def main(argv):
"""
n_train
n_test
d is the dimension of the samples. Should be higher than 2 and preferable 10 or more..
output_dir is the directory in which we'll write the results
"""
import getopt
import cPickle
try:
opts, args = getopt.getopt(
sys.argv[1:], "hv", ["n_train=", "n_test=", "d=", "output_dir="])
except getopt.GetoptError as err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
n_train = None
n_test = None
d = None
output_dir = None
verbose = False
for o, a in opts:
if o == "-v":
verbose = True
elif o in ("-h", "--help"):
usage()
sys.exit()
elif o in ("--n_train"):
n_train = int(a)
elif o in ("--n_test"):
n_test = int(a)
elif o in ("--d"):
d = int(a)
elif o in ("--output_dir"):
output_dir = a
else:
assert False, "unhandled option"
assert n_train
assert n_test
assert d
assert output_dir
# These points are used to define the arcs from which the samples are drawn.
base_number_of_points = 8
(base_x, top_arc, bottom_arc, twin_bumps_obs_noise_stddev,
twin_bumps_kernel_stddev
) = generate_pinched_twin_bumps_quasi_mirrored_gp(base_number_of_points)
# These values are hardcoded to yield something that looks good.
# We're not really interested in varying those with parameters.
kernel_stddev = 0.15
obs_noise_stddev = 0.2
def kernel(x1, x2):
return gaussian_process.square_distance_kernel_1D(
x1, x2, kernel_stddev)
samples_x = np.linspace(0.0, 1.0, d)
N = n_train + n_test
samples = np.zeros((N, d))
# Track from which arc you get the sample.
cluster_index = np.array(np.random.uniform(0, 1, size=N) < 0.5, dtype=int)
# Not the most efficient way to do this because it
# recomputes certain matrices instead of caching them,
# but that's not important.
for n in range(N):
R = gaussian_process.sample_trajectory_1D(
base_x,
top_arc * cluster_index[n] + bottom_arc * (1 - cluster_index[n]),
kernel, samples_x, obs_noise_stddev)
samples[n, :] = R['samples']
# always the same f_star_mean and f_star_cov
f_star_mean = R['f_star_mean']
f_star_cov = R['f_star_cov']
if not os.path.exists(output_dir):
os.makedirs(output_dir)
print "Creating directory %s" % output_dir,
extra_props = {
'base_x': base_x,
'top_arc': top_arc,
'bottom_arc': bottom_arc,
'samples_x': samples_x,
'f_star_mean': f_star_mean,
'f_star_cov': f_star_cov,
'n': None,
'd': d,
'kernel_stddev': kernel_stddev,
'obs_noise_stddev': obs_noise_stddev,
'base_number_of_points': base_number_of_points,
'twin_bumps_obs_noise_stddev': twin_bumps_obs_noise_stddev,
'twin_bumps_kernel_stddev': twin_bumps_kernel_stddev
}
#print type(extra_props)
#print type(conj(extra_props, ('n', n_train)))
#print type(dict(extra_props.items() + [('lupi',"chien")]))
#quit()
train_samples = samples[0:n_train, :]
train_cluster_index = cluster_index[0:n_train]
train_samples_filename = os.path.join(output_dir, "train_samples.pkl")
train_samples_extra_filename = os.path.join(output_dir,
"train_samples_extra.pkl")
cPickle.dump(train_samples, open(train_samples_filename, "w"))
cPickle.dump(
conj(conj(extra_props, ('n', n_train)),
('cluster_indices', train_cluster_index)),
open(train_samples_extra_filename, "w"))
print "wrote " + train_samples_filename
print "wrote " + train_samples_extra_filename
test_samples = samples[n_train:(n_train + n_test), :]
test_cluster_index = cluster_index[n_train:(n_train + n_test)]
test_samples_filename = os.path.join(output_dir, "test_samples.pkl")
test_samples_extra_filename = os.path.join(output_dir,
"test_samples_extra.pkl")
cPickle.dump(test_samples, open(test_samples_filename, "w"))
cPickle.dump(
conj(conj(extra_props, ('n', n_test)),
('cluster_indices', test_cluster_index)),
open(test_samples_extra_filename, "w"))
print "wrote " + test_samples_filename
print "wrote " + test_samples_extra_filename
output_image_file = os.path.join(output_dir, "overview.png")
plot_the_overview(base_x, top_arc, bottom_arc, samples_x,
train_samples[0:10, :], train_samples[10:20, :],
output_image_file)
print "wrote " + output_image_file
def main(argv):
"""
n_train
n_test
d is the dimension of the samples. Should be higher than 2 and preferable 10 or more.
