def _init_partition(self, base_measure):
self.partition = Partition()
for item, _ in enumerate(self.data):
self.partition.add_cell(base_measure.random())
self.partition.add_item(item, item)
def initialise_partition(self, data, init_method):
'''
Args:
data : (list) Data points.
Kwargs:
method : (str) Initialisation method to use.
- 'separate' will allocate each data point to a separate partition.
- 'together' will allocate all data points to the same partition.
'''
self.partition = Partition()
if init_method == 'separate':
for item, _ in enumerate(data):
self.partition.add_cell(
self.partition_sampler.base_measure.random())
self.partition.add_item(item, item)
elif init_method == 'together':
self.partition.add_cell(
self.partition_sampler.base_measure.random())
for item, _ in enumerate(data):
self.partition.add_item(item, 0)
def draw_from_prior(base_measure, size):
alpha = gamma_rvs(1, 1)
# partition = sample_from_crp(alpha, size, base_measure)
partition = Partition()
partition.add_cell(base_measure.random())
for item in range(size):
partition.add_item(item, 0)
return alpha, partition
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 initialise_partition(self, data):
self.partition = Partition()
for item, _ in enumerate(data):
self.partition.add_cell(self.base_measure.random())
self.partition.add_item(item, item)
for i in range(1000):
x = poisson_rvs(100)
data.append(PoissonData(x))
for i in range(50):
x = poisson_rvs(25)
data.append(PoissonData(x))
alpha = 1
base_measure = GammaBaseMeasure(1, 1)
cluster_density = PoissonDensity()
partition = Partition()
for item, data_point in enumerate(data):
partition.add_cell(base_measure.random())
partition.add_item(item, item)
concentration_sampler = GammaPriorConcentrationSampler(1, 1)
posterior_density = NegativeBinomialDensity()
partition_sampler = MarginalGibbsPartitionSampler(base_measure,
cluster_density,
posterior_density)
#partition_sampler = AuxillaryParameterPartitionSampler(base_measure, cluster_density)
atom_sampler = GammaPoissonGibbsAtomSampler(base_measure, cluster_density)
