = True
########################################
# Override the possible combinations with the reduced list of IS0
# Because we do this, we should also generate our own historical sample
combos_no_IS = [
k[1] + "Pb" + k[0] + "_" + k[2]
for k in [key.split() for key in IS0.keys()]
]
sim.historical_nsample = 10
choices = np.random.choice(combos_no_IS,
sim.historical_nsample,
replace=False)
tmp_data = pal_strings.alphaToNum(choices,
solvents,
mixed_halides=True,
name_has_IS=False)
data = []
for IS in range(len(sim.IS)):
for i, d in enumerate(tmp_data):
h, c, _, s, _ = pal_strings.parseName(pal_strings.parseNum(
d, solvents, mixed_halides=True, num_has_IS=False),
name_has_IS=False)
c = c[0]
data.append([IS] + d + [sim.IS[IS](h, c, s)])
sim.fname_historical = "data_dumps/%d.history" % run_index
pickle.dump(data, open(sim.fname_historical, 'w'))
simple_data = [d for d in data if d[0] == 0]
pickle.dump(simple_data,
open("data_dumps/%d_reduced.history" % run_index, 'w'))
########################################
sim.n_start = 10 # The number of starting MLE samples
sim.reopt = 20
sim.ramp_opt = None
sim.parallel = False
# Possible compositions by default
sim.A = ["Cs", "MA", "FA"]
sim.B = ["Pb"]
sim.X = ["Cl", "Br", "I"]
sim.solvents = copy.deepcopy(solvents)
sim.S = list(set([v["name"] for k, v in sim.solvents.items()]))
sim.mixed_halides = True
sim.mixed_solvents = False
# Parameters for debugging and overwritting
sim.debug = False
sim.verbose = True
sim.overwrite = True # If True, warning, else Error
sim.acquisition = getNextSample_misokg
# Functional forms of our mean and covariance
# MEAN: 4 * mu_alpha + mu_zeta
# COV: sig_alpha * |X><X| + sig_beta * I_N + sig_zeta + MaternKernel(S, weights, sig_m)
SCALE = [2.0, 4.0][int(sim.mixed_halides)]
# _1, _2, _3 used as dummy entries
def mean(X, Y, theta):
mu = np.array([SCALE * theta.mu_alpha + theta.mu_zeta for _ in Y])
return mu
sim.mean = mean
def cov_old(X, Y, theta):
A = theta.sig_alpha * np.dot(
np.array(X)[:, 1:-3],
np.array(X)[:, 1:-3].T)
B = theta.sig_beta * np.diag(np.ones(len(X)))
C = theta.sig_zeta
D = mk52(np.array(X)[:, -3:-1], [theta.l1, theta.l2], theta.sig_m)
return theta.rho_matrix(X) * (A + B + C + D)
def cov(X0, Y, theta):
A = theta.sig_alpha * np.dot(
np.array(X0)[:, :-3],
np.array(X0)[:, :-3].T)
B = theta.sig_beta * np.diag(np.ones(len(X0)))
C = theta.sig_zeta
D = mk52(np.array(X0)[:, -3:-1], [theta.l1, theta.l2], theta.sig_m)
Kx = A + B + C + D
Ks = np.array([
np.array(
[theta.rho[str(sorted([i, j]))] for j in range(theta.n_IS)])
for i in range(theta.n_IS)
])
if theta.normalize_Ks:
Ks = Ks / np.linalg.norm(Ks)
e = np.diag(np.array([theta.e1, theta.e2]))
Ks = e.dot(Ks.dot(e))
return np.kron(Ks, Kx)
sim.cov = cov
sim.theta.bounds = {}
sim.theta.mu_alpha, sim.theta.bounds['mu_alpha'] = None, (
1E-3, lambda _, Y: max(Y))
sim.theta.sig_alpha, sim.theta.bounds['sig_alpha'] = None, (
1E-2, lambda _, Y: 10.0 * np.var(Y))
sim.theta.sig_beta, sim.theta.bounds['sig_beta'] = None, (
1E-2, lambda _, Y: 10.0 * np.var(Y))
sim.theta.mu_zeta, sim.theta.bounds['mu_zeta'] = None, (
1E-3, lambda _, Y: max(Y))
sim.theta.sig_zeta, sim.theta.bounds['sig_zeta'] = None, (
1E-2, lambda _, Y: 10.0 * np.var(Y))
sim.theta.sig_m, sim.theta.bounds['sig_m'] = None, (1E-2,
lambda _, Y: np.var(Y))
sim.theta.l1, sim.theta.bounds['l1'] = None, (1E-1, 1)
sim.theta.l2, sim.theta.bounds['l2'] = None, (1E-1, 1)
sim.theta.e1, sim.theta.bounds['e1'] = None, (1E-1, 1.0)
sim.theta.e2, sim.theta.bounds['e2'] = None, (1E-1, 1.0)
