def setup_titanic():
# Build a model of the titanic disaster
global titanic_network, passenger, gender, tclass
# Passengers on the Titanic either survive or perish
passenger = DiscreteDistribution({'survive': 0.6, 'perish': 0.4})
# Gender, given survival data
gender = ConditionalProbabilityTable(
[['survive', 'male', 0.0], ['survive', 'female', 1.0],
['perish', 'male', 1.0], ['perish', 'female', 0.0]], [passenger])
# Class of travel, given survival data
tclass = ConditionalProbabilityTable(
[['survive', 'first', 0.0], ['survive', 'second', 1.0],
['survive', 'third', 0.0], ['perish', 'first', 1.0],
['perish', 'second', 0.0], ['perish', 'third', 0.0]], [passenger])
# State objects hold both the distribution, and a high level name.
s1 = State(passenger, name="passenger")
s2 = State(gender, name="gender")
s3 = State(tclass, name="class")
# Create the Bayesian network object with a useful name
titanic_network = BayesianNetwork("Titanic Disaster")
# Add the three nodes to the network
titanic_network.add_nodes(s1, s2, s3)
# Add transitions which represent conditional dependencies, where the
# second node is conditionally dependent on the first node (Monty is
# dependent on both guest and prize)
titanic_network.add_edge(s1, s2)
titanic_network.add_edge(s1, s3)
titanic_network.bake()
def test_cpd_sampling():
d1 = DiscreteDistribution({"A": 0.1, "B": 0.9})
d2 = ConditionalProbabilityTable(
[["A", "A", 0.1], ["A", "B", 0.9], ["B", "A", 0.7], ["B", "B", 0.3]],
[d1])
# P(A) = 0.1*0.1 + 0.9*0.7 = 0.64
# P(B) = 0.1*0.9 + 0.9*0.3 = 0.36
true = [0.64, 0.36]
est = numpy.bincount([0 if d2.sample() == "A" else 1 for i in range(1000)]) / 1000.0
assert_almost_equal(est[0], true[0], 1)
assert_almost_equal(est[1], true[1], 1)
# when A is observed, it reduces to [0.1, 0.9]
true1 = [0.1, 0.9]
par_val = {}
par_val[d1] = "A"
est = numpy.bincount(
[0 if d2.sample(parent_values=par_val) == "A" else 1 for i in range(1000)]
) / 1000.0
assert_almost_equal(est[0], true1[0], 1)
assert_almost_equal(est[1], true1[1], 1)
true2= [0.7, 0.3]
par_val = {}
par_val[d1] = "B"
est = numpy.bincount(
[0 if d2.sample(parent_values=par_val) == "A" else 1 for i in range(1000)]
) / 1000.0
assert_almost_equal(est[0], true2[0], 1)
assert_almost_equal(est[1], true2[1], 1)
def get_bayesnet(self):
door_lock = DiscreteDistribution({'d1': 0.7, 'd2': 0.3})
clock_alarm = DiscreteDistribution( { 'a1' : 0.8, 'a2' : 0.2} )
light = ConditionalProbabilityTable(
[[ 'd1', 'a1', 'l1', 0.96 ],
['d1', 'a1', 'l2', 0.04 ],
[ 'd1', 'a2', 'l1', 0.89 ],
[ 'd1', 'a2', 'l2', 0.11 ],
[ 'd2', 'a1', 'l1', 0.96 ],
[ 'd2', 'a1', 'l2', 0.04 ],
[ 'd2', 'a2', 'l1', 0.89 ],
[ 'd2', 'a2', 'l2', 0.11 ]], [door_lock, clock_alarm])
coffee_maker = ConditionalProbabilityTable(
[[ 'a1', 'c1', 0.92 ],
[ 'a1', 'c2', 0.08 ],
[ 'a2', 'c1', 0.03 ],
[ 'a2', 'c2', 0.97 ]], [clock_alarm] )
s_door_lock = State(door_lock, name="door_lock")
