class StickbreakingCorrelatedLDA(_LDABase):
"Correlated LDA with the stick breaking representation"
def __init__(self, data, T, alpha_beta):
mu, sigma = compute_uniform_mean_psi(T)
self.theta_prior = Gaussian(
mu=mu, sigma=sigma, mu_0=mu, sigma_0=T * sigma / 10.0, nu_0=T / 10.0, kappa_0=1.0 / 10
)
self.ppgs = initialize_polya_gamma_samplers()
self.omega = np.zeros((data.shape[0], T - 1))
super(StickbreakingCorrelatedLDA, self).__init__(data, T, alpha_beta)
@property
def theta(self):
return psi_to_pi(self.psi)
@theta.setter
def theta(self, theta):
self.psi = pi_to_psi(theta)
def initialize_theta(self):
self.psi = np.tile(self.theta_prior.mu, (self.D, 1))
def resample_theta(self):
self.resample_omega()
self.resample_psi()
def resample(self):
super(StickbreakingCorrelatedLDA, self).resample()
self.resample_theta_prior()
def resample_omega(self):
pgdrawvpar(
self.ppgs, N_vec(self.doc_topic_counts).astype("float64").ravel(), self.psi.ravel(), self.omega.ravel()
)
np.clip(self.omega, 1e-32, np.inf, out=self.omega)
def resample_psi(self):
Lmbda = np.linalg.inv(self.theta_prior.sigma)
h = Lmbda.dot(self.theta_prior.mu)
randvec = np.random.randn(self.D, self.T - 1) # pre-generate randomness
for d, c in enumerate(self.doc_topic_counts):
self.psi[d] = sample_infogaussian(Lmbda + np.diag(self.omega[d]), h + kappa_vec(c), randvec[d])
def resample_theta_prior(self):
self.theta_prior.resample(self.psi)
def copy_sample(self):
new = copy.copy(self)
new.beta = self.beta.copy()
new.psi = self.psi.copy()
new.theta_prior = self.theta_prior.copy_sample()
del new.z
del new.omega
return new
class LogisticNormalCorrelatedLDA(_LDABase):
"Correlated LDA with the stick breaking representation"
def __init__(self, data, T, alpha_beta):
mu, sigma = np.zeros(T), np.eye(T)
self.theta_prior = \
Gaussian(
mu=mu, sigma=sigma, mu_0=mu, sigma_0=T*sigma/10.,
nu_0=T/10., kappa_0=10.)
self.ppgs = initialize_polya_gamma_samplers()
self.omega = np.zeros((data.shape[0], T))
super(LogisticNormalCorrelatedLDA, self).__init__(data, T, alpha_beta)
@property
def theta(self):
return ln_psi_to_pi(self.psi)
@theta.setter
def theta(self, theta):
self.psi = ln_pi_to_psi(theta)
def initialize_theta(self):
self.psi = np.tile(self.theta_prior.mu, (self.D, 1))
def resample_theta(self):
self.resample_psi_and_omega()
def resample(self):
super(LogisticNormalCorrelatedLDA, self).resample()
self.resample_theta_prior()
def resample_psi_and_omega(self):
Lmbda = np.linalg.inv(self.theta_prior.sigma)
for d in xrange(self.D):
N = self.data[d].sum()
c = self.doc_topic_counts[d]
for t in xrange(self.T):
self.omega[d, t] = self.ppgs[0].pgdraw(
N, self._conditional_omega(d, t))
mu_cond, sigma_cond = self._conditional_psi(d, t, Lmbda, N, c)
self.psi[d, t] = np.random.normal(mu_cond, np.sqrt(sigma_cond))
def _conditional_psi(self, d, t, Lmbda, N, c):
nott = np.arange(self.T) != t
psi = self.psi[d]
omega = self.omega[d]
mu = self.theta_prior.mu
zetat = logsumexp(psi[nott])
mut_marg = mu[t] - 1. / Lmbda[t, t] * Lmbda[t, nott].dot(psi[nott] -
mu[nott])
sigmat_marg = 1. / Lmbda[t, t]
sigmat_cond = 1. / (omega[t] + 1. / sigmat_marg)
# kappa is the mean dot precision, i.e. the sufficient statistic of a Gaussian
# therefore we can sum over datapoints
kappa = (c[t] - N / 2.0).sum()
mut_cond = sigmat_cond * (kappa + mut_marg / sigmat_marg +
omega[t] * zetat)
return mut_cond, sigmat_cond
def _conditional_omega(self, d, t):
nott = np.arange(self.T) != t
psi = self.psi[d]
zetat = logsumexp(psi[nott])
return psi[t] - zetat
def resample_theta_prior(self):
self.theta_prior.resample(self.psi)
def copy_sample(self):
new = copy.copy(self)
new.beta = self.beta.copy()
new.psi = self.psi.copy()
new.theta_prior = self.theta_prior.copy_sample()
del new.z
del new.omega
