def sample(self, data, partition, alpha):
for item, data_point in enumerate(data):
old_cell_index = partition.labels[item]
partition.remove_item(item, old_cell_index)
partition.remove_empty_cells()
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)
params = self.base_measure.params
cluster_log_p = self.posterior_density.log_p(data_point, params)
log_p.append(log(alpha) + cluster_log_p)
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
new_cell_index = discrete_rvs(p)
if new_cell_index == partition.number_of_cells:
partition.add_cell(self.base_measure.random())
partition.add_item(item, new_cell_index)
def sample(self, data, partition, alpha):
for item, data_point in enumerate(data):
old_cell_index = partition.labels[item]
partition.remove_item(item, old_cell_index)
partition.remove_empty_cells()
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)
params = self.base_measure.params
cluster_log_p = self.posterior_density.log_p(data_point, params)
log_p.append(log(alpha) + cluster_log_p)
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
new_cell_index = discrete_rvs(p)
if new_cell_index == partition.number_of_cells:
partition.add_cell(self.base_measure.random())
partition.add_item(item, new_cell_index)
def _split(self, i, j, old_cell, data, partition):
old_cell.remove_item(i)
old_cell.remove_item(j)
param_i = old_cell.value
param_j = self.proposal_func.random(param_i)
forward_log_q = self.proposal_func.log_p(param_i, param_i) + self.proposal_func.log_p(param_j, param_i)
reverse_log_q = self.proposal_func.log_p(param_i, param_i)
new_cell_i = partition.add_cell(param_i)
new_cell_j = partition.add_cell(param_j)
new_cell_i.add_item(i)
new_cell_j.add_item(j)
s = old_cell.items
shuffle(s)
for k in s:
old_cell.remove_item(k)
n_i = new_cell_i.size
n_j = new_cell_j.size
log_p = [
log(n_i) + self.cluster_density.log_p(data[k], param_i),
log(n_j) + self.cluster_density.log_p(data[k], param_j)
]
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
c_k = discrete_rvs(p)
if c_k == 0:
new_cell_i.add_item(k)
else:
new_cell_j.add_item(k)
forward_log_q += log_p[c_k]
partition.remove_empty_cells()
return new_cell_i, new_cell_j, forward_log_q, reverse_log_q
def _split(self, i, j, old_cell, data, partition):
old_cell.remove_item(i)
old_cell.remove_item(j)
param_i = old_cell.value
param_j = self.proposal_func.random(param_i)
forward_log_q = self.proposal_func.log_p(param_i, param_i) + self.proposal_func.log_p(param_j, param_i)
reverse_log_q = self.proposal_func.log_p(param_i, param_i)
new_cell_i = partition.add_cell(param_i)
new_cell_j = partition.add_cell(param_j)
new_cell_i.add_item(i)
new_cell_j.add_item(j)
s = old_cell.items
shuffle(s)
for k in s:
old_cell.remove_item(k)
n_i = new_cell_i.size
n_j = new_cell_j.size
log_p = [
log(n_i) + self.cluster_density.log_p(data[k], param_i),
log(n_j) + self.cluster_density.log_p(data[k], param_j)
]
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
c_k = discrete_rvs(p)
if c_k == 0:
new_cell_i.add_item(k)
else:
new_cell_j.add_item(k)
forward_log_q += log_p[c_k]
partition.remove_empty_cells()
return new_cell_i, new_cell_j, forward_log_q, reverse_log_q
def sample(self, data, partition, alpha, m=2):
'''
Sample a new partition according to algorithm 8 of Neal "Sampling Methods For Dirichlet Process Mixture Models"
'''
items = range(len(data))
shuffle(items)
for item in items:
data_point = data[item]
old_cell_index = partition.get_cell_index(item)
partition.remove_item(item, old_cell_index)
if partition.counts[old_cell_index] == 0:
num_new_tables = m - 1
else:
num_new_tables = m
for _ in range(num_new_tables):
partition.add_cell(self.base_measure.random())
log_p = []
for cell in partition.cells:
cluster_log_p = self.cluster_density.log_p(data_point, cell.value)
counts = cell.size
if counts == 0:
counts = alpha / m
log_p.append(log(counts) + cluster_log_p)
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
new_cell_index = discrete_rvs(p)
partition.add_item(item, new_cell_index)
partition.remove_empty_cells()
def sample(self, data, partition, alpha, m=2):
'''
Sample a new partition according to algorithm 8 of Neal "Sampling Methods For Dirichlet Process Mixture Models"
'''
items = range(len(data))
shuffle(items)
for item in items:
data_point = data[item]
old_cell_index = partition.labels[item]
partition.remove_item(item, old_cell_index)
if partition.counts[old_cell_index] == 0:
num_new_tables = m - 1
else:
num_new_tables = m
for _ in range(num_new_tables):
partition.add_cell(self.base_measure.random())
log_p = []
for cell in partition.cells:
cluster_log_p = self.cluster_density.log_p(data_point, cell.value)
counts = cell.size
if counts == 0:
counts = alpha / m
log_p.append(log(counts) + cluster_log_p)
log_p = log_space_normalise(log_p)
p = [exp(x) for x in log_p]
new_cell_index = discrete_rvs(p)
partition.add_item(item, new_cell_index)
partition.remove_empty_cells()
def sample_from_crp(alpha, size, base_measure):
labels = []
values = []
tables = []
# Seat the first customer
tables.append([
0,
])
labels.append(0)
values.append(base_measure.random())
for customer in range(1, size):
p = _get_table_probabilities(tables, alpha)
table_id = discrete_rvs(p)
if table_id == len(tables):
tables.append([
customer,
])
values.append(base_measure.random())
else:
tables[table_id].append(customer)
labels.append(table_id)
partition = Partition()
for v in values:
partition.add_cell(v)
for item, cell_index in enumerate(labels):
partition.add_item(item, cell_index)
return partition
def sample(self, old_value, num_clusters, num_data_points):
a = self.a
b = self.b
k = num_clusters
n = num_data_points
eta = beta_rvs(old_value + 1, n)
x = (a + k - 1) / (n * (b - log(eta)))
pi = x / (1 + x)
label = discrete_rvs([pi, 1 - pi])
scale = b - log(eta)
if label == 0:
new_value = gamma_rvs(a + k, scale)
else:
new_value = gamma_rvs(a + k - 1, scale)
return new_value
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()
