def setUp(self):
self.sn2 = {'grade': ['A', 'B', 'F'], 'diff': ['high', 'low'],
'intel': ['poor', 'good', 'very good']}
self.sn1 = {'speed': ['low', 'medium', 'high'],
'switch': ['on', 'off'], 'time': ['day', 'night']}
self.phi1 = Factor(['speed', 'switch', 'time'],
[3, 2, 2], np.ones(12))
self.phi2 = Factor(['speed', 'switch', 'time'],
[3, 2, 2], np.ones(12), state_names=self.sn1)
self.cpd1 = TabularCPD('grade', 3, [[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'],
evidence_card=[2, 3])
self.cpd2 = TabularCPD('grade', 3, [[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'],
evidence_card=[2, 3],
state_names=self.sn2)
student = BayesianModel([('diff', 'grade'), ('intel', 'grade')])
diff_cpd = TabularCPD('diff', 2, [[0.2, 0.8]])
intel_cpd = TabularCPD('intel', 2, [[0.3, 0.7]])
grade_cpd = TabularCPD('grade', 3, [[0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'],
evidence_card=[2, 2])
student.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.model1 = Inference(student)
self.model2 = Inference(student, state_names=self.sn2)
def test_markov_inference_init(self):
infer_markov = Inference(self.markov)
self.assertEqual(set(infer_markov.variables), {'a', 'b', 'c', 'd'})
self.assertEqual(infer_markov.cardinality, {
'a': 2,
'b': 2,
'c': 2,
'd': 2
})
self.assertEqual(
infer_markov.factors, {
'a': [
Factor(['a', 'b'], [2, 2], np.array([100, 1, 1, 100])),
Factor(['a', 'c'], [2, 2], np.array([40, 30, 100, 20]))
],
'b': [
Factor(['a', 'b'], [2, 2], np.array([100, 1, 1, 100])),
Factor(['b', 'd'], [2, 2], np.array([1, 100, 100, 1]))
],
'c': [
Factor(['a', 'c'], [2, 2], np.array([40, 30, 100, 20])),
Factor(['c', 'd'], [2, 2], np.array([60, 60, 40, 40]))
],
'd': [
Factor(['b', 'd'], [2, 2], np.array([1, 100, 100, 1])),
Factor(['c', 'd'], [2, 2], np.array([60, 60, 40, 40]))
]
})
def test_bayesian_inference_init(self):
infer_bayesian = Inference(self.bayesian)
self.assertEqual(set(infer_bayesian.variables),
{"a", "b", "c", "d", "e"})
self.assertEqual(infer_bayesian.cardinality, {
"a": 2,
"b": 2,
"c": 2,
"d": 2,
"e": 2
})
self.assertIsInstance(infer_bayesian.factors, defaultdict)
self.assertEqual(
set(infer_bayesian.factors["a"]),
set([
self.bayesian.get_cpds("a").to_factor(),
self.bayesian.get_cpds("b").to_factor(),
]),
)
self.assertEqual(
set(infer_bayesian.factors["b"]),
set([
self.bayesian.get_cpds("b").to_factor(),
self.bayesian.get_cpds("c").to_factor(),
]),
)
self.assertEqual(
set(infer_bayesian.factors["c"]),
set([
self.bayesian.get_cpds("c").to_factor(),
self.bayesian.get_cpds("d").to_factor(),
]),
)
self.assertEqual(
set(infer_bayesian.factors["d"]),
set([
self.bayesian.get_cpds("d").to_factor(),
self.bayesian.get_cpds("e").to_factor(),
]),
)
self.assertEqual(
set(infer_bayesian.factors["e"]),
set([self.bayesian.get_cpds("e").to_factor()]),
)
def _absorption(self, marginal_tree, c_i, c_j):
"""
Send a message from c_j to c_i during propagation.
"""
# Union of all factors in c_j and its separators' factors
neighbors = marginal_tree.neighbors(c_j)
if c_i in neighbors:
neighbors.remove(c_i)
R_s = []
for neighbor in neighbors:
if (neighbor, c_j) in marginal_tree.separators:
R_s.extend(marginal_tree.separators[(neighbor, c_j)])
R_s.extend(marginal_tree.factor_node_assignment[c_j])
separator = frozenset(c_i).intersection(frozenset(c_j))
# Variables to marginalize from R_s
marginalize = list(set(c_j) - set(separator))
R_s = self._find_relevant_potentials(R_s, separator, marginal_tree)
R_s = Inference.sum_out(marginalize, R_s)
# Associate the messages with the separator of c_i and c_j,
# in the right direction (from c_j to c_i)
marginal_tree.separators[(c_j, c_i)] = R_s
def _absorption(self, marginal_tree, c_i, c_j):
"""
Send a message from c_j to c_i during propagation.
