def stepwise_e_step(self, data, varNames):
'''collect sufficient statistics for each variable
data: 2d numpy array
varNames: list of string
'''
ctp = NaturalCliqueTreePropagation(self._model)
tree = ctp.cliqueTree()
cliques = tree.cliques
# set up evidence
datacase = ContinuousDatacase.create(varNames)
datacase.synchronize(self._model)
for i in range(len(data)):
datacase.putValues(data[i])
evidence = datacase.getEvidence()
ctp.use(evidence)
ctp.propagate()
for j in range(len(cliques)):
self.batchSufficientStatistics[j].add(cliques[j].potential)
# construct variable to statisticMap
variableStatisticMap = dict()
for node in self._model.nodes:
clique = tree.getClique(node.variable)
index = cliques.index(clique)
variableStatisticMap[node.variable] = (
self.sufficientStatistics[index],
self.batchSufficientStatistics[index])
return variableStatisticMap
def initializeSufficientStatistics(self, batch_size):
ctp = NaturalCliqueTreePropagation(self._model)
ctp.initializePotentials()
tree = ctp.cliqueTree()
cliques = tree.cliques
sufficientStatistics = [None] * len(cliques)
batchSufficientStatistics = [None] * len(cliques)
for i in range(len(cliques)):
if isinstance(cliques[i], DiscreteClique):
sufficientStatistics[i] = DiscreteCliqueSufficientStatistics(
cliques[i], batch_size)
batchSufficientStatistics[
i] = DiscreteCliqueSufficientStatistics(
cliques[i], batch_size)
elif isinstance(cliques[i], MixedClique):
sufficientStatistics[i] = MixedCliqueSufficientStatistics(
cliques[i], batch_size)
batchSufficientStatistics[i] = MixedCliqueSufficientStatistics(
cliques[i], batch_size)
else:
raise Exception("unknown type of clique")
return sufficientStatistics, batchSufficientStatistics
def grad(self, x):
datacase = ContinuousDatacase.create(self.varNames)
datacase.synchronize(self._model)
ctp = NaturalCliqueTreePropagation(self._model)
num, dim = x.shape
out = np.zeros((num, dim), dtype=np.float32)
datacase.putValues(x)
evidence = datacase.getEvidence()
ctp.use(evidence)
ctp.propagate()
tree = ctp.cliqueTree()
gradient = np.zeros((num, dim))
for node in self._model.getLeafNodes():
clique = tree.getClique(node.variable)
cliquePotential = clique.potential.clone()
cliquePotential.normalize()
moGpotential = node.potential.clone()
vars = moGpotential.continuousVariables
value = evidence.getValues(vars)
b = np.zeros(len(vars))
subgradient = np.zeros((num, len(vars)))
for j in range(moGpotential.size):
sol = np.linalg.solve(moGpotential.get(j).covar, (np.expand_dims(moGpotential.get(j).mu, axis=0) - value).T).T
# subgradient += sol * np.expand_dims(cliquePotential.p[:, j], axis=1)
subgradient += sol * np.expand_dims(np.exp(cliquePotential.logp[:, j]), axis=1)
for j in range(len(vars)):
index = datacase.variables.index(vars[j])
gradient[:, index] = subgradient[:, j]
return gradient