# # NOTE! This is a reserved keyword in misoKG. We will generate a list of the same length
# # of the information sources, and use this for scaling our IS.
sim.theta.rho = {"[0, 0]": 1.0, "[0, 1]": 0.96, "[1, 1]": 1.0}
sim.theta.bounds['rho [0, 0]'] = (0.1, 1.0)
sim.theta.bounds['rho [0, 1]'] = (0.1, 1.0)
sim.theta.bounds['rho [1, 1]'] = (0.1, 1.0)
sim.theta.set_hp_names()
sim.primary_rho_opt = False
sim.update_hp_only_with_IS0 = False
sim.update_hp_only_with_overlapped = False
sim.theta.normalize_L = False
sim.theta.normalize_Ks = False
# This was a test feature that actually over-wrote rho to be PSD
# sim.force_rho_psd = True
sim.recommendation_kill_switch = "FAPbBrBrCl_THTO_0"
###################################################################################################
# Start simulation
sim.run()
def run_misokg(run_index):
# Store data for debugging
IS0 = pickle.load(open("enthalpy_N1_R3_Ukcal-mol", 'r'))
IS1 = pickle.load(open("enthalpy_N1_R2_Ukcal-mol", 'r'))
# Generate the main object
sim = Optimizer()
# Assign simulation properties
#sim.hyperparameter_objective = MAP
sim.hyperparameter_objective = MLE
###################################################################################################
# File names
sim.fname_out = "enthalpy_misokg.dat"
sim.fname_historical = None
# Information sources, in order from expensive to cheap
sim.IS = [
lambda h, c, s: -1.0 * IS0[' '.join([''.join(h), c, s])],
lambda h, c, s: -1.0 * IS1[' '.join([''.join(h), c, s])]
]
sim.costs = [
1.0,
0.1,
]
sim.logger_fname = "data_dumps/%d_misokg.log" % run_index
if os.path.exists(sim.logger_fname):
os.system("rm %s" % sim.logger_fname)
os.system("touch %s" % sim.logger_fname)
sim.obj_vs_cost_fname = "data_dumps/%d_misokg.dat" % run_index
sim.mu_fname = "data_dumps/%d_mu_misokg.dat" % run_index
sim.sig_fname = "data_dumps/%d_sig_misokg.dat" % run_index
sim.combos_fname = "data_dumps/%d_combos_misokg.dat" % run_index
sim.hp_fname = "data_dumps/%d_hp_misokg.dat" % run_index
sim.acquisition_fname = "data_dumps/%d_acq_misokg.dat" % run_index
sim.save_extra_files = True
########################################
# Override the possible combinations with the reduced list of IS0
# Because we do this, we should also generate our own historical sample
combos_no_IS = [
k[1] + "Pb" + k[0] + "_" + k[2]
for k in [key.split() for key in IS0.keys()]
]
#sim.historical_nsample = 240
sim.historical_nsample = 10
choices = np.random.choice(combos_no_IS,
sim.historical_nsample,
replace=False)
tmp_data = pal_strings.alphaToNum(choices,
solvents,
mixed_halides=True,
name_has_IS=False)
data = []
for IS in range(len(sim.IS)):
for i, d in enumerate(tmp_data):
h, c, _, s, _ = pal_strings.parseName(pal_strings.parseNum(
d, solvents, mixed_halides=True, num_has_IS=False),
name_has_IS=False)
c = c[0]
data.append([IS] + d + [sim.IS[IS](h, c, s)])
sim.fname_historical = "data_dumps/%d.history" % run_index
pickle.dump(data, open(sim.fname_historical, 'w'))
simple_data = [d for d in data if d[0] == 0]
pickle.dump(simple_data,
open("data_dumps/%d_reduced.history" % run_index, 'w'))
########################################
sim.n_start = 10 # The number of starting MLE samples
sim.reopt = 10
sim.ramp_opt = None
sim.parallel = False
# Possible compositions by default
sim.A = ["Cs", "MA", "FA"]
sim.B = ["Pb"]
sim.X = ["Cl", "Br", "I"]
sim.solvents = copy.deepcopy(solvents)
sim.S = list(set([v["name"] for k, v in sim.solvents.items()]))
sim.mixed_halides = True
sim.mixed_solvents = False
# Parameters for debugging and overwritting
sim.debug = False
sim.verbose = True
