def _query(self, variables, operation, evidence=None):
"""
This is a generalized query method that can be used for both query and map query.
Parameters
----------
variables: list
list of variables for which you want to compute the probability
operation: str ('marginalize' | 'maximize')
The operation to do for passing messages between nodes.
evidence: dict
a dict key, value pair as {var: state_of_var_observed}
None if no evidence
Examples
--------
>>> from pgmpy.inference import BeliefPropagation
>>> from pgmpy.models import BayesianModel
>>> import numpy as np
>>> import pandas as pd
>>> values = pd.DataFrame(np.random.randint(low=0, high=2, size=(1000, 5)),
... columns=['A', 'B', 'C', 'D', 'E'])
>>> model = BayesianModel([('A', 'B'), ('C', 'B'), ('C', 'D'), ('B', 'E')])
>>> model.fit(values)
>>> inference = BeliefPropagation(model)
>>> phi_query = inference.query(['A', 'B'])
References
----------
Algorithm 10.4 Out-of-clique inference in clique tree
Probabilistic Graphical Models: Principles and Techniques Daphne Koller and Nir Friedman.
"""
is_calibrated = self._is_converged(operation=operation)
# Calibrate the junction tree if not calibrated
if not is_calibrated:
self.calibrate()
if not isinstance(variables, (list, tuple, set)):
query_variables = [variables]
else:
query_variables = list(variables)
query_variables.extend(evidence.keys() if evidence else [])
# Find a tree T' such that query_variables are a subset of scope(T')
nodes_with_query_variables = set()
for var in query_variables:
nodes_with_query_variables.update(filter(lambda x: var in x, self.junction_tree.nodes()))
subtree_nodes = nodes_with_query_variables
# Conversion of set to tuple just for indexing
nodes_with_query_variables = tuple(nodes_with_query_variables)
# As junction tree is a tree, that means that there would be only path between any two nodes in the tree
# thus we can just take the path between any two nodes; no matter there order is
for i in range(len(nodes_with_query_variables) - 1):
subtree_nodes.update(nx.shortest_path(self.junction_tree, nodes_with_query_variables[i],
nodes_with_query_variables[i + 1]))
subtree_undirected_graph = self.junction_tree.subgraph(subtree_nodes)
# Converting subtree into a junction tree
if len(subtree_nodes) == 1:
subtree = JunctionTree()
subtree.add_node(subtree_nodes.pop())
else:
subtree = JunctionTree(subtree_undirected_graph.edges())
# Selecting a node is root node. Root node would be having only one neighbor
if len(subtree.nodes()) == 1:
root_node = subtree.nodes()[0]
else:
root_node = tuple(filter(lambda x: len(subtree.neighbors(x)) == 1, subtree.nodes()))[0]
clique_potential_list = [self.clique_beliefs[root_node]]
# For other nodes in the subtree compute the clique potentials as follows
# As all the nodes are nothing but tuples so simple set(root_node) won't work at it would update the set with'
# all the elements of the tuple; instead use set([root_node]) as it would include only the tuple not the
# internal elements within it.
parent_nodes = set([root_node])
nodes_traversed = set()
while parent_nodes:
parent_node = parent_nodes.pop()
for child_node in set(subtree.neighbors(parent_node)) - nodes_traversed:
clique_potential_list.append(self.clique_beliefs[child_node] /
self.sepset_beliefs[frozenset([parent_node, child_node])])
parent_nodes.update([child_node])
nodes_traversed.update([parent_node])
# Add factors to the corresponding junction tree
subtree.add_factors(*clique_potential_list)
# Sum product variable elimination on the subtree
variable_elimination = VariableElimination(subtree)
if operation == 'marginalize':
return variable_elimination.query(variables=variables, evidence=evidence)
elif operation == 'maximize':
return variable_elimination.map_query(variables=variables, evidence=evidence)
def _query(self, variables, operation, evidence=None):
"""
This is a generalized query method that can be used for both query and map query.
Parameters
----------
variables: list
list of variables for which you want to compute the probability
operation: str ('marginalize' | 'maximize')
The operation to do for passing messages between nodes.
evidence: dict
a dict key, value pair as {var: state_of_var_observed}
None if no evidence
Examples
--------
>>> from pgmpy.inference import BeliefPropagation
>>> from pgmpy.models import BayesianModel
>>> import numpy as np
>>> import pandas as pd
>>> values = pd.DataFrame(np.random.randint(low=0, high=2, size=(1000, 5)),
... columns=['A', 'B', 'C', 'D', 'E'])
>>> model = BayesianModel([('A', 'B'), ('C', 'B'), ('C', 'D'), ('B', 'E')])
>>> model.fit(values)
>>> inference = BeliefPropagation(model)
>>> phi_query = inference.query(['A', 'B'])
References
----------
Algorithm 10.4 Out-of-clique inference in clique tree
Probabilistic Graphical Models: Principles and Techniques Daphne Koller and Nir Friedman.
"""
is_calibrated = self._is_converged(operation=operation)
# Calibrate the junction tree if not calibrated
if not is_calibrated:
self.calibrate()
if not isinstance(variables, (list, tuple, set)):
query_variables = [variables]
else:
query_variables = list(variables)
query_variables.extend(evidence.keys() if evidence else [])
# Find a tree T' such that query_variables are a subset of scope(T')
nodes_with_query_variables = set()
for var in query_variables:
nodes_with_query_variables.update(
filter(lambda x: var in x, self.junction_tree.nodes()))
subtree_nodes = nodes_with_query_variables
# Conversion of set to tuple just for indexing
nodes_with_query_variables = tuple(nodes_with_query_variables)
# As junction tree is a tree, that means that there would be only path between any two nodes in the tree
# thus we can just take the path between any two nodes; no matter there order is
for i in range(len(nodes_with_query_variables) - 1):
subtree_nodes.update(
nx.shortest_path(self.junction_tree,
nodes_with_query_variables[i],
nodes_with_query_variables[i + 1]))
subtree_undirected_graph = self.junction_tree.subgraph(subtree_nodes)
# Converting subtree into a junction tree
if len(subtree_nodes) == 1:
subtree = JunctionTree()
subtree.add_node(subtree_nodes.pop())
else:
subtree = JunctionTree(subtree_undirected_graph.edges())
# Selecting a node is root node. Root node would be having only one neighbor
if len(subtree.nodes()) == 1:
root_node = subtree.nodes()[0]
else:
root_node = tuple(
filter(lambda x: len(list(subtree.neighbors(x))) == 1,
subtree.nodes()))[0]
clique_potential_list = [self.clique_beliefs[root_node]]
# For other nodes in the subtree compute the clique potentials as follows
# As all the nodes are nothing but tuples so simple set(root_node) won't work at it would update the set with'
# all the elements of the tuple; instead use set([root_node]) as it would include only the tuple not the
# internal elements within it.
parent_nodes = set([root_node])
nodes_traversed = set()
while parent_nodes:
parent_node = parent_nodes.pop()
for child_node in set(
subtree.neighbors(parent_node)) - nodes_traversed:
clique_potential_list.append(
self.clique_beliefs[child_node] /
self.sepset_beliefs[frozenset([parent_node, child_node])])
parent_nodes.update([child_node])
nodes_traversed.update([parent_node])
# Add factors to the corresponding junction tree
subtree.add_factors(*clique_potential_list)
# Sum product variable elimination on the subtree
variable_elimination = VariableElimination(subtree)
if operation == 'marginalize':
return variable_elimination.query(variables=variables,
evidence=evidence)
elif operation == 'maximize':
return variable_elimination.map_query(variables=variables,
evidence=evidence)