s_clock_alarm = State(clock_alarm, name="clock_alarm")
s_light = State(light, name="light")
s_coffee_maker = State(coffee_maker, name="coffee_maker")
network = BayesianNetwork("User_pref")
network.add_nodes(s_door_lock, s_clock_alarm, s_light, s_coffee_maker)
network.add_edge(s_door_lock,s_light)
network.add_edge(s_clock_alarm,s_coffee_maker)
network.add_edge(s_clock_alarm,s_light)
network.bake()
return network
def test_cpd_sampling():
d1 = DiscreteDistribution({"A": 0.1, "B": 0.9})
d2 = ConditionalProbabilityTable(
[["A", "A", 0.1], ["A", "B", 0.9], ["B", "A", 0.7], ["B", "B", 0.3]],
[d1])
# P(A) = 0.1*0.1 + 0.9*0.7 = 0.64
# P(B) = 0.1*0.9 + 0.9*0.3 = 0.36
true = [0.64, 0.36]
est = numpy.bincount([0 if d2.sample() == "A" else 1
for i in range(1000)]) / 1000.0
assert_almost_equal(est[0], true[0], 1)
assert_almost_equal(est[1], true[1], 1)
# when A is observed, it reduces to [0.1, 0.9]
true1 = [0.1, 0.9]
par_val = {}
par_val[d1] = "A"
est = numpy.bincount([
0 if d2.sample(parent_values=par_val) == "A" else 1
for i in range(1000)
]) / 1000.0
assert_almost_equal(est[0], true1[0], 1)
assert_almost_equal(est[1], true1[1], 1)
true2 = [0.7, 0.3]
par_val = {}
par_val[d1] = "B"
est = numpy.bincount([
0 if d2.sample(parent_values=par_val) == "A" else 1
for i in range(1000)
]) / 1000.0
assert_almost_equal(est[0], true2[0], 1)
assert_almost_equal(est[1], true2[1], 1)
def test_conditional():
phditis = DiscreteDistribution({True: 0.01, False: 0.99})
test_result = ConditionalProbabilityTable(
[[True, True, 0.95],
[True, False, 0.05],
[False, True, 0.05],
[False, False, 0.95]], [phditis])
assert discrete_equality(test_result.marginal(),
DiscreteDistribution({False: 0.941, True: 0.059}))
def test_conditional():
phditis = DiscreteDistribution({True: 0.01, False: 0.99})
test_result = ConditionalProbabilityTable(
[[True, True, 0.95],
[True, False, 0.05],
[False, True, 0.05],
[False, False, 0.95]], [phditis])
assert discrete_equality(test_result.marginal(),
DiscreteDistribution({False: 0.941, True: 0.059}))
def test_distributions_cpt_random_sample():
d1 = DiscreteDistribution({"A": 0.1, "B": 0.9})
d = ConditionalProbabilityTable(
[["A", "A", 0.1], ["A", "B", 0.9], ["B", "A", 0.7], ["B", "B", 0.3]],
[d1])
x = numpy.array(['B', 'A', 'B', 'B', 'A', 'B', 'A', 'A', 'B', 'A', 'A',
'B', 'A', 'A', 'A', 'A', 'A', 'A', 'A', 'A'])
assert_array_equal(d.sample(n=20, random_state=5), x)
assert_raises(AssertionError, assert_array_equal, d.sample(n=10), x)
def __init__(self):
Pollution = DiscreteDistribution({'F': 0.9, 'T': 0.1})
Smoker = DiscreteDistribution({'T': 0.3, 'F': 0.7})
print(Smoker)
Cancer = ConditionalProbabilityTable([
['T', 'T', 'T', 0.05],
['T', 'T', 'F', 0.95],
['T', 'F', 'T', 0.02],
['T', 'F', 'F', 0.98],
['F', 'T', 'T', 0.03],
['F', 'T', 'F', 0.97],
['F', 'F', 'T', 0.001],
['F', 'F', 'F', 0.999],
], [Pollution, Smoker])
print(Cancer)
XRay = ConditionalProbabilityTable([
['T', 'T', 0.9],