"""
# Union of all factors in c_j and its separators' factors
neighbors = marginal_tree.neighbors(c_j)
if c_i in neighbors:
neighbors.remove(c_i)
R_s = []
for neighbor in neighbors:
if (neighbor, c_j) in marginal_tree.separators:
R_s.extend(marginal_tree.separators[(neighbor, c_j)])
R_s.extend(marginal_tree.factor_node_assignment[c_j])
separator = frozenset(c_i).intersection(frozenset(c_j))
# Variables to marginalize from R_s
marginalize = list(set(c_j) - set(separator))
R_s = self._find_relevant_potentials(R_s, separator, marginal_tree)
R_s = Inference.sum_out(marginalize, R_s)
# Associate the messages with the separator of c_i and c_j,
# in the right direction (from c_j to c_i)
marginal_tree.separators[(c_j, c_i)] = R_s
def test_bayesian_inference_init(self):
infer_bayesian = Inference(self.bayesian)
self.assertEqual(set(infer_bayesian.variables),
{'a', 'b', 'c', 'd', 'e'})
self.assertEqual(infer_bayesian.cardinality, {
'a': 2,
'b': 2,
'c': 2,
'd': 2,
'e': 2
})
self.assertIsInstance(infer_bayesian.factors, defaultdict)
self.assertEqual(
set(infer_bayesian.factors['a']),
set([
self.bayesian.get_cpds('a').to_factor(),
self.bayesian.get_cpds('b').to_factor()
]))
self.assertEqual(
set(infer_bayesian.factors['b']),
set([
self.bayesian.get_cpds('b').to_factor(),
self.bayesian.get_cpds('c').to_factor()
]))
self.assertEqual(
set(infer_bayesian.factors['c']),
set([
self.bayesian.get_cpds('c').to_factor(),
self.bayesian.get_cpds('d').to_factor()
]))
self.assertEqual(
set(infer_bayesian.factors['d']),
set([
self.bayesian.get_cpds('d').to_factor(),
self.bayesian.get_cpds('e').to_factor()
]))
self.assertEqual(set(infer_bayesian.factors['e']),
set([self.bayesian.get_cpds('e').to_factor()]))
def test_markov_inference_init(self):
infer_markov = Inference(self.markov)
self.assertEqual(set(infer_markov.variables), {"a", "b", "c", "d"})
self.assertEqual(infer_markov.cardinality, {
"a": 2,
"b": 2,
"c": 2,
"d": 2
})
self.assertEqual(
infer_markov.factors,
{
"a": [
DiscreteFactor(["a", "b"], [2, 2],
np.array([100, 1, 1, 100])),
DiscreteFactor(["a", "c"], [2, 2],
np.array([40, 30, 100, 20])),
],
"b": [
DiscreteFactor(["a", "b"], [2, 2],
np.array([100, 1, 1, 100])),
DiscreteFactor(["b", "d"], [2, 2],
np.array([1, 100, 100, 1])),
],
"c": [
DiscreteFactor(["a", "c"], [2, 2],
np.array([40, 30, 100, 20])),
DiscreteFactor(["c", "d"], [2, 2],
np.array([60, 60, 40, 40])),
],
"d": [
DiscreteFactor(["b", "d"], [2, 2],
np.array([1, 100, 100, 1])),
DiscreteFactor(["c", "d"], [2, 2],
np.array([60, 60, 40, 40])),
],
},
)
def query(self, query, evidence=None, elimination_order=None):
if not isinstance(query, list):
query = [query]
### DEBUG
# print(">>>>>--------------------------------------<<<<<<")
# print(">>> Query: %s" % query)
# print(">>> Evidence: %s" % evidence)
# print(">>> Saved MTs:")
# for mt in self.marginal_trees:
# print("--> Nodes: %s" % mt.nodes())
# print(mt.evidence)
### --- DEBUG
# See if it is possible to reuse saved MTs
marginal_tree = None
reuse_mts = self.find_reusable(query, evidence)
### DEBUG
# print(">>> Reusable MTs:")
# for mt in reuse_mts:
# print("--> Nodes: %s" % mt.nodes())
# print(mt.evidence)
### --- DEBUG
factors = []
if len(reuse_mts) > 0:
# TODO: choose MT by the size of it
# Choose one MT and rebuild it for the new query and evidence
marginal_tree = reuse_mts[0]
