class bo(object):
def __init__(self, f, X, y, x_range, eval_only, extra, options):
self.f = f
self.t = options['t']
self.x_range = x_range
self.options = options
self.well_defined = X.shape[0] > 0
self.solver = GibbsSampler(X, y, options)
self.eval_only = eval_only
self.opt_n = options['opt_n']
self.dx = options['dx']
if eval_only:
self.newX = extra
else:
self.n_bo = extra
self.opt_n = np.maximum(self.opt_n, self.n_bo * 2)
if 'ziw' in options:
self.max_value = self.options['max_value'] + np.random.normal(
) * 0.05
else:
self.max_value = self.options['max_value']
self.n_bo_top_percent = self.options['n_bo_top_percent']
def learn(self):
self.gp, self.z, self.k = self.solver.run(self.options['gibbs_iter'])
def run(self):
if self.eval_only:
ynew = [self.f(x) for x in self.newX]
return ynew
# return random inputs if X is empty
if not self.well_defined:
xnew = np.random.uniform(self.x_range[0], self.x_range[1],
(self.n_bo, self.dx))
acfnew = [self.max_value] * self.n_bo
return xnew, acfnew, self.solver.z, self.solver.k, self.max_value
# learn and optimize
self.learn()
# initialization
xnew = np.empty((self.n_bo, self.dx))
xnew[0] = np.random.uniform(self.x_range[0], self.x_range[1])
# optimize group by group
all_cat = np.unique(self.z)
for a in np.random.permutation(all_cat):
active = self.z == a
af = lambda x: MAX_VALUE(x, xnew[0], active, self.max_value, self.
gp) # lower confidential bound
xnew[:, active], acfnew = global_minimize(af, self.x_range[:,active], \
self.opt_n, self.n_bo, self.n_bo_top_percent)
return xnew, acfnew, self.z, self.k, self.max_value
parser.add_argument("-y", "--yaml", help = "Specify yaml file")
args = parser.parse_args()
yaml_file = args.yaml
with open(yaml_file) as yml:
cdict = yaml.load(yml, Loader = yaml.FullLoader)
Ldict = {key : cdict[key] for key in cdict if (key in LikelihoodFg.__init__.__code__.co_varnames)}
Lclass = LikelihoodFg(**Ldict)
Gdict = {key : cdict[key] for key in cdict if (key in GibbsSampler.__init__.__code__.co_varnames)}
Nstep = 30000
gibbs_sampler = GibbsSampler(Nstep, Lclass, args.resume, **Gdict)
gibbs_sampler.run()
def get_lag(id, kmax, accepted):
a = accepted[:, id]
a_avg = np.mean(a)
N = len(a)
denom = np.sum((a-a_avg)**2)
lag = []
for k in range(1, kmax + 1):
num = 0
for i in range(0, N - k):
num += (a[i] - a_avg) * (a[i+k]-a_avg)
lag.append(num)
lag = np.array(lag)
def main():
### Parse command line options
usage = "usage: %prog [options] datafile"
cmdline_parser = OptionParser(usage=usage)
cmdline_parser.add_option('-o',
'--output',
dest='output_filename',
metavar='FILE',
default='results.pkl',
help='Serialize results to pickle FILE')
cmdline_parser.add_option('-m',
'--model',
dest='model',
metavar='FILE',
default='model',
help='Choose model to use')
cmdline_parser.add_option('-v',
'--verbose',
dest='loglevel',
default=logging.WARNING,
action='store_const',
const=logging.DEBUG,
help='Debug logging level mode')
cmdline_parser.add_option('-i',
'--iterations',
dest='iterations',
type='int',
default=25000,
help='Number of Gibbs iterations')
cmdline_parser.add_option('-b',
'--burnin',
dest='burnin',
type='int',
default=500,
help='Number of burn-in iterations')
cmdline_parser.add_option('-s',
'--subsample',
dest='subsample',
type='int',
default=10,
help='Subsample rate')
cmdline_parser.add_option('-t',
'--start',
dest='start',
type='int',
default=None,
help='start')
cmdline_parser.add_option('-e',
'--end',
dest='end',
type='int',
default=None,
help='end')
cmdline_parser.add_option('-g',
'--visualize',
dest='visualize',
action='store_true',
help='Visualize intermediate results')
cmdline_parser.add_option('-G',
'--visualize-priors',
dest='visualize_priors',
action='store_true',
help='Visualize prior distributions')
cmdline_parser.add_option(
'-p',
'--parameter-file',
dest='parameter_filename',
help='Use known parameters in file (i.e. simulated file).')
