def __init__(
self,
A, ## profile matrix
pkappa, ## [mean, var] for kappa
ptau, ## [mean, var] for tau
SCexpr, ## L-by-N, single cell expression
G, ## L-by-1, single cell types
itype ## cell ids in each type
):
## data: never changed
(self.SCexpr, self.G, self.L) = (SCexpr, G, SCexpr.shape[0])
(self.N, self.K) = A.shape
self.SCrd = SCexpr.sum(axis=1) ## read depths
self.itype = itype
## parameters: can only be changed by self.update_parameters()
self.A = np.array(A, dtype=float, copy=True)
self.pkappa = np.array(pkappa, dtype=float, copy=True)
self.ptau = np.array(ptau, dtype=float, copy=True)
## zero-expressed entries
self.izero = np.where(self.SCexpr == 0)
## for sampling from Polya-Gamma
# self.ppgs = ppg.PyPolyaGamma(seed=0)
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = self.initialize_polya_gamma_samplers()
def sample_w(self):
"""
This method samples the augmenting w parameters from its conditional posterior distribution.
For details about the augmentation see the paper.
:return: samples for w_i from a polyagamma distribution.
list of lists of arrays num_images x num_subjects x T(image, subject).
"""
nthreads = pypolyagamma.get_omp_num_threads()
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
w = []
for i in range(len(self.saliencies_ts)):
w.append([])
for saliency_ts in self.saliencies_ts[i]:
T = saliency_ts.shape[0]
A = np.ones(T)
w_is = np.zeros(T)
pypolyagamma.pgdrawvpar(
ppgs, A,
np.abs(self.b.value * (saliency_ts - self.s_0.value)),
w_is)
w[-1].append(w_is)
return w
def __init__(self, V, K, X=None, b=None, sigmasq_b=1.0,
sigmasq_prior_prms=None, name=None):
self.V, self.K = V, K
# Initialize prior
sigmasq_prior_prms = sigmasq_prior_prms if sigmasq_prior_prms is not None else {}
self.sigmasq_x_prior = self._sigmasq_x_prior_class(K, **sigmasq_prior_prms)
self.sigmasq_b = sigmasq_b
# Initialize parameters
self.X = np.sqrt(self.sigmasq_x) * npr.randn(V, K) if X is None else X * np.ones((V, K))
self.b = np.zeros((V, V)) if b is None else b * np.ones((V, V))
# Models encapsulate data
# A: observed adjacency matrix
# m: mask for network n specifying which features to use
# mask: mask specifying which entries in A were observed/hidden
self.As = []
self.ms = []
self.masks = []
# Polya-gamma RNGs
num_threads = get_omp_num_threads()
seeds = npr.randint(2 ** 16, size=num_threads)
self.ppgs = [PyPolyaGamma(seed) for seed in seeds]
# Name the model
self.name = name if name is not None else "lsm_K{}".format(K)
def __init__(self,
model,
covariates=None,
data=None,
mask=None,
stateseq=None,
gaussian_states=None,
**kwargs):
super(PGRecurrentSLDSStates, self).\
__init__(model, covariates=covariates, data=data, mask=mask,
stateseq=stateseq, gaussian_states=gaussian_states,
**kwargs)
# Initialize the Polya gamma samplers if they haven't already been set
if not hasattr(self, 'ppgs'):
import pypolyagamma as ppg
# Initialize the Polya-gamma samplers
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
# Initialize auxiliary variables for transitions
self.trans_omegas = np.ones((self.T - 1, self.num_states - 1))
# If discrete and continuous states are given, resample the auxiliary variables once
if stateseq is not None and gaussian_states is not None:
self.resample_transition_auxiliary_variables()
def __init__(self, N, B, **kwargs):
super(_SparsePGRegressionBase, self).__init__(N, B, **kwargs)
# Initialize Polya-gamma samplers
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = npr.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
def __init__(self, N, B, **kwargs):
super(_SparsePGRegressionBase, self).__init__(N, B, **kwargs)
# Initialize Polya-gamma samplers
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = npr.randint(2 ** 16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