### DEBUG
# print(">>> Nodes before evidence")
# print(marginal_tree.nodes())
# print(">>> Messages before evidence")
# for s in marginal_tree.separators:
# print("--> Separator %s" % s.__str__())
# for f in marginal_tree.separators[s]:
# print(f)
### --- DEBUG
# Reduce new evidences
new_evidence = {k: evidence[k]
for k in evidence
if k not in marginal_tree.evidence}
marginal_tree.set_evidence(new_evidence)
### DEBUG
# print(">>> Nodes after evidence")
# print(marginal_tree.nodes())
# print(">>> Messages before evidence")
# for s in marginal_tree.separators:
# print("--> Separator %s" % s.__str__())
# for f in marginal_tree.separators[s]:
# print(f)
### --- DEBUG
# Rebuild MT to answer new query
marginal_tree = marginal_tree.rebuild(query, evidence)
# Perform one way propagation
self.partial_one_way_propagation(marginal_tree)
else:
marginal_tree = self._build(query, evidence, elimination_order)
### DEBUG
# print(">>> Saving marginal tree")
# print(marginal_tree.nodes())
# print(marginal_tree.evidence)
### --- DEBUG
# Save the new MT
self.marginal_trees.append(marginal_tree)
# Answer the query
node = marginal_tree.root
# Define the variables to marginalize
marginalize = set(node) - set(query)
# Collect factors for the node
neighbors = marginal_tree.neighbors(node)
# Collect incoming messages
for neighbor in neighbors:
if (neighbor, node) in marginal_tree.separators:
factors.extend([f for f in marginal_tree.separators[(neighbor, node)]
if len(f.variables) > 0])
### DEBUG
# print(">>> Root: %s" % marginal_tree.root.__str__())
# print("incoming...")
# for f in factors:
# print(f)
### --- DEBUG
# Collect assigned Factors
factors.extend([f for f in marginal_tree.factor_node_assignment[node]
if len(f.variables) > 0])
### DEBUG
# print("assigned...")
# for f in marginal_tree.factor_node_assignment[node]:
# print(f)
# print("going to SUM OUT %s" % marginalize.__str__())
# for f in factors:
# print(f)
### --- DEBUG
result = None
# Sum out variables from factors
if len(factors) > 0:
result = Inference.sum_out(marginalize, factors)
### DEBUG
# print(">>> After SUM OUT")
# for f in result:
# print(f)
### --- DEBUG
# Multiply all remaining CPDs
if len(result) > 0:
result = factor_product(*result)
### DEBUG
# print(">>> After PRODUCT")
# print(result)
### --- DEBUG
# Normalize
result.normalize()
### DEBUG
# print(">>> After Normalize")
# print(result)
# marginal_tree.draw()
### --- DEBUG
return result
def query(self, query, evidence=None, elimination_order=None):
if not isinstance(query, list):
query = [query]
### DEBUG
# print(">>>>>--------------------------------------<<<<<<")
# print(">>> Query: %s" % query)
# print(">>> Evidence: %s" % evidence)
# print(">>> Saved MTs:")
# for mt in self.marginal_trees:
# print("--> Nodes: %s" % mt.nodes())
# print(mt.evidence)
### --- DEBUG
# See if it is possible to reuse saved MTs
marginal_tree = None
reuse_mts = self.find_reusable(query, evidence)
### DEBUG
# print(">>> Reusable MTs:")
# for mt in reuse_mts:
# print("--> Nodes: %s" % mt.nodes())
# print(mt.evidence)
### --- DEBUG
factors = []
if len(reuse_mts) > 0:
# TODO: choose MT by the size of it
# Choose one MT and rebuild it for the new query and evidence
marginal_tree = reuse_mts[0]
### DEBUG
# print(">>> Nodes before evidence")
# print(marginal_tree.nodes())
# print(">>> Messages before evidence")
# for s in marginal_tree.separators:
# print("--> Separator %s" % s.__str__())
# for f in marginal_tree.separators[s]:
# print(f)
### --- DEBUG
# Reduce new evidences
new_evidence = {
k: evidence[k]
