def resample(self,data=[],niter=None):
niter = niter if niter else self.niter
if getdatasize(data) == 0:
self.A = sample_gaussian(J=self.J_0,h=self.h_0.ravel())\
.reshape(self.h_0.shape)
self.sigma = sample_invwishart(self.S_0,self.nu_0)
else:
yyT, yxT, xxT, n = self._get_statistics(data)
for itr in range(niter):
self._resample_A(xxT, yxT, self.sigma)
self._resample_sigma(xxT, yxT, yyT, n, self.A)
def resample(self, data=[], niter=None):
niter = niter if niter else self.niter
if getdatasize(data) == 0:
self.A = sample_gaussian(J=self.J_0,h=self.h_0.ravel())\
.reshape(self.h_0.shape)
self.sigma = sample_invwishart(self.S_0, self.nu_0)
else:
yyT, yxT, xxT, n = self._get_statistics(data)
for itr in range(niter):
self._resample_A(xxT, yxT, self.sigma)
self._resample_sigma(xxT, yxT, yyT, n, self.A)
def _resample_sigma(self, xxT, yxT, yyT, n, A):
S = self.S_0 + yyT - yxT.dot(A.T) - A.dot(yxT.T) + A.dot(xxT).dot(A.T)
nu = self.nu_0 + n
self.sigma = sample_invwishart(S, nu)
def main(name, datadir, datafn, K, expdir=None, nfolds=1, nrestarts=1, seed=None):
""" Run experiment on 4 state, two group synthetic data.
name : Name of experiment.
datadir : Path to directory containing data.
datafn : Prefix name to files that data and missing masks are stored
in.
K : Number of components in HMM.
expdir : Path to directory to store experiment results. If None
(default), then a directory, `name`_results, is made in the
current directory.
nfolds : Number of folds to generate if datafn is None.
nrestarts : Number of random initial parameters.
seed : Random number seed.
"""
# Set seed for reproducibility
np.random.seed(seed)
# Generate/Load data and folds (missing masks)
# These are the emission distributions for the following tests
if not os.path.exists(datadir):
raise RuntimeError("Could not find datadir: %s" % (datadir,))
else:
if not os.path.isdir(datadir):
raise RuntimeError("datadir: %s exists but is not a directory" % (datadir,))
if datafn is None:
datafn = name
dpath = os.path.join(datadir, datafn + "_data.txt")
mpath = os.path.join(datadir, datafn + "_fold*.txt")
try:
X = np.loadtxt(dpath)
except IOError:
if os.path.exists(dpath) and not os.path.isdir(dpath):
raise RuntimeError("Could not load data: %s" % (dpath,))
masks = glob.glob(mpath)
if len(masks) == 0:
masks = [None]
# Initialize parameter possibilities
obs_mean = np.mean(X, axis=0)
mu_0 = obs_mean
sigma_0 = 0.75*np.cov(X.T)
# Vague values that keeps covariance matrices p.d.
kappa_0 = 0.01
nu_0 = 4
prior_init = np.ones(K)
prior_tran = np.ones((K,K))
N, D = X.shape
rand_starts = list()
for r in xrange(nrestarts):
init_means = np.empty((K,D))
init_cov = list()
for k in xrange(K):
init_means[k,:] = mvnrand(mu_0, cov=sigma_0)
init_cov.append(sample_invwishart(np.linalg.inv(sigma_0), nu_0))
# We use prior b/c mu and sigma are sampled here
prior_emit = np.array([Gaussian(mu=init_means[k,:], sigma=sigma_0,
mu_0=mu_0, sigma_0=sigma_0,
kappa_0=kappa_0, nu_0=nu_0)
for k in xrange(K)])
init_init = np.random.rand(K)
init_init /= np.sum(init_init)
init_tran = np.random.rand(K,K)
init_tran /= np.sum(init_tran, axis=1)[:,np.newaxis]
# Make dict with initial parameters to pass to experiment.
pd = {'init_init': init_init, 'init_tran': init_tran,
'prior_init': prior_init, 'prior_tran': prior_tran,
'prior_emit': prior_emit, 'maxit': maxit, 'verbose': verbose}
rand_starts.append(pd)
# Compute Cartesian product of random starts with other possible parameter
# values, make a generator to fill in entries in the par dicts created
# above, and then construct the par_list by calling the generator with the
# Cartesian product iterator.
par_prod_iter = itertools.product(rand_starts, taus, kappas, reuse_msg,
grow_buffer, Ls, correct_trans)
def gen_par(par_tuple):
d = copy.copy(par_tuple[0])
d['tau'] = par_tuple[1]
d['kappa'] = par_tuple[2]
d['reuseMsg'] = par_tuple[3]
d['growBuffer'] = par_tuple[4]
d['metaobs_half'] = par_tuple[5]
d['correctTrans'] = par_tuple[6]
d['mb_sz'] = 100//(2*par_tuple[5]+1)