options, args = cmdline_parser.parse_args()
logging.basicConfig(level=options.loglevel,
format='%(asctime)s %(message)s')
data_filename = args[0]
gibbs_iters = options.iterations
burnin = options.burnin
subsample = options.subsample
model_module = __import__(options.model)
if options.parameter_filename is not None:
known_params = pickle.load(open(options.parameter_filename, 'rb'))
# Build model and load data
data = load_as_frame(data_filename, start=options.start, end=options.end)
model = model_module.define_model(data, known_params)
# Setup gibbs sampler
sampler = GibbsSampler(model=model,
iterations=gibbs_iters,
burnin=burnin,
subsample=subsample)
if options.visualize:
sampler.add_visualizer(model_module.visualize_gibbs)
if options.visualize_priors:
model_module.visualize_priors(model.priors)
# Begin sampling
start_time = time.time()
sampler.run()
gibbs_time = time.time() - start_time
print "Gibbs sampler ran %d.1 minutes" % (gibbs_time / 60.)
# Write out results
results = {}
results['options'] = options
results['variable_names'] = model.variable_names
results['known_params'] = model.known_params
results['hyper_params'] = model.hyper_params
results['filename'] = data_filename
results['data'] = data
results['gibbs_results'] = sampler.results()
pickle.dump(results, open(options.output_filename, 'wb'))
'''
This is an example using 3 input ensembles Adenylate Kinase pdb_chainID: 1AKE_A, 4AKE_A, 1ANK_A
'''
import numpy as np
from gibbs import load_coordinates, GibbsSampler
from matplotlib import pyplot as plt
input_coordinate = load_coordinates('1AKE_A', '4AKE_A', '1ANK_A')
#Run Gibb sampler using 2 priors
gibb = GibbsSampler(input_coordinate, prior=2)
gibb.run(500)
print 'Number of Domain = ', np.unique(gibb.membership).shape[0]
print 'Membership', gibb.membership
print 'Log likelihood = ', gibb.log_likelihood
plt.plot(gibb.membership)
plt.title('Membership')
plt.show()
def main():
### Parse command line options
usage = "usage: %prog [options] datafile"
cmdline_parser = OptionParser(usage=usage)
cmdline_parser.add_option(
'-o', '--output', dest='output_filename', metavar='FILE',
default='results.pkl',
help='Serialize results to pickle FILE')
cmdline_parser.add_option(
'-m', '--model', dest='model', metavar='FILE',
default='model',
help='Choose model to use')
cmdline_parser.add_option(
'-v', '--verbose', dest='loglevel', default=logging.WARNING,
action='store_const', const=logging.DEBUG,
help='Debug logging level mode')
cmdline_parser.add_option(
'-i', '--iterations', dest='iterations',
type='int', default=25000,
help='Number of Gibbs iterations')
cmdline_parser.add_option(
'-b', '--burnin', dest='burnin',
type='int', default=500,
help='Number of burn-in iterations')
cmdline_parser.add_option(
'-s', '--subsample', dest='subsample',
type='int', default=10,
help='Subsample rate')
cmdline_parser.add_option(
'-t', '--start', dest='start',
type='int', default=None,
help='start')
cmdline_parser.add_option(
'-e', '--end', dest='end',
type='int', default=None,
help='end')
cmdline_parser.add_option(
'-g', '--visualize', dest='visualize',
action='store_true',
help='Visualize intermediate results')
cmdline_parser.add_option(
'-G', '--visualize-priors', dest='visualize_priors',
action='store_true',
help='Visualize prior distributions')
cmdline_parser.add_option(
'-p', '--parameter-file', dest='parameter_filename',
help='Use known parameters in file (i.e. simulated file).')
options, args = cmdline_parser.parse_args()
logging.basicConfig(level=options.loglevel, format='%(asctime)s %(message)s')
data_filename = args[0]
gibbs_iters = options.iterations
burnin = options.burnin
subsample = options.subsample
model_module = __import__(options.model)
if options.parameter_filename is not None:
known_params = pickle.load(open(options.parameter_filename, 'rb'))
# Build model and load data
data = load_as_frame(data_filename, start=options.start, end=options.end)
model = model_module.define_model(data, known_params)
# Setup gibbs sampler
sampler = GibbsSampler(
model=model,
iterations=gibbs_iters,
burnin=burnin,
subsample=subsample)
if options.visualize:
sampler.add_visualizer(model_module.visualize_gibbs)
if options.visualize_priors:
model_module.visualize_priors(model.priors)
# Begin sampling
start_time = time.time()
sampler.run()
gibbs_time = time.time() - start_time
print "Gibbs sampler ran %d.1 minutes" % (gibbs_time/60.)
# Write out results
results = {}
results['options'] = options
results['variable_names'] = model.variable_names
results['known_params'] = model.known_params
results['hyper_params'] = model.hyper_params
results['filename'] = data_filename
results['data'] = data
results['gibbs_results'] = sampler.results()
pickle.dump(results, open(options.output_filename, 'wb'))