def sample(self, data, partition, alpha):
u = uniform_rvs(0, 1)
if u < self.ratio:
self.auxillary_sampler.sample(data, partition, alpha)
else:
self.split_merge_sampler.sample(data, partition, alpha)
def sample(self, data, partition, alpha):
u = uniform_rvs(0, 1)
if u < self.ratio:
self.auxillary_sampler.sample(data, partition, alpha)
else:
self.split_merge_sampler.sample(data, partition, alpha)
def sample(self, data, partition):
old_param = self.cluster_density.params
new_param = self.proposal_func.random(old_param)
old_ll = self.base_measure.log_p(old_param)
new_ll = self.base_measure.log_p(new_param)
for cell in partition.cells:
atom_params = cell.value
for j in cell.items:
old_ll += self.cluster_density.log_p(data[j], atom_params)
self.cluster_density.params = new_param
for cell in partition.cells:
atom_params = cell.value
for j in cell.items:
new_ll += self.cluster_density.log_p(data[j], atom_params)
forward_log_ratio = new_ll - self.proposal_func.log_p(
new_param, old_param)
reverse_log_ratio = old_ll - self.proposal_func.log_p(
old_param, new_param)
log_ratio = forward_log_ratio - reverse_log_ratio
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
self.cluster_density.params = new_param
else:
self.cluster_density.params = old_param
def sample(self, data, old_partition, alpha):
items = range(len(data))
i, j = sample(items, 2)
labels = old_partition.labels
c_i = labels[i]
c_j = labels[j]
new_partition = old_partition.copy()
if c_i == c_j:
c = c_i
old_cell = new_partition.cells[c]
new_cell_i, new_cell_j, forward_log_q, reverse_log_q = self._split(i, j, old_cell, data, new_partition)
forward_log_p = self._compute_partition_log_p(new_cell_i, data) + \
self._compute_partition_log_p(new_cell_j, data)
old_cell = old_partition.cells[c]
reverse_log_p = self._compute_partition_log_p(old_cell, data)
else:
cell_i = new_partition.cells[c_i]
cell_j = new_partition.cells[c_j]
new_cell, forward_log_q, reverse_log_q = self._merge(cell_i, cell_j, data, new_partition)
forward_log_p = self._compute_partition_log_p(new_cell, data)
old_cell_i = old_partition.cells[c_i]
old_cell_j = old_partition.cells[c_j]
reverse_log_p = self._compute_partition_log_p(old_cell_i, data) + \
self._compute_partition_log_p(old_cell_j, data)
forward_log_prior = self._compute_prior_log_p(alpha, new_partition)
reverse_log_prior = self._compute_prior_log_p(alpha, old_partition)
forward_log_ratio = forward_log_p + forward_log_prior - forward_log_q
reverse_log_ratio = reverse_log_p + reverse_log_prior - reverse_log_q
log_ratio = forward_log_ratio - reverse_log_ratio
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
print "accepted"
old_partition.cells = new_partition.cells
else:
# print "rejected"
# print forward_log_p - reverse_log_p, forward_log_q - reverse_log_q
pass
def sample(self, data, old_partition, alpha):
items = range(len(data))
i, j = sample(items, 2)
labels = old_partition.labels
c_i = labels[i]
c_j = labels[j]
new_partition = old_partition.copy()
if c_i == c_j:
c = c_i
old_cell = new_partition.cells[c]
new_cell_i, new_cell_j, forward_log_q, reverse_log_q = self._split(i, j, old_cell, data, new_partition)
forward_log_p = self._compute_partition_log_p(new_cell_i, data) + \
self._compute_partition_log_p(new_cell_j, data)
old_cell = old_partition.cells[c]
reverse_log_p = self._compute_partition_log_p(old_cell, data)
else:
cell_i = new_partition.cells[c_i]
cell_j = new_partition.cells[c_j]
new_cell, forward_log_q, reverse_log_q = self._merge(cell_i, cell_j, data, new_partition)
forward_log_p = self._compute_partition_log_p(new_cell, data)
old_cell_i = old_partition.cells[c_i]
old_cell_j = old_partition.cells[c_j]
reverse_log_p = self._compute_partition_log_p(old_cell_i, data) + \
self._compute_partition_log_p(old_cell_j, data)
forward_log_prior = self._compute_prior_log_p(alpha, new_partition)
reverse_log_prior = self._compute_prior_log_p(alpha, old_partition)
forward_log_ratio = forward_log_p + forward_log_prior - forward_log_q
reverse_log_ratio = reverse_log_p + reverse_log_prior - reverse_log_q
log_ratio = forward_log_ratio - reverse_log_ratio
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
print "accepted"
old_partition.cells = new_partition.cells