mixing_prop controls how much of the vector v_t we mix in with the proposal for v_{t+1}
leading_eigenvalue
n_components
output_dir is the directory in which we'll write the results
"""
import getopt
import cPickle
try:
opts, args = getopt.getopt(sys.argv[1:], "hv", ["d=", "n_train=", "n_test=", "mixing_prop=", "leading_eigenvalue=", "n_components=", "output_dir="])
except getopt.GetoptError as err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
n_train = None
n_test = None
d = None
mixing_prop = 0.5
leading_eigenvalue = 1.0
output_dir = None
verbose = False
for o, a in opts:
if o == "-v":
verbose = True
elif o in ("-h", "--help"):
usage()
sys.exit()
elif o in ("--n_train"):
n_train = int(a)
elif o in ("--n_test"):
n_test = int(a)
elif o in ("--d"):
d = int(a)
elif o in ("--mixing_prop"):
mixing_prop = float(a)
elif o in ("--leading_eigenvalue"):
leading_eigenvalue = float(a)
elif o in ("--n_components"):
n_components = int(a)
elif o in ("--output_dir"):
output_dir = a
else:
assert False, "unhandled option"
assert n_train
assert n_test
assert d
assert n_components
assert output_dir
start_time = time.time()
(component_means, component_covariances) = sample_manifold_components(d, n_components, leading_eigenvalue, mixing_prop)
(samples, component_indices) = sample_from_mixture(component_means, component_covariances, n_train + n_test)
end_time = time.time()
computational_cost_in_seconds = int(end_time - start_time)
print "Sampling took %d seconds." % computational_cost_in_seconds
print component_means
if not os.path.exists(output_dir):
os.makedirs(output_dir)
print "Creating directory %s" % output_dir,
extra_props = {'component_means':component_means,
'component_covariances':component_covariances,
#'n_train':n_train,
#'n_test':n_test,
'd':d,
'leading_eigenvalue':leading_eigenvalue,
'mixing_prop':mixing_prop,
'n_components':n_components,
'computational_cost_in_seconds':computational_cost_in_seconds}
train_samples = samples[0:n_train,:]
train_component_indices = component_indices[0:n_train]
train_samples_filename = os.path.join(output_dir, "train_samples.pkl")
train_samples_extra_filename = os.path.join(output_dir, "train_samples_extra.pkl")
cPickle.dump(train_samples, open(train_samples_filename, "w"))
cPickle.dump(conj(conj(extra_props,
('n', n_train)),
('component_indices', train_component_indices)),
open(train_samples_extra_filename, "w"))
print "wrote " + train_samples_filename
print "wrote " + train_samples_extra_filename
test_samples = samples[n_train:(n_train + n_test),:]
test_component_indices= component_indices[n_train:(n_train + n_test)]
test_samples_filename = os.path.join(output_dir, "test_samples.pkl")
test_samples_extra_filename = os.path.join(output_dir, "test_samples_extra.pkl")
cPickle.dump(test_samples, open(test_samples_filename, "w"))
cPickle.dump(conj(conj(extra_props,
('n', n_test)),
('component_indices', test_component_indices)),
open(test_samples_extra_filename, "w"))
print "wrote " + test_samples_filename
print "wrote " + test_samples_extra_filename
for i in range(0,d-1):
output_image_file = os.path.join(output_dir,"overview_dimensions_%d_and_%d.png" % (i,i+1))
plot_the_overview(samples, i, i+1, output_image_file)
print "wrote " + output_image_file
def main(argv):
"""
n_train
n_test
d is the dimension of the samples. Should be higher than 2 and preferable 10 or more.
