def learn_params_mle(self, samples):
"""
Maximum liklihood estimation (MLE) parameter learing for a BNET.
Parameters
----------
samples: List
A list of fully observed samples for the spanning the total domain
of this BNET. Where samples[i][n] is the i'th sample for node n.
"""
"""Convert the samples list to an array"""
samples = np.array(samples)
"""If the CPD's have not yet been initialized"""
if len(self.cpds) == 0:
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Create a blank CPD for the node"""
family = graph.family(self.model_graph, i)
self.cpds.append(cpds.tabular_CPD(i, self.node_sizes, \
self.model_graph))
"""Get the samples within this nodes CPDs domain"""
local_samples = samples[:, family]
"""Learn the node parameters"""
if len(local_samples.tolist()) != 0:
self.cpds[i].learn_params_mle(local_samples)
else:
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Get the samples within this nodes CPDs domain"""
family = graph.family(self.model_graph, i)
local_samples = samples[:, family]
"""Learn the node parameters"""
if len(local_samples.tolist()) != 0:
self.cpds[i].learn_params_mle(local_samples)
def learn_params_mle(self, samples):
"""
Maximum liklihood estimation (MLE) parameter learing for a BNET.
Parameters
----------
samples: List
A list of fully observed samples for the spanning the total domain
of this BNET. Where samples[i][n] is the i'th sample for node n.
"""
"""Convert the samples list to an array"""
samples = np.array(samples)
if len(self.node_cpds) == 0:
self.init_cpds()
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Get the samples within this nodes CPDs domain"""
family = graph.family(self.adj_mat, i)
local_samples = samples[:, family]
"""Learn the node parameters"""
if len(local_samples.tolist()) != 0:
self.node_cpds[i].learn_params_mle(local_samples)
else:
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Get the samples within this nodes CPDs domain"""
family = graph.family(self.adj_mat, i)
local_samples = samples[:, family]
"""Learn the node parameters"""
if len(local_samples.tolist()) != 0:
self.node_cpds[i].learn_params_mle(local_samples)
def learn_params_mle(self, samples):
"""
Maximum liklihood estimation (MLE) parameter learing for a BNET.
Parameters
----------
samples: List
A list of fully observed samples for the spanning the total domain
of this BNET. Where samples[i][n] is the i'th sample for node n.
"""
"""Convert the samples list to an array"""
samples = np.array(samples)
if len(self.node_cpds) == 0:
self.init_cpds()
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Get the samples within this nodes CPDs domain"""
family = graph.family(self.adj_mat, i)
local_samples = samples[:, family]
"""Learn the node parameters"""
if len(local_samples.tolist()) != 0:
self.node_cpds[i].learn_params_mle(local_samples)
else:
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Get the samples within this nodes CPDs domain"""
family = graph.family(self.adj_mat, i)
local_samples = samples[:, family]
"""Learn the node parameters"""
if len(local_samples.tolist()) != 0:
self.node_cpds[i].learn_params_mle(local_samples)
def init_cpds(self):
self.node_cpds = np.empty(self.node_cpds_N, dtype=object)
for i in range(0, self.num_nodes):
"""Create a blank CPD for the node"""
family = graph.family(self.adj_mat, i)
if i in self.continuous_nodes:
self.node_cpds[i] = node_cpds.GaussianCPD()
else:
fam = np.hstack([i, graph.parents(self.adj_mat, i)])
fam_sizes = self.node_sizes[fam]
self.node_cpds[i] = cpds.TabularCPD(np.ones(fam_sizes))
def init_cpds(self):
self.node_cpds = np.empty(self.node_cpds_N, dtype=object)
for i in range(0, self.num_nodes):
"""Create a blank CPD for the node"""
family = graph.family(self.adj_mat, i)
if i in self.continuous_nodes:
self.node_cpds[i] = node_cpds.GaussianCPD()
else:
fam = np.hstack([i,graph.parents(self.adj_mat, i)])
fam_sizes = self.node_sizes[fam]
self.node_cpds[i] = cpds.TabularCPD(np.ones(fam_sizes))
def learn_params_EM(self, samples, max_iter=10, thresh=np.exp(-4), \
exact=True, inf_max_iter=10):
"""
EM algorithm parameter learing for a BNET, accepts partially
observed samples.
Parameters
----------
samples: List
A list of partially observed samples for the spanning the total
domain of this BNET. Where samples[i][n] is the i'th sample for
node n. samples[i][n] can be [] if node n was not observed in the
i'th sample.
"""
"""If the CPDs have not yet been defined, then create them"""
if len(self.cpds) == 0:
"""For every node in the BNET"""
for i in range(0, self.num_nodes):
"""Create a blank CPD for the node"""
family = graph.family(self.model_graph, i)
self.cpds.append(cpds.tabular_CPD(i, self.node_sizes, \
self.model_graph))
else:
"""If they have been defined, reset the CPT's"""
for i in range(0, self.num_nodes):
self.cpds[i].CPT = np.ones(self.cpds[i].CPT.shape)
"""Create data used in the EM algorithm"""
loglik = 0
prev_loglik = -1*np.Inf
converged = False
num_iter = 0
"""Init the training inference engine for the new BNET"""
self.init_inference_engine(exact, inf_max_iter)
while ((not converged) and (num_iter < max_iter)):
"""Perform an EM iteration and gain the new log likelihood"""
loglik = self.EM_step(samples)
"""Check for convergence"""
delta_loglik = np.abs(loglik - prev_loglik)
avg_loglik = np.nan_to_num((np.abs(loglik) + \
np.abs(prev_loglik))/2)
if (delta_loglik / avg_loglik) < thresh:
"""Algorithm has converged"""
break
prev_loglik = loglik
"""Increase the iteration counter"""
num_iter = num_iter + 1
def test_family(self):
"""
FUNCTION: family, in graph.py.
"""
"""Use the function to determine the family of each node"""
family = []
for i in range(0, self.n):
family.append(graph.family(self.dag, i))
"""
Assert that the function returns the expected family for each node.
"""
assert family[0] == [0]
assert family[1] == [0, 1]
assert family[2] == [0, 2]
assert family[3] == [1, 2, 3]
def test_family(self):
"""
FUNCTION: family, in graph.py.
"""
"""Use the function to determine the family of each node"""
family = []
for i in range(0, self.n):
family.append(graph.family(self.dag, i))
"""
Assert that the function returns the expected family for each node.
"""
print family
assert_array_equal(family[0], np.array([0]))
assert_array_equal(family[1], np.array([0, 1]))
assert_array_equal(family[2], np.array([0, 2]))
assert_array_equal(family[3], np.array([1, 2, 3]))
def test_family(self):
"""
FUNCTION: family, in graph.py.
"""
"""Use the function to determine the family of each node"""
family = []
for i in range(0, self.n):
family.append(graph.family(self.dag, i))
"""
Assert that the function returns the expected family for each node.
"""
print family
assert_array_equal(family[0], np.array([0]))
assert_array_equal(family[1], np.array([0,1]))
assert_array_equal(family[2], np.array([0,2]))
assert_array_equal(family[3], np.array([1,2,3]))