else:
# print "rejected"
# print forward_log_p - reverse_log_p, forward_log_q - reverse_log_q
pass
def sample_atom(self, data, cell):
old_param = cell.value
new_param = self.proposal_func.random(old_param)
old_ll = self.base_measure.log_p(old_param)
new_ll = self.base_measure.log_p(new_param)
for j in cell.items:
old_ll += self.cluster_density.log_p(data[j], old_param)
new_ll += self.cluster_density.log_p(data[j], new_param)
forward_log_ratio = new_ll - self.proposal_func.log_p(new_param, old_param)
reverse_log_ratio = old_ll - self.proposal_func.log_p(old_param, new_param)
log_ratio = forward_log_ratio - reverse_log_ratio
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
return new_param
else:
return old_param
def sample(self, data, partition, alpha):
n = partition.number_of_items
for item, data_point in enumerate(data):
old_cluster_label = partition.labels[item]
old_value = partition.item_values[item]
partition.remove_item(item, old_cluster_label)
if partition.counts[old_cluster_label] == 0:
p = [x / (n - 1) for x in partition.counts]
new_cluster_label = discrete_rvs(p)
new_value = partition.cell_values[new_cluster_label]
old_ll = self.cluster_density.log_p(data_point, old_value)
new_ll = self.cluster_density.log_p(data_point, new_value)
log_ratio = log(n - 1) - log(alpha) + new_ll - old_ll
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
partition.add_item(item, new_cluster_label)
else:
partition.add_item(item, old_cluster_label)
else:
new_value = self.base_measure.random()
old_ll = self.cluster_density.log_p(data_point, old_value)
new_ll = self.cluster_density.log_p(data_point, new_value)
log_ratio = log(alpha) - log(n - 1) + new_ll - old_ll
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
partition.add_cell(new_value)
cell = partition.get_cell_by_value(new_value)
cell.add_item(item)
else:
partition.add_item(item, old_cluster_label)
partition.remove_empty_cells()
for item, data_point in enumerate(data):
old_cluster_label = partition.labels[item]
if partition.cells[old_cluster_label].size == 1:
continue
partition.remove_item(item, old_cluster_label)
log_p = []
for cell in partition.cells:
cluster_log_p = self.cluster_density.log_p(data_point, cell.value)
counts = cell.size
log_p.append(log(counts) + cluster_log_p)
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
new_cluster_label = discrete_rvs(p)
partition.add_item(item, new_cluster_label)
partition.remove_empty_cells()
def sample(self, data, partition, alpha):
n = partition.number_of_items
for item, data_point in enumerate(data):
old_cluster_label = partition.labels[item]
old_value = partition.item_values[item]
partition.remove_item(item, old_cluster_label)
if partition.counts[old_cluster_label] == 0:
p = [x / (n - 1) for x in partition.counts]
new_cluster_label = discrete_rvs(p)
new_value = partition.cell_values[new_cluster_label]
old_ll = self.cluster_density.log_p(data_point, old_value)
new_ll = self.cluster_density.log_p(data_point, new_value)
log_ratio = log(n - 1) - log(alpha) + new_ll - old_ll
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
partition.add_item(item, new_cluster_label)
else:
partition.add_item(item, old_cluster_label)
else:
new_value = self.base_measure.random()
old_ll = self.cluster_density.log_p(data_point, old_value)
new_ll = self.cluster_density.log_p(data_point, new_value)
log_ratio = log(alpha) - log(n - 1) + new_ll - old_ll
u = uniform_rvs(0, 1)
if log_ratio >= log(u):
partition.add_cell(new_value)
cell = partition.get_cell_by_value(new_value)
cell.add_item(item)
else:
partition.add_item(item, old_cluster_label)
partition.remove_empty_cells()
for item, data_point in enumerate(data):
old_cluster_label = partition.labels[item]
if partition.cells[old_cluster_label].size == 1:
continue
partition.remove_item(item, old_cluster_label)
log_p = []
for cell in partition.cells:
cluster_log_p = self.cluster_density.log_p(data_point, cell.value)
counts = cell.size
log_p.append(log(counts) + cluster_log_p)
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
new_cluster_label = discrete_rvs(p)
partition.add_item(item, new_cluster_label)
partition.remove_empty_cells()
def random(self):
phi = uniform_rvs(0, 1)
return PyCloneParameter(phi)