['T', 'F', 0.1],
['F', 'T', 0.2],
['F', 'F', 0.8],
], [Cancer])
Dyspnoea = ConditionalProbabilityTable([
['T', 'T', 0.65],
['T', 'F', 0.35],
['F', 'T', 0.3],
['F', 'F', 0.7],
], [Cancer])
s1 = Node(Pollution, name="Pollution")
s2 = Node(Smoker, name="Smoker")
s3 = Node(Cancer, name="Cancer")
s4 = Node(XRay, name="XRay")
s5 = Node(Dyspnoea, name="Dyspnoea")
model = BayesianNetwork("Lung Cancer")
model.add_states(s1, s2, s3, s4, s5)
model.add_edge(s1, s3)
model.add_edge(s2, s3)
model.add_edge(s3, s4)
model.add_edge(s3, s5)
model.bake()
self.model = model
meta = []
name_mapper = ["Pollution", "Smoker", "Cancer", "XRay", "Dyspnoea"]
for i in range(self.model.node_count()):
meta.append({
"name": name_mapper[i],
"type": "categorical",
"size": 2,
"i2s": ['T', 'F']
})
self.meta = meta
def __init__(self):
A = DiscreteDistribution({'1': 1. / 3, '2': 1. / 3, '3': 1. / 3})
B = ConditionalProbabilityTable([
['1', '1', 0.5],
['1', '2', 0.5],
['1', '3', 0],
['2', '1', 0],
['2', '2', 0.5],
['2', '3', 0.5],
['3', '1', 0.5],
['3', '2', 0],
['3', '3', 0.5],
], [A])
C = ConditionalProbabilityTable([
['1', '4', 0.5],
['1', '5', 0.5],
['1', '6', 0],
['2', '4', 0],
['2', '5', 0.5],
['2', '6', 0.5],
['3', '4', 0.5],
['3', '5', 0],
['3', '6', 0.5],
], [A])
s1 = Node(A, name="A")
s2 = Node(B, name="B")
s3 = Node(C, name="C")
model = BayesianNetwork("tree")
model.add_states(s1, s2, s3)
model.add_edge(s1, s2)
model.add_edge(s1, s3)
model.bake()
self.model = model
meta = []
for i in range(self.model.node_count() - 1):
meta.append({
"name": chr(ord('A') + i),
"type": "categorical",
"size": 3,
"i2s": ['1', '2', '3']
})
meta.append({
"name": "C",
"type": "categorical",
"size": 3,
"i2s": ['4', '5', '6']
})
self.meta = meta
def test_io_fit():
d1 = DiscreteDistribution({True: 0.6, False: 0.4})
d2 = ConditionalProbabilityTable([
[True, 'A', 0.2],
[True, 'B', 0.8],
[False, 'A', 0.3],
[False, 'B', 0.7]], [d1])
d3 = ConditionalProbabilityTable([
['A', 0, 0.3],
['A', 1, 0.7],
['B', 0, 0.8],
['B', 1, 0.2]], [d2])
n1 = Node(d1)
n2 = Node(d2)
n3 = Node(d3)
model1 = BayesianNetwork()
model1.add_nodes(n1, n2, n3)
model1.add_edge(n1, n2)
model1.add_edge(n2, n3)
model1.bake()
model1.fit(X, weights=weights)
d1 = DiscreteDistribution({True: 0.2, False: 0.8})
d2 = ConditionalProbabilityTable([
[True, 'A', 0.7],
[True, 'B', 0.2],
[False, 'A', 0.4],
[False, 'B', 0.6]], [d1])
d3 = ConditionalProbabilityTable([
['A', 0, 0.9],
['A', 1, 0.1],
['B', 0, 0.0],
['B', 1, 1.0]], [d2])
n1 = Node(d1)
n2 = Node(d2)
n3 = Node(d3)
model2 = BayesianNetwork()
model2.add_nodes(n1, n2, n3)
model2.add_edge(n1, n2)
model2.add_edge(n2, n3)
model2.bake()
model2.fit(data_generator)
logp1 = model1.log_probability(X)
logp2 = model2.log_probability(X)
assert_array_almost_equal(logp1, logp2)
def setup_monty():
# Build a model of the Monty Hall Problem
global monty_network, monty_index, prize_index, guest_index
random.seed(0)
