def main():
mkdir_p(EXP_DIR)
parser = argparse.ArgumentParser(description='gprf_opt')
parser.add_argument('--ntrain', dest='ntrain', type=int, help="number of points to locate")
parser.add_argument('--ntest', dest='ntest', type=int, default=500, help="sample additional test points to evaluate predictive accuracy (not in paper)")
parser.add_argument('--nblocks', dest='nblocks', default=1, type=int, help="divides the sampled points into a grid of this many blocks. May do strange things if number is not a perfect square. Mutually exclusive with rpc_blocksize. ")
parser.add_argument('--rpc_blocksize', dest='rpc_blocksize', default=-1, type=int, help="divides the sampled points into blocks using recursive projection clustering, aiming for this target blocksize. Mutually exclusive with nblocks. ")
parser.add_argument('--lscale', dest='lscale', type=float, help="SE kernel lengthscale for the sampled functions")
parser.add_argument('--obs_std', dest='obs_std', type=float, help="std of Gaussian noise corrupting the X locations")
parser.add_argument('--local_dist', dest='local_dist', default=1.0, type=float, help="when using RPC clustering, specifies minimum kernel value necessary to connect blocks in a GPRF (1.0 corresponds to local GPs). When using grids of blocks, any setting other than 1.0 yields a GPRF with neighbor connections. ")
parser.add_argument('--method', dest='method', default="l-bfgs-b", type=str, help="any optimization method supported by scipy.optimize.minimize (l-bfgs-b)")
parser.add_argument('--seed', dest='seed', default=0, type=int, help="seed for generating synthetic data")
parser.add_argument('--yd', dest='yd', default=50, type=int, help="number of output dimensions to sample (50)")
parser.add_argument('--maxsec', dest='maxsec', default=3600, type=int, help="maximum number of seconds to run the optimization (3600)")
parser.add_argument('--task', dest='task', default="x", type=str, help="'x', 'cov', or 'xcov' to infer locations, kernel hyperparams, or both. (x)")
parser.add_argument('--analyze', dest='analyze', default=False, action="store_true", help="just analyze existing saved inference results, don't do any new inference")
parser.add_argument('--analyze_full', dest='analyze_full', default=False, action="store_true", help="do a fuller (slower) analysis that also computes predictive accuracy")
parser.add_argument('--parallel', dest='parallel', default=False, action="store_true", help="run multiple threads for local/gprf blocks. be careful when combining this with multithreaded BLAS libraries.")
parser.add_argument('--init_seed', dest='init_seed', default=-1, type=int, help="if >=0, initialize optimization to locations generated from this random seed.")
parser.add_argument('--init_true', dest='init_true', default=False, action="store_true", help="initialize optimization at true X locations instead of observed locations (False)")
parser.add_argument('--noise_var', dest='noise_var', default=0.01, type=float, help="variance of iid noise in synthetic Y values")
parser.add_argument('--gplvm_type', dest='gplvm_type', default="gprf", type=str, help = "use 'sparse' or 'bayesian' for GPy inducing point comparison (gprf)")
parser.add_argument('--num_inducing', dest='num_inducing', default=0, type=int, help="number of inducing points to use with sparse approximations")
args = parser.parse_args()
d = exp_dir(args)