return new
class StickbreakingCorrelatedLDA(_LDABase):
"Correlated LDA with the stick breaking representation"
def __init__(self, data, T, alpha_beta):
mu, sigma = compute_uniform_mean_psi(T)
self.theta_prior = Gaussian(mu=mu,
sigma=sigma,
mu_0=mu,
sigma_0=T * sigma / 10.,
nu_0=T / 10.,
kappa_0=1. / 10)
self.ppgs = initialize_polya_gamma_samplers()
self.omega = np.zeros((data.shape[0], T - 1))
super(StickbreakingCorrelatedLDA, self).__init__(data, T, alpha_beta)
@property
def theta(self):
return psi_to_pi(self.psi)
@theta.setter
def theta(self, theta):
self.psi = pi_to_psi(theta)
def initialize_theta(self):
self.psi = np.tile(self.theta_prior.mu, (self.D, 1))
def resample_theta(self):
self.resample_omega()
self.resample_psi()
def resample(self):
super(StickbreakingCorrelatedLDA, self).resample()
self.resample_theta_prior()
def resample_omega(self):
pgdrawvpar(self.ppgs,
N_vec(self.doc_topic_counts).astype('float64').ravel(),
self.psi.ravel(), self.omega.ravel())
np.clip(self.omega, 1e-32, np.inf, out=self.omega)
def resample_psi(self):
Lmbda = np.linalg.inv(self.theta_prior.sigma)
h = Lmbda.dot(self.theta_prior.mu)
randvec = np.random.randn(self.D,
self.T - 1) # pre-generate randomness
for d, c in enumerate(self.doc_topic_counts):
self.psi[d] = sample_infogaussian(Lmbda + np.diag(self.omega[d]),
h + kappa_vec(c), randvec[d])
def resample_theta_prior(self):
self.theta_prior.resample(self.psi)
def copy_sample(self):
new = copy.copy(self)
new.beta = self.beta.copy()
new.psi = self.psi.copy()
new.theta_prior = self.theta_prior.copy_sample()
del new.z
del new.omega
return new
class LogisticNormalCorrelatedLDA(_LDABase):
"Correlated LDA with the stick breaking representation"
def __init__(self, data, T, alpha_beta):
mu, sigma = np.zeros(T), np.eye(T)
self.theta_prior = \
Gaussian(
mu=mu, sigma=sigma, mu_0=mu, sigma_0=T*sigma/10.,
nu_0=T/10., kappa_0=10.)
self.ppgs = initialize_polya_gamma_samplers()
self.omega = np.zeros((data.shape[0], T))
super(LogisticNormalCorrelatedLDA, self).__init__(data, T, alpha_beta)
@property
def theta(self):
return ln_psi_to_pi(self.psi)
@theta.setter
def theta(self, theta):
self.psi = ln_pi_to_psi(theta)
def initialize_theta(self):
self.psi = np.tile(self.theta_prior.mu, (self.D, 1))
def resample_theta(self):
self.resample_psi_and_omega()
def resample(self):
super(LogisticNormalCorrelatedLDA, self).resample()
self.resample_theta_prior()
def resample_psi_and_omega(self):
Lmbda = np.linalg.inv(self.theta_prior.sigma)
for d in xrange(self.D):
N = self.data[d].sum()
c = self.doc_topic_counts[d]
for t in xrange(self.T):
self.omega[d,t] = self.ppgs[0].pgdraw(
N, self._conditional_omega(d,t))
mu_cond, sigma_cond = self._conditional_psi(d, t, Lmbda, N, c)
self.psi[d,t] = np.random.normal(mu_cond, np.sqrt(sigma_cond))
def _conditional_psi(self, d, t, Lmbda, N, c):
nott = np.arange(self.T) != t
psi = self.psi[d]
omega = self.omega[d]
mu = self.theta_prior.mu
zetat = logsumexp(psi[nott])
mut_marg = mu[t] - 1./Lmbda[t,t] * Lmbda[t,nott].dot(psi[nott] - mu[nott])
sigmat_marg = 1./Lmbda[t,t]
sigmat_cond = 1./(omega[t] + 1./sigmat_marg)
# kappa is the mean dot precision, i.e. the sufficient statistic of a Gaussian
# therefore we can sum over datapoints
kappa = (c[t] - N/2.0).sum()
mut_cond = sigmat_cond * (kappa + mut_marg / sigmat_marg + omega[t]*zetat)
return mut_cond, sigmat_cond
def _conditional_omega(self, d, t):
nott = np.arange(self.T) != t
psi = self.psi[d]
zetat = logsumexp(psi[nott])
return psi[t] - zetat
def resample_theta_prior(self):
self.theta_prior.resample(self.psi)
def copy_sample(self):
new = copy.copy(self)
new.beta = self.beta.copy()
new.psi = self.psi.copy()
new.theta_prior = self.theta_prior.copy_sample()
del new.z
del new.omega
return new