# Friends emissions are completely random
guest = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
# The actual prize is independent of the other distributions
prize = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
# Monty is dependent on both the guest and the prize.
monty = ConditionalProbabilityTable(
[['A', 'A', 'A', 0.0],
['A', 'A', 'B', 0.5],
['A', 'A', 'C', 0.5],
['A', 'B', 'A', 0.0],
['A', 'B', 'B', 0.0],
['A', 'B', 'C', 1.0],
['A', 'C', 'A', 0.0],
['A', 'C', 'B', 1.0],
['A', 'C', 'C', 0.0],
['B', 'A', 'A', 0.0],
['B', 'A', 'B', 0.0],
['B', 'A', 'C', 1.0],
['B', 'B', 'A', 0.5],
['B', 'B', 'B', 0.0],
['B', 'B', 'C', 0.5],
['B', 'C', 'A', 1.0],
['B', 'C', 'B', 0.0],
['B', 'C', 'C', 0.0],
['C', 'A', 'A', 0.0],
['C', 'A', 'B', 1.0],
['C', 'A', 'C', 0.0],
['C', 'B', 'A', 1.0],
['C', 'B', 'B', 0.0],
['C', 'B', 'C', 0.0],
['C', 'C', 'A', 0.5],
['C', 'C', 'B', 0.5],
['C', 'C', 'C', 0.0]], [guest, prize])
# Make the states
s1 = State(guest, name="guest")
s2 = State(prize, name="prize")
s3 = State(monty, name="monty")
# Make the bayes net, add the states, and the conditional dependencies.
monty_network = BayesianNetwork("test")
monty_network.add_nodes(s1, s2, s3)
monty_network.add_edge(s1, s3)
monty_network.add_edge(s2, s3)
monty_network.bake()
monty_index = monty_network.states.index(s3)
prize_index = monty_network.states.index(s2)
guest_index = monty_network.states.index(s1)
def create_con_prob_table(num_prereqs, num_grades, states):
# Creates the cartesian product of the grades as a DataFrame
df_events = create_cartesian_table(num_grades, num_prereqs + 1)
# Adds a column of probabilities as floats to the DataFrame
df_events[len(df_events.columns)] = 1 / num_grades
return ConditionalProbabilityTable(df_events.values.tolist(),
get_disc_dist_list(states))
def __init__(self):
Rain = DiscreteDistribution({'T': 0.2, 'F': 0.8})
Sprinkler = ConditionalProbabilityTable([
['F', 'T', 0.4],
['F', 'F', 0.6],
['T', 'T', 0.1],
['T', 'F', 0.9],
], [Rain])
Wet = ConditionalProbabilityTable([
['F', 'F', 'T', 0.01],
['F', 'F', 'F', 0.99],
['F', 'T', 'T', 0.8],
['F', 'T', 'F', 0.2],
['T', 'F', 'T', 0.9],
['T', 'F', 'F', 0.1],
['T', 'T', 'T', 0.99],
['T', 'T', 'F', 0.01],
], [Sprinkler, Rain])
s1 = Node(Rain, name="Rain")
s2 = Node(Sprinkler, name="Sprinkler")
s3 = Node(Wet, name="Wet")
model = BayesianNetwork("Simple fully connected")
model.add_states(s1, s2, s3)
model.add_edge(s1, s2)
model.add_edge(s1, s3)
model.add_edge(s2, s3)
model.bake()
self.model = model
meta = []
for i in range(self.model.node_count()):
meta.append({
"name": None,
"type": "categorical",
"size": 2,
"i2s": ['T', 'F']
})
meta[0]['name'] = 'Rain'
meta[1]['name'] = 'Sprinkler'
meta[2]['name'] = 'Wet'
self.meta = meta
def build_cpts(dfs):
cpts = dict() # maps the name of the node to its cpt