do_run(d=d, lscale=args.lscale, obs_std=args.obs_std, local_dist=args.local_dist, n=args.ntrain+args.ntest, ntrain=args.ntrain, nblocks=args.nblocks, yd=args.yd, method=args.method, rpc_blocksize=args.rpc_blocksize, seed=args.seed, maxsec=args.maxsec, analyze_only=args.analyze, analyze_full = args.analyze_full, task=args.task, init_seed=args.init_seed, noise_var=args.noise_var, parallel=args.parallel, gplvm_type=args.gplvm_type, num_inducing=args.num_inducing, init_true=args.init_true)
def seismic_exp_dir(args):
npts, block_size, thresh, init_cov, init_x, task, synth_lscale, obs_std = args.npts, args.rpc_blocksize, args.threshold, args.init_cov, args.init_x, args.task, args.synth_lscale, args.obs_std
import hashlib
base_dir = os.path.join(os.environ["HOME"], "seismic_experiments")
init_str = "default"
if init_cov or init_x:
init_str = "_%s" % hashlib.md5(init_cov+init_x).hexdigest()[:8]
run_name = "%d_%d_%.4f_%s_%s_%.0f_%.1f" % (npts, block_size, thresh, init_str, task, synth_lscale, obs_std)
d = os.path.join(base_dir, run_name)
mkdir_p(d)
return d
def seismic_exp_dir(args):
npts, block_size, thresh, init_cov, init_x, task, synth_lscale, obs_std = args.npts, args.rpc_blocksize, args.threshold, args.init_cov, args.init_x, args.task, args.synth_lscale, args.obs_std
import hashlib
base_dir = os.path.join(os.environ["HOME"], "seismic_experiments")
init_str = "default"
if init_cov or init_x:
init_str = "_%s" % hashlib.md5(init_cov + init_x).hexdigest()[:8]
run_name = "%d_%d_%.4f_%s_%s_%.0f_%.1f" % (
npts, block_size, thresh, init_str, task, synth_lscale, obs_std)
d = os.path.join(base_dir, run_name)
mkdir_p(d)
return d
def sample_data(n, ntrain, lscale, obs_std, yd, seed,
centers, noise_var, rpc_blocksize=-1):
sample_basedir = os.path.join(os.environ["HOME"], "gprf_experiments", "synthetic_datasets")
mkdir_p(sample_basedir)
sample_fname = "%d_%d_%.6f_%.6f_%d_%d%s.pkl" % (n, ntrain, lscale, obs_std, yd, seed, "" if noise_var==0.01 else "_%.4f" % noise_var)
sample_fname_full = os.path.join(sample_basedir, sample_fname)
try:
with open(sample_fname_full, 'rb') as f:
sdata = pickle.load(f)
except IOError:
sdata = SampledData(n=n, ntrain=ntrain, lscale=lscale, obs_std=obs_std, seed=seed, yd=yd, noise_var=noise_var)
with open(sample_fname_full, 'wb') as f:
pickle.dump(sdata, f)
if centers is not None:
sdata.set_centers(centers)
else:
np.random.seed(seed)
sdata.cluster_rpc(rpc_blocksize)
return sdata
def sample_data(n,
ntrain,
lscale,
obs_std,
yd,
seed,
centers,
noise_var,
rpc_blocksize=-1):
sample_basedir = os.path.join(os.environ["HOME"], "gprf_experiments",
"synthetic_datasets")
mkdir_p(sample_basedir)
sample_fname = "%d_%d_%.6f_%.6f_%d_%d%s.pkl" % (
n, ntrain, lscale, obs_std, yd, seed,
"" if noise_var == 0.01 else "_%.4f" % noise_var)
sample_fname_full = os.path.join(sample_basedir, sample_fname)
try:
with open(sample_fname_full, 'rb') as f:
sdata = pickle.load(f)
except IOError:
sdata = SampledData(n=n,
ntrain=ntrain,
lscale=lscale,
obs_std=obs_std,
seed=seed,
yd=yd,
noise_var=noise_var)
with open(sample_fname_full, 'wb') as f:
pickle.dump(sdata, f)
if centers is not None:
sdata.set_centers(centers)
else:
np.random.seed(seed)
sdata.cluster_rpc(rpc_blocksize)
return sdata
def exp_dir(args):
run_name = build_run_name(args)
exp_dir = os.path.join(EXP_DIR, run_name)
mkdir_p(exp_dir)
return exp_dir
def main():
mkdir_p(EXP_DIR)
parser = argparse.ArgumentParser(description='gprf_opt')
parser.add_argument('--ntrain',
dest='ntrain',
type=int,
help="number of points to locate")
parser.add_argument(
'--ntest',
dest='ntest',
type=int,
default=500,
help=
"sample additional test points to evaluate predictive accuracy (not in paper)"
)
parser.add_argument(
'--nblocks',
dest='nblocks',
default=1,
type=int,
help=