def initialize_polya_gamma_samplers():
if "OMP_NUM_THREADS" in os.environ:
num_threads = int(os.environ["OMP_NUM_THREADS"])
else:
num_threads = ppg.get_omp_num_threads()
assert num_threads > 0
# Choose random seeds
seeds = np.random.randint(2**16, size=num_threads)
return [ppg.PyPolyaGamma(seed) for seed in seeds]
def initialize_polya_gamma_samplers(self):
if "OMP_NUM_THREADS" in os.environ:
self.num_threads = int(os.environ["OMP_NUM_THREADS"])
else:
self.num_threads = ppg.get_omp_num_threads()
assert self.num_threads > 0
# Choose random seeds
seeds = np.random.randint(2**16, size=self.num_threads)
return [ppg.PyPolyaGamma(seed) for seed in seeds]
def __init__(self, N, D, **kwargs):
super(_GibbsLogisticEigenmodel, self).__init__(N, D, **kwargs)
nthreads = ppg.get_omp_num_threads()
seeds = np.random.randint(0, 2**16, size=nthreads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
# DEBUG:
self.F = np.sqrt(self.sigma_F) * np.random.randn(self.N, self.D)
self.mu_0 = self.mu_mu_0 + np.sqrt(self.sigma_mu0) * np.random.randn()
self.resample()
def sample_w_i(S, J_i):
"""
:param S: observation matrix
:param J_i: neuron i's couplings
:return: samples for w_i from a polyagamma distribution
"""
nthreads = pypolyagamma.get_omp_num_threads()
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
T = S.shape[0]
A = np.ones(T)
w_i = np.zeros(T)
pypolyagamma.pgdrawvpar(ppgs, A, np.dot(S, J_i), w_i)
return w_i
def test_parallel(verbose=False):
# Call the parallel vectorized version
np.random.seed(0)
n = 5
nthreads = pypolyagamma.get_omp_num_threads()
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
if verbose:
print(v3)
return True
def test_parallel(verbose=False):
# Call the parallel vectorized version
np.random.seed(0)
n = 5
nthreads = pypolyagamma.get_omp_num_threads()
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
if verbose:
print(v3)
return True
def __init__(self, S, C):
self.S, self.C = S, C
self.T, self.N = S.shape
self.c = np.random.randint(0,C, size=self.N)
self.psis = np.zeros((self.T, self.C))
from pybasicbayes.distributions.gaussian import ScalarGaussianNIX
self.gaussian = ScalarGaussianNIX(mu_0=0, kappa_0=1, sigmasq_0=1.0, nu_0=2.0)
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
self.omega = np.zeros((self.T, self.N))
def __init__(self, S, C):
self.S, self.C = S, C
self.T, self.N = S.shape
self.c = np.random.randint(0, C, size=self.N)
self.psis = np.zeros((self.T, self.C))
from pybasicbayes.distributions.gaussian import ScalarGaussianNIX
self.gaussian = ScalarGaussianNIX(mu_0=0,
kappa_0=1,
sigmasq_0=1.0,
nu_0=2.0)
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
self.omega = np.zeros((self.T, self.N))
def __init__(self, X=None, psi=None):
"""
:param X: TxN matrix of observations
"""
assert X is not None or psi is not None
if psi is not None and X is None:
X = self.rvs(psi)
assert X.ndim == 2
self.X = X
self.T, self.N = X.shape
# Initialize Polya-gamma samplers
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
# Initialize auxiliary variables, omega
self.omega = np.ones((self.T, self.N))
def __init__(self, model, data=None, mask=None, **kwargs):
super(LDSStatesCountData, self). \
__init__(model, data=data, mask=mask, **kwargs)
# Check if the emission matrix is a count regression
from pypolyagamma.distributions import _PGLogisticRegressionBase
if isinstance(self.emission_distn, _PGLogisticRegressionBase):
self.has_count_data = True
# Initialize the Polya-gamma samplers
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
# Initialize auxiliary variables, omega
self.omega = np.ones((self.T, self.D_emission), dtype=np.float)
else:
self.has_count_data = False
def __init__(self, S, D):
self.S = S
self.T, self.N = S.shape
self.D = D
self.Z = np.zeros((self.N,self.D))
self.omega = np.zeros((self.T, self.N))