for k in evidence if k not in marginal_tree.evidence
}
marginal_tree.set_evidence(new_evidence)
### DEBUG
# print(">>> Nodes after evidence")
# print(marginal_tree.nodes())
# print(">>> Messages before evidence")
# for s in marginal_tree.separators:
# print("--> Separator %s" % s.__str__())
# for f in marginal_tree.separators[s]:
# print(f)
### --- DEBUG
# Rebuild MT to answer new query
marginal_tree = marginal_tree.rebuild(query, evidence)
# Perform one way propagation
self.partial_one_way_propagation(marginal_tree)
else:
marginal_tree = self._build(query, evidence, elimination_order)
### DEBUG
# print(">>> Saving marginal tree")
# print(marginal_tree.nodes())
# print(marginal_tree.evidence)
### --- DEBUG
# Save the new MT
self.marginal_trees.append(marginal_tree)
# Answer the query
node = marginal_tree.root
# Define the variables to marginalize
marginalize = set(node) - set(query)
# Collect factors for the node
neighbors = marginal_tree.neighbors(node)
# Collect incoming messages
for neighbor in neighbors:
if (neighbor, node) in marginal_tree.separators:
factors.extend([
f for f in marginal_tree.separators[(neighbor, node)]
if len(f.variables) > 0
])
### DEBUG
# print(">>> Root: %s" % marginal_tree.root.__str__())
# print("incoming...")
# for f in factors:
# print(f)
### --- DEBUG
# Collect assigned Factors
factors.extend([
f for f in marginal_tree.factor_node_assignment[node]
if len(f.variables) > 0
])
### DEBUG
# print("assigned...")
# for f in marginal_tree.factor_node_assignment[node]:
# print(f)
# print("going to SUM OUT %s" % marginalize.__str__())
# for f in factors:
# print(f)
### --- DEBUG
result = None
# Sum out variables from factors
if len(factors) > 0:
result = Inference.sum_out(marginalize, factors)
### DEBUG
# print(">>> After SUM OUT")
# for f in result:
# print(f)
### --- DEBUG
# Multiply all remaining CPDs
if len(result) > 0:
result = factor_product(*result)
### DEBUG
# print(">>> After PRODUCT")
# print(result)
### --- DEBUG
# Normalize
result.normalize()
### DEBUG
# print(">>> After Normalize")
# print(result)
# marginal_tree.draw()
### --- DEBUG
return result
def setUp(self):
self.sn2 = {
"grade": ["A", "B", "F"],
"diff": ["high", "low"],
"intel": ["poor", "good", "very good"],
}
self.sn1 = {
"speed": ["low", "medium", "high"],
"switch": ["on", "off"],
"time": ["day", "night"],
}
self.sn2_no_names = {
"grade": [0, 1, 2],
"diff": [0, 1],
"intel": [0, 1, 2]
}
self.sn1_no_names = {
"speed": [0, 1, 2],
"switch": [0, 1],
"time": [0, 1]
}
self.phi1 = DiscreteFactor(["speed", "switch", "time"], [3, 2, 2],
np.ones(12))
self.phi2 = DiscreteFactor(["speed", "switch", "time"], [3, 2, 2],
np.ones(12),
state_names=self.sn1)
self.cpd1 = TabularCPD(
"grade",
3,
[
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8],
],
evidence=["diff", "intel"],
evidence_card=[2, 3],
)
self.cpd2 = TabularCPD(
"grade",
3,
[
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8],
],
evidence=["diff", "intel"],
evidence_card=[2, 3],
state_names=self.sn2,
)
student = BayesianModel([("diff", "grade"), ("intel", "grade")])
diff_cpd = TabularCPD("diff", 2, [[0.2, 0.8]])
intel_cpd = TabularCPD("intel", 2, [[0.3, 0.7]])
grade_cpd = TabularCPD(
"grade",
3,
[[0.1, 0.1, 0.1, 0.1], [0.1, 0.1, 0.1, 0.1], [0.8, 0.8, 0.8, 0.8]],
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
student.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.model1 = Inference(student)
self.model2 = Inference(student)