mixing_prop controls how much of the vector v_t we mix in with the proposal for v_{t+1}
leading_eigenvalue
n_components
output_dir is the directory in which we'll write the results
"""
import getopt
import cPickle
try:
opts, args = getopt.getopt(sys.argv[1:], "hv", [
"d=", "n_train=", "n_test=", "mixing_prop=", "leading_eigenvalue=",
"n_components=", "output_dir="
])
except getopt.GetoptError as err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
n_train = None
n_test = None
d = None
mixing_prop = 0.5
leading_eigenvalue = 1.0
output_dir = None
verbose = False
for o, a in opts:
if o == "-v":
verbose = True
elif o in ("-h", "--help"):
usage()
sys.exit()
elif o in ("--n_train"):
n_train = int(a)
elif o in ("--n_test"):
n_test = int(a)
elif o in ("--d"):
d = int(a)
elif o in ("--mixing_prop"):
mixing_prop = float(a)
elif o in ("--leading_eigenvalue"):
leading_eigenvalue = float(a)
elif o in ("--n_components"):
n_components = int(a)
elif o in ("--output_dir"):
output_dir = a
else:
assert False, "unhandled option"
assert n_train
assert n_test
assert d
assert n_components
assert output_dir
start_time = time.time()
(component_means, component_covariances) = sample_manifold_components(
d, n_components, leading_eigenvalue, mixing_prop)
(samples, component_indices) = sample_from_mixture(component_means,
component_covariances,
n_train + n_test)
end_time = time.time()
computational_cost_in_seconds = int(end_time - start_time)
print "Sampling took %d seconds." % computational_cost_in_seconds
print component_means
if not os.path.exists(output_dir):
os.makedirs(output_dir)
print "Creating directory %s" % output_dir,
extra_props = {
'component_means': component_means,
'component_covariances': component_covariances,
#'n_train':n_train,
#'n_test':n_test,
'd': d,
'leading_eigenvalue': leading_eigenvalue,
'mixing_prop': mixing_prop,
'n_components': n_components,
'computational_cost_in_seconds': computational_cost_in_seconds
}
train_samples = samples[0:n_train, :]
train_component_indices = component_indices[0:n_train]
train_samples_filename = os.path.join(output_dir, "train_samples.pkl")
train_samples_extra_filename = os.path.join(output_dir,
"train_samples_extra.pkl")
cPickle.dump(train_samples, open(train_samples_filename, "w"))
cPickle.dump(
conj(conj(extra_props, ('n', n_train)),
('component_indices', train_component_indices)),
open(train_samples_extra_filename, "w"))
print "wrote " + train_samples_filename
print "wrote " + train_samples_extra_filename
test_samples = samples[n_train:(n_train + n_test), :]
test_component_indices = component_indices[n_train:(n_train + n_test)]
test_samples_filename = os.path.join(output_dir, "test_samples.pkl")
test_samples_extra_filename = os.path.join(output_dir,
"test_samples_extra.pkl")
cPickle.dump(test_samples, open(test_samples_filename, "w"))
cPickle.dump(
conj(conj(extra_props, ('n', n_test)),
('component_indices', test_component_indices)),
open(test_samples_extra_filename, "w"))
print "wrote " + test_samples_filename
print "wrote " + test_samples_extra_filename
for i in range(0, d - 1):
output_image_file = os.path.join(
output_dir, "overview_dimensions_%d_and_%d.png" % (i, i + 1))
plot_the_overview(samples, i, i + 1, output_image_file)
print "wrote " + output_image_file
def main(argv):
"""
n_train
n_test
d is the dimension of the samples. Should be higher than 2 and preferable 10 or more..