for node, df in dfs:
_, parents, values = get_metadata_of(node)
if not any(parents):
# if we have only two columns, DiscreteDistribution
cpts[node] = DiscreteDistribution(dict(df.values))
else:
cpts[node] = ConditionalProbabilityTable(
df.values, [cpts[parent] for parent in parents])
return cpts
def export_probabilities(self, parents=None):
if self.get_is_conditional():
probs = []
for item in self._items:
probs.append(item.export_probabilities())
out = ConditionalProbabilityTable(probs, parents)
else:
probs = {}
for item in self._items:
probs[item.get_outcome()] = item.get_probability()
out = DiscreteDistribution(probs)
return out
def setup_cpt():
guest = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
prize = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
global monty
monty = ConditionalProbabilityTable(
[['A', 'A', 'A', 0.0], ['A', 'A', 'B', 0.5], ['A', 'A', 'C', 0.5],
['A', 'B', 'A', 0.0], ['A', 'B', 'B', 0.0], ['A', 'B', 'C', 1.0],
['A', 'C', 'A', 0.0], ['A', 'C', 'B', 1.0], ['A', 'C', 'C', 0.0],
['B', 'A', 'A', 0.0], ['B', 'A', 'B', 0.0], ['B', 'A', 'C', 1.0],
['B', 'B', 'A', 0.5], ['B', 'B', 'B', 0.0], ['B', 'B', 'C', 0.5],
['B', 'C', 'A', 1.0], ['B', 'C', 'B', 0.0], ['B', 'C', 'C', 0.0],
['C', 'A', 'A', 0.0], ['C', 'A', 'B', 1.0], ['C', 'A', 'C', 0.0],
['C', 'B', 'A', 1.0], ['C', 'B', 'B', 0.0], ['C', 'B', 'C', 0.0],
['C', 'C', 'A', 0.5], ['C', 'C', 'B', 0.5], ['C', 'C', 'C', 0.0]],
[guest, prize])
global X
X = [['A', 'A', 'C'], ['A', 'A', 'B'], ['A', 'A', 'C'], ['A', 'A', 'B'],
['A', 'A', 'A'], ['A', 'B', 'A'], ['A', 'B', 'A'], ['A', 'B', 'B'],
['A', 'B', 'C'], ['A', 'C', 'A'], ['A', 'C', 'C'], ['A', 'C', 'C'],
['A', 'C', 'C'], ['A', 'C', 'B'], ['B', 'A', 'A'], ['B', 'A', 'B'],
['B', 'A', 'B'], ['B', 'A', 'B'], ['B', 'B', 'B'], ['B', 'B', 'C'],
['B', 'C', 'A'], ['B', 'C', 'B'], ['B', 'C', 'A'], ['B', 'C', 'B'],
['C', 'A', 'B'], ['C', 'B', 'B'], ['C', 'B', 'C'], ['C', 'C', 'A'],
['C', 'C', 'C'], ['C', 'C', 'C'], ['C', 'C', 'C']]
global X_nan
X_nan = [['nan', 'A', 'C'], ['A', 'A', 'nan'], ['A', 'nan', 'C'],
['A', 'A', 'B'], ['A', 'A', 'A'], ['A', 'B', 'nan'],
['A', 'B', 'A'], ['A', 'B', 'nan'], ['A', 'B', 'C'],
['A', 'C', 'A'], ['A', 'nan', 'C'], ['A', 'C', 'C'],
['A', 'C', 'C'], ['A', 'C', 'B'], ['B', 'nan', 'A'],
['B', 'A', 'B'], ['nan', 'A', 'B'], ['B', 'A', 'B'],
['B', 'B', 'B'], ['B', 'B', 'C'], ['B', 'C', 'A'],
['nan', 'C', 'B'], ['B', 'C', 'A'], ['nan', 'C', 'B'],
['C', 'A', 'B'], ['C', 'B', 'B'], ['C', 'nan', 'C'],
['C', 'nan', 'A'], ['C', 'nan', 'C'], ['C', 'C', 'C'],
['C', 'C', 'C']]
def __get_bayesian_network_model(
self,
symptom_distributions: List,
symptom_states: List,
file_name: str,
disease_name: str,
):
disease_conditional_distribution = list()
for (s1, s2, s3, s4, s5, d, p) in get_from_csv(file_name):