"divides the sampled points into a grid of this many blocks. May do strange things if number is not a perfect square. Mutually exclusive with rpc_blocksize. "
)
parser.add_argument(
'--rpc_blocksize',
dest='rpc_blocksize',
default=-1,
type=int,
help=
"divides the sampled points into blocks using recursive projection clustering, aiming for this target blocksize. Mutually exclusive with nblocks. "
)
parser.add_argument('--lscale',
dest='lscale',
type=float,
help="SE kernel lengthscale for the sampled functions")
parser.add_argument(
'--obs_std',
dest='obs_std',
type=float,
help="std of Gaussian noise corrupting the X locations")
parser.add_argument(
'--local_dist',
dest='local_dist',
default=1.0,
type=float,
help=
"when using RPC clustering, specifies minimum kernel value necessary to connect blocks in a GPRF (1.0 corresponds to local GPs). When using grids of blocks, any setting other than 1.0 yields a GPRF with neighbor connections. "
)
parser.add_argument(
'--method',
dest='method',
default="l-bfgs-b",
type=str,
help=
"any optimization method supported by scipy.optimize.minimize (l-bfgs-b)"
)
parser.add_argument('--seed',
dest='seed',
default=0,
type=int,
help="seed for generating synthetic data")
parser.add_argument('--yd',
dest='yd',
default=50,
type=int,
help="number of output dimensions to sample (50)")
parser.add_argument(
'--maxsec',
dest='maxsec',
default=3600,
type=int,
help="maximum number of seconds to run the optimization (3600)")
parser.add_argument(
'--task',
dest='task',
default="x",
type=str,
help=
"'x', 'cov', or 'xcov' to infer locations, kernel hyperparams, or both. (x)"
)
parser.add_argument(
'--analyze',
dest='analyze',
default=False,
action="store_true",
help=
"just analyze existing saved inference results, don't do any new inference"
)
parser.add_argument(
'--analyze_full',
dest='analyze_full',
default=False,
action="store_true",
help=
"do a fuller (slower) analysis that also computes predictive accuracy")
parser.add_argument(
'--parallel',
dest='parallel',
default=False,
action="store_true",
help=
"run multiple threads for local/gprf blocks. be careful when combining this with multithreaded BLAS libraries."
)
parser.add_argument(
'--init_seed',
dest='init_seed',
default=-1,
type=int,
help=
"if >=0, initialize optimization to locations generated from this random seed."
)
parser.add_argument(
'--init_true',
dest='init_true',
default=False,
action="store_true",
help=
"initialize optimization at true X locations instead of observed locations (False)"
)
parser.add_argument('--noise_var',
dest='noise_var',
default=0.01,
type=float,
help="variance of iid noise in synthetic Y values")
parser.add_argument(
'--gplvm_type',
dest='gplvm_type',
default="gprf",
type=str,
help=
"use 'sparse' or 'bayesian' for GPy inducing point comparison (gprf)")
parser.add_argument(
'--num_inducing',
dest='num_inducing',
default=0,
type=int,
help="number of inducing points to use with sparse approximations")
args = parser.parse_args()
d = exp_dir(args)
do_run(d=d,
lscale=args.lscale,
obs_std=args.obs_std,
local_dist=args.local_dist,
n=args.ntrain + args.ntest,
ntrain=args.ntrain,
nblocks=args.nblocks,
yd=args.yd,
method=args.method,
rpc_blocksize=args.rpc_blocksize,
seed=args.seed,
maxsec=args.maxsec,
analyze_only=args.analyze,
analyze_full=args.analyze_full,
task=args.task,
init_seed=args.init_seed,
noise_var=args.noise_var,
parallel=args.parallel,
gplvm_type=args.gplvm_type,
num_inducing=args.num_inducing,
init_true=args.init_true)
def exp_dir(args):
run_name = build_run_name(args)
exp_dir = os.path.join(EXP_DIR, run_name)
mkdir_p(exp_dir)
return exp_dir