# Initialize regression model
# from pybasicbayes.distributions.regression import Regression
# S_0 = np.eye(self.T)
# K_0 = np.eye(self.D+1)
# M_0 = np.zeros((self.T, self.D+1))
# nu_0 = self.T+2
# self.regression = Regression(nu_0, S_0, M_0, K_0, affine=True)
self.A = np.zeros((self.T, self.D))
self.bias = np.zeros((self.T,))
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
def __init__(self, S, D):
self.S = S
self.T, self.N = S.shape
self.D = D
self.Z = np.zeros((self.N, self.D))
self.omega = np.zeros((self.T, self.N))
# Initialize regression model
# from pybasicbayes.distributions.regression import Regression
# S_0 = np.eye(self.T)
# K_0 = np.eye(self.D+1)
# M_0 = np.zeros((self.T, self.D+1))
# nu_0 = self.T+2
# self.regression = Regression(nu_0, S_0, M_0, K_0, affine=True)
self.A = np.zeros((self.T, self.D))
self.bias = np.zeros((self.T, ))
import pypolyagamma as ppg
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
import matplotlib.pyplot as plt
from scipy.stats import norm, probplot
# Use a simple Normal-Bernoulli model
# z ~ N(z | 0, 1)
# x ~ [Bern(x | \sigma(z))]^{1/T} = Bern(x | \sigma(z / T))
# Where T is the temperature of the tempered distribution in [1, \inf)
# When T=1 we target the posterior. When T=\inf we target the prior
T = 2.0
mu_z = 0.0
sigma_z = 1.0
# Initialize Polya-gamma samplers
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
def kappa(x):
# Compute kappa = [a(x) - b(x)/2.] / T
# for the Bernoulli model where a(x) = x and b(x) = 1
return (x - 0.5) / T
def resample_z(x, omega):
# Resample z from its Gaussian conditional
prior_J = 1. / sigma_z
prior_h = prior_J * mu_z
for n in xrange(N):
plt.subplot(N,1,n+1)
lns.append(plt.plot(psi[:T_plot,n], 'r')[0])
plt.plot(psi[:T_plot,n], 'b')
spks = np.where(S[:T_plot,n])[0]
plt.plot(spks, np.ones_like(spks), 'ko', markerfacecolor="k")
plt.ylim((min(0.9, psi.min()-0.1), max(1.1, psi.max()+0.1)))
plt.show()
# Do some inference
# Instantiate the auxiliary variables
omega = np.zeros_like(psi)
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
# Collect samples
b_samples = []
W_samples = []
A_samples = []
psi_samples = []
for itr in xrange(N_samples):
print "Iteration ", itr
resample_omega()
resample_A()
resample_W_b()
def test_parallel2():
"""Test multiple cases of OMP"""
num_threads = pypolyagamma.get_omp_num_threads()
if num_threads < 2:
return
np.random.seed(0)
# Case 1: n < nthreads, nthreads = num_threads
nthreads = num_threads
n = nthreads - 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 2: n < nthreads, nthreads < num_threads
nthreads = num_threads - 1
n = nthreads - 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 3: n < nthreads, nthreads > num_threads
nthreads = num_threads + 1
n = nthreads - 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 4: n > nthreads, nthreads = num_threads
nthreads = num_threads
n = nthreads + 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 5: n > nthreads, nthreads < num_threads
nthreads = num_threads - 1
n = nthreads + 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 6: n > nthreads, nthreads > num_threads
nthreads = num_threads + 1
n = nthreads + 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 7: n = nthreads, nthreads = num_threads
nthreads = num_threads
n = nthreads
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 8: n = nthreads, nthreads < num_threads
nthreads = num_threads - 1
n = nthreads
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 9: n = nthreads, nthreads > num_threads
nthreads = num_threads + 1
n = nthreads
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
return True
def __init__(self, population, trunc=200):
self.population = population
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed, trunc) for seed in seeds]