output_dir is the directory in which we'll write the results
"""
import getopt
import cPickle
try:
opts, args = getopt.getopt(sys.argv[1:], "hv", ["n_train=", "n_test=", "d=", "output_dir="])
except getopt.GetoptError as err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
n_train = None
n_test = None
d = None
output_dir = None
verbose = False
for o, a in opts:
if o == "-v":
verbose = True
elif o in ("-h", "--help"):
usage()
sys.exit()
elif o in ("--n_train"):
n_train = int(a)
elif o in ("--n_test"):
n_test = int(a)
elif o in ("--d"):
d = int(a)
elif o in ("--output_dir"):
output_dir = a
else:
assert False, "unhandled option"
assert n_train
assert n_test
assert d
assert output_dir
# These points are used to define the arcs from which the samples are drawn.
base_number_of_points = 8
(base_x, top_arc, bottom_arc,
twin_bumps_obs_noise_stddev,
twin_bumps_kernel_stddev) = generate_pinched_twin_bumps_quasi_mirrored_gp(base_number_of_points)
# These values are hardcoded to yield something that looks good.
# We're not really interested in varying those with parameters.
kernel_stddev = 0.15
obs_noise_stddev = 0.2
def kernel(x1,x2):
return gaussian_process.square_distance_kernel_1D(x1,x2,kernel_stddev)
samples_x = np.linspace(0.0, 1.0, d)
N = n_train + n_test
samples = np.zeros((N, d))
# Track from which arc you get the sample.
cluster_index = np.array(np.random.uniform(0,1,size=N) < 0.5, dtype=int)
# Not the most efficient way to do this because it
# recomputes certain matrices instead of caching them,
# but that's not important.
for n in range(N):
R = gaussian_process.sample_trajectory_1D(
base_x,
top_arc * cluster_index[n] + bottom_arc * (1 - cluster_index[n]),
kernel,
samples_x,
obs_noise_stddev)
samples[n,:] = R['samples']
# always the same f_star_mean and f_star_cov
f_star_mean = R['f_star_mean']
f_star_cov = R['f_star_cov']
if not os.path.exists(output_dir):
os.makedirs(output_dir)
print "Creating directory %s" % output_dir,
extra_props = {'base_x':base_x,
'top_arc':top_arc,
'bottom_arc':bottom_arc,
'samples_x':samples_x,
'f_star_mean':f_star_mean,
'f_star_cov':f_star_cov,
'n':None,
'd':d,
'kernel_stddev':kernel_stddev,
'obs_noise_stddev':obs_noise_stddev,
'base_number_of_points':base_number_of_points,
'twin_bumps_obs_noise_stddev':twin_bumps_obs_noise_stddev,
'twin_bumps_kernel_stddev':twin_bumps_kernel_stddev}
#print type(extra_props)
#print type(conj(extra_props, ('n', n_train)))
#print type(dict(extra_props.items() + [('lupi',"chien")]))
#quit()
train_samples = samples[0:n_train,:]
train_cluster_index = cluster_index[0:n_train]
train_samples_filename = os.path.join(output_dir, "train_samples.pkl")
train_samples_extra_filename = os.path.join(output_dir, "train_samples_extra.pkl")
cPickle.dump(train_samples, open(train_samples_filename, "w"))
cPickle.dump(conj(conj(extra_props,
('n', n_train)),
('cluster_indices', train_cluster_index)),
open(train_samples_extra_filename, "w"))
print "wrote " + train_samples_filename
print "wrote " + train_samples_extra_filename
test_samples = samples[n_train:(n_train + n_test),:]
test_cluster_index = cluster_index[n_train:(n_train + n_test)]
test_samples_filename = os.path.join(output_dir, "test_samples.pkl")
test_samples_extra_filename = os.path.join(output_dir, "test_samples_extra.pkl")
cPickle.dump(test_samples, open(test_samples_filename, "w"))
cPickle.dump(conj(conj(extra_props,
('n', n_test)),
('cluster_indices', test_cluster_index)),
open(test_samples_extra_filename, "w"))
print "wrote " + test_samples_filename
print "wrote " + test_samples_extra_filename
output_image_file = os.path.join(output_dir,"overview.png")
plot_the_overview(base_x, top_arc, bottom_arc, samples_x, train_samples[0:10,:], train_samples[10:20,:], output_image_file)
print "wrote " + output_image_file