return d
# Call gen_par on each par product to pack into dictionary to pass to
# experiment.
par_list = itertools.imap(gen_par, par_prod_iter)
# Create ExperimentSequential and call run_exper
dname = os.path.join(datadir, datafn + "_data.txt")
exp = ExpSeq(datafn, dname, run_exper, par_list,
masks=masks, exper_dir=expdir)
exp.run()
def _resample_sigma(self, xxT, yxT, yyT, n, A):
S = self.S_0 + yyT - yxT.dot(A.T) - A.dot(yxT.T) + A.dot(xxT).dot(A.T)
nu = self.nu_0 + n
self.sigma = sample_invwishart(S, nu)
def test_wishart_correlated_pgm_rvs(K=10):
# Randomly generate a covariance matrix
from pybasicbayes.util.stats import sample_invwishart
Sigma = sample_invwishart(np.eye(K-1), nu=K)
test_correlated_pgm_rvs(Sigma)
def test_wishart_correlated_pgm_rvs(K=10):
# Randomly generate a covariance matrix
from pybasicbayes.util.stats import sample_invwishart
Sigma = sample_invwishart(np.eye(K - 1), nu=K)
test_correlated_pgm_rvs(Sigma)
def main(name, datadir, datafn, K, expdir=None, nfolds=1, nrestarts=1, seed=None):
""" Run experiment on 4 state, two group synthetic data.
name : Name of experiment.
datadir : Path to directory containing data.
datafn : Prefix name to files that data and missing masks are stored
in.
K : Number of components in HMM.
expdir : Path to directory to store experiment results. If None
(default), then a directory, `name`_results, is made in the
current directory.
nfolds : Number of folds to generate if datafn is None.
nrestarts : Number of random initial parameters.
seed : Random number seed.
"""
# Set seed for reproducibility
np.random.seed(seed)
# Generate/Load data and folds (missing masks)
# These are the emission distributions for the following tests
if not os.path.exists(datadir):
raise RuntimeError("Could not find datadir: %s" % (datadir,))
else:
if not os.path.isdir(datadir):
raise RuntimeError("datadir: %s exists but is not a directory" % (datadir,))
if datafn is None:
datafn = name
dpath = os.path.join(datadir, datafn + "_data.txt")
mpath = os.path.join(datadir, datafn + "_fold*.txt")
try:
X = np.loadtxt(dpath)
except IOError:
if os.path.exists(dpath) and not os.path.isdir(dpath):
raise RuntimeError("Could not load data: %s" % (dpath,))
masks = glob.glob(mpath)
if len(masks) == 0:
masks = [None]
# Initialize parameter possibilities
obs_mean = np.mean(X, axis=0)
mu_0 = obs_mean
sigma_0 = 0.75*np.cov(X.T)
# Vague values that keeps covariance matrices p.d.
kappa_0 = 0.01
nu_0 = 4
prior_init = np.ones(K)
prior_tran = np.ones((K,K))
rand_starts = list()
for r in xrange(nrestarts):
init_means = np.empty((K,D))
init_cov = list()
for k in xrange(K):
init_means[k,:] = mvnrand(mu_0, cov=sigma_0)
init_cov.append(sample_invwishart(np.linalg.inv(sigma_0), nu_0))
# We use prior b/c mu and sigma are sampled here
prior_emit = np.array([Gaussian(mu=init_means[k,:], sigma=sigma_0,
mu_0=mu_0, sigma_0=sigma_0,
kappa_0=kappa_0, nu_0=nu_0)
for k in xrange(K)])
init_init = np.random.rand(K)
init_init /= np.sum(init_init)
init_tran = np.random.rand(K,K)
init_tran /= np.sum(init_tran, axis=1)[:,np.newaxis]
# Make dict with initial parameters to pass to experiment.
pd = {'init_init': init_init, 'init_tran': init_tran,
'prior_init': prior_init, 'prior_tran': prior_tran,
'prior_emit': prior_emit, 'maxit': maxit}
rand_starts.append(pd)
# Compute Cartesian product of random starts with other possible parameter
# values, make a generator to fill in entries in the par dicts created
# above, and then construct the par_list by calling the generator with the
# Cartesian product iterator.
par_prod_iter = itertools.product(rand_starts, taus, kappas, Ls)
def gen_par(par_tuple):
d = copy.copy(par_tuple[0])
d['tau'] = par_tuple[1]
d['kappa'] = par_tuple[2]
d['metaobs_half'] = par_tuple[3]
return d
# Call gen_par on each par product to pack into dictionary to pass to
# experiment.
par_list = itertools.imap(gen_par, par_prod_iter)
# Create ExperimentSequential and call run_exper
dname = os.path.join(datadir, datafn + "_data.txt")
exp = ExpSeq('exper_synth_4statedd', dname, run_exper, par_list,
masks=masks, exper_dir=expdir)
exp.run()