self.N = self.population.N
def __init__(self, population, trunc=200):
self.population = population
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed, trunc) for seed in seeds]
self.N = self.population.N
def test_parallel2():
"""Test multiple cases of OMP"""
num_threads = pypolyagamma.get_omp_num_threads()
if num_threads < 2:
return
np.random.seed(0)
# Case 1: n < nthreads, nthreads = num_threads
nthreads = num_threads
n = nthreads - 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 2: n < nthreads, nthreads < num_threads
nthreads = num_threads - 1
n = nthreads - 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 3: n < nthreads, nthreads > num_threads
nthreads = num_threads + 1
n = nthreads - 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 4: n > nthreads, nthreads = num_threads
nthreads = num_threads
n = nthreads + 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 5: n > nthreads, nthreads < num_threads
nthreads = num_threads - 1
n = nthreads + 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 6: n > nthreads, nthreads > num_threads
nthreads = num_threads + 1
n = nthreads + 1
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 7: n = nthreads, nthreads = num_threads
nthreads = num_threads
n = nthreads
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 8: n = nthreads, nthreads < num_threads
nthreads = num_threads - 1
n = nthreads
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
# Case 9: n = nthreads, nthreads > num_threads
nthreads = num_threads + 1
n = nthreads
v3 = np.zeros(n)
a = 14 * np.ones(n)
b = 0 * np.ones(n)
seeds = np.random.randint(2**16, size=nthreads)
ppgs = [pypolyagamma.PyPolyaGamma(seed) for seed in seeds]
pypolyagamma.pgdrawvpar(ppgs, a, b, v3)
return True
def __init__(self, model, data=None, **kwargs):
# The data must be provided in sparse row format
# This makes it easy to iterate over rows. Basically,
# for each row, t, it is easy to get the output dimensions, n,
# such that y_{t,n} > 0.
super(LDSStatesZeroInflatedCountData, self).\
__init__(model, data=data, **kwargs)
# Initialize the Polya-gamma samplers
num_threads = ppg.get_omp_num_threads()
seeds = np.random.randint(2**16, size=num_threads)
self.ppgs = [ppg.PyPolyaGamma(seed) for seed in seeds]
# Initialize the masked data
if data is not None:
assert isinstance(
data, csr_matrix
), "Data must be a sparse row matrix for zero-inflated models"
# Initialize a sparse matrix of masked data. The mask
# specifies which observations were "exposed" and which
# were determinisitcally zero. In other words, the mask
# gives the data values at the places where z_{t,n} = 1.
T, N, C, D, b = self.T, self.D_emission, self.C, self.D, self.emission_distn.b
indptr = [0]
indices = []
vals = []
offset = 0
for t in range(T):
# Get the nonzero entries in the t-th row
ns_t = data.indices[data.indptr[t]:data.indptr[t + 1]]
y_t = np.zeros(N)
y_t[ns_t] = data.data[data.indptr[t]:data.indptr[t + 1]]
# Sample zero inflation mask
z_t = np.random.rand(N) < self.rho
z_t[ns_t] = True
# Construct the sparse matrix
t_inds = np.where(z_t)[0]
indices.append(t_inds)
vals.append(y_t[t_inds])
offset += t_inds.size
indptr.append(offset)
# Construct a sparse matrix
vals = np.concatenate(vals)
indices = np.concatenate(indices)
indptr = np.array(indptr)
self.masked_data = csr_matrix((vals, indices, indptr),
shape=(T, N))
# DEBUG: Start with all the data
# dense_data = data.toarray()
# values = dense_data.ravel()
# indices = np.tile(np.arange(self.D_emission), (self.T,))
# indptrs = np.arange(self.T+1) * self.D_emission
# self.masked_data = csr_matrix((values, indices, indptrs), (self.T, self.D_emission))
# assert np.allclose(self.masked_data.toarray(), dense_data)
self.resample_auxiliary_variables()
else:
self.masked_data = None
self.omega = None