sim.overwrite = True # If True, warning, else Error
sim.acquisition = getNextSample_misokg
# Functional forms of our mean and covariance
# MEAN: 4 * mu_alpha + mu_zeta
# COV: sig_alpha * |X><X| + sig_beta * I_N + sig_zeta + MaternKernel(S, weights, sig_m)
SCALE = [2.0, 4.0][int(sim.mixed_halides)]
# _1, _2, _3 used as dummy entries
def mean(X, Y, theta):
mu = np.array([SCALE * theta.mu_alpha + theta.mu_zeta for _ in Y])
return mu
sim.mean = mean
def cov_old(X, Y, theta):
A = theta.sig_alpha * np.dot(
np.array(X)[:, 1:-3],
np.array(X)[:, 1:-3].T)
B = theta.sig_beta * np.diag(np.ones(len(X)))
C = theta.sig_zeta
D = mk52(np.array(X)[:, -3:-1], [theta.l1, theta.l2], theta.sig_m)
return theta.rho_matrix(X) * (A + B + C + D)
def cov_old2(X, Y, theta):
A = theta.sig_alpha * np.dot(
np.array(X)[:, 1:-3],
np.array(X)[:, 1:-3].T)
B = theta.sig_beta * np.diag(np.ones(len(X)))
C = theta.sig_zeta
D = mk52(np.array(X)[:, -3:-1], [theta.l1, theta.l2], theta.sig_m)
return theta.rho_matrix(X, use_psd=True) * (A + B + C + D)
def cov_new(X, Y, theta):
# Get a list of all unique X, removing initial IS identifier
X0 = []
for x in X:
if not any(
[all([a == b for a, b in zip(x[1:], xchk)]) for xchk in X0]):
X0.append(x[1:])
A = theta.sig_alpha * np.dot(
np.array(X0)[:, :-3],
np.array(X0)[:, :-3].T)
B = theta.sig_beta * np.diag(np.ones(len(X0)))
C = theta.sig_zeta
D = mk52(np.array(X0)[:, -3:-1], [theta.l1, theta.l2], theta.sig_m)
Kx = A + B + C + D
L = np.array([
np.array([
theta.rho[str(sorted([i, j]))] if i >= j else 0.0
for j in range(theta.n_IS)
]) for i in range(theta.n_IS)
])
# Normalize L to stop over-scaling values small
L = L / np.linalg.norm(L)
# Force it to be positive semi-definite
Ks = L.dot(L.T)
return np.kron(Ks, Kx)
#K = np.kron(Ks, Kx)
# Now, we get the sub-covariance matrix for the specified sampled X and Y
indices = []
for l in range(theta.n_IS):
for i, x in enumerate(X0):
test = [l] + list(x)
if any(
[all([a == b for a, b in zip(test, xchk)]) for xchk in X]):
indices.append(l * len(X0) + i)
K_local = K[np.ix_(indices, indices)]
return K_local
sim.cov = cov_new
sim.theta.bounds = {}
sim.theta.mu_alpha, sim.theta.bounds['mu_alpha'] = None, (
1E-3, lambda _, Y: max(Y))
sim.theta.sig_alpha, sim.theta.bounds['sig_alpha'] = None, (
1E-2, lambda _, Y: 10.0 * np.var(Y))
sim.theta.sig_beta, sim.theta.bounds['sig_beta'] = None, (
1E-2, lambda _, Y: 10.0 * np.var(Y))
sim.theta.mu_zeta, sim.theta.bounds['mu_zeta'] = None, (
1E-3, lambda _, Y: max(Y))
sim.theta.sig_zeta, sim.theta.bounds['sig_zeta'] = None, (
1E-2, lambda _, Y: 10.0 * np.var(Y))
sim.theta.sig_m, sim.theta.bounds['sig_m'] = None, (1E-2,
lambda _, Y: np.var(Y))
sim.theta.l1, sim.theta.bounds['l1'] = None, (1E-1, 1)
sim.theta.l2, sim.theta.bounds['l2'] = None, (1E-1, 1)
# # NOTE! This is a reserved keyword in misoKG. We will generate a list of the same length
# # of the information sources, and use this for scaling our IS.
# sim.theta.rho = {"[0, 0]": 1, "[0, 1]": None, "[1, 1]": 1}
# sim.theta.bounds['rho [0, 1]'] = (-1.0, 1.0)
# sim.theta.bounds['rho [0, 0]'] = (1, 1)
# sim.theta.bounds['rho [1, 1]'] = (1, 1)
sim.theta.rho = {"[0, 0]": None, "[0, 1]": None, "[1, 1]": None}
sim.theta.bounds['rho [0, 0]'] = (0.1, 1.0)
sim.theta.bounds['rho [0, 1]'] = (0.1, 1.0)
sim.theta.bounds['rho [1, 1]'] = (0.1, 1.0)
sim.theta.set_hp_names()
sim.primary_rho_opt = False
#sim.update_hp_only_with_IS0 = True
sim.update_hp_only_with_overlapped = True
###################################################################################################
# Start simulation
sim.run()