disease_conditional_distribution.append(
[s1, s2, s3, s4, s5, d, float(p)])
disease_distribution = ConditionalProbabilityTable(
disease_conditional_distribution,
symptom_distributions,
)
disease = Node(disease_distribution, name=disease_name)
model = BayesianNetwork(disease_name)
model.add_state(disease)
for symptom_state in symptom_states:
model.add_state(symptom_state)
model.add_edge(symptom_state, disease)
model.bake()
return model
def worker(node: Type[BaseNode]) -> DiscreteParams:
parents = node.disc_parents + node.cont_parents
if not parents:
dist = DiscreteDistribution.from_samples(
data[node.name].values)
cprob = list(dict(sorted(dist.items())).values())
vals = sorted(
[str(x) for x in list(dist.parameters[0].keys())])
else:
dist = DiscreteDistribution.from_samples(
data[node.name].values)
vals = sorted(
[str(x) for x in list(dist.parameters[0].keys())])
dist = ConditionalProbabilityTable.from_samples(
data[parents + [node.name]].values)
params = dist.parameters[0]
cprob = dict()
for i in range(0, len(params), len(vals)):
probs = []
for j in range(i, (i + len(vals))):
probs.append(params[j][-1])
combination = [str(x) for x in params[i][0:len(parents)]]
cprob[str(combination)] = probs
return {"cprob": cprob, 'vals': vals}
from pomegranate import DiscreteDistribution
from pomegranate import ConditionalProbabilityTable
from pomegranate import BayesianNetwork
from pomegranate import Node
guest = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
prize = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
monty = ConditionalProbabilityTable(
[['A', 'A', 'A', 0.0], ['A', 'A', 'B', 0.5], ['A', 'A', 'C', 0.5],
['A', 'B', 'A', 0.0], ['A', 'B', 'B', 0.0], ['A', 'B', 'C', 1.0],
['A', 'C', 'A', 0.0], ['A', 'C', 'B', 1.0], ['A', 'C', 'C', 0.0],
['B', 'A', 'A', 0.0], ['B', 'A', 'B', 0.0], ['B', 'A', 'C', 1.0],
['B', 'B', 'A', 0.5], ['B', 'B', 'B', 0.0], ['B', 'B', 'C', 0.5],
['B', 'C', 'A', 1.0], ['B', 'C', 'B', 0.0], ['B', 'C', 'C', 0.0],
['C', 'A', 'A', 0.0], ['C', 'A', 'B', 1.0], ['C', 'A', 'C', 0.0],
['C', 'B', 'A', 1.0], ['C', 'B', 'B', 0.0], ['C', 'B', 'C', 0.0],
['C', 'C', 'A', 0.5], ['C', 'C', 'B', 0.5], ['C', 'C', 'C', 0.0]],
[guest, prize])
s1 = Node(guest, name="guest")
s2 = Node(prize, name="prize")
s3 = Node(monty, name="monty")
model = BayesianNetwork("Monty Hall Problem")
model.add_states(s1, s2, s3)
model.add_edge(s1, s3)
model.add_edge(s2, s3)
model.bake()
def __init__(self, filename):
with open(filename) as f:
bif = f.read()
vars = re.findall(r"variable[^\{]+{[^\}]+}", bif)
probs = re.findall(r"probability[^\{]+{[^\}]+}", bif)
var_nodes = {}
var_index_to_name = []
edges = []
self.meta = []
todo = set()
for v, p in zip(vars, probs):
m = re.search(r"variable\s+([^\{\s]+)\s+", v)
v_name = m.group(1)
m = re.search(r"type\s+discrete\s+\[\s*(\d+)\s*\]\s*\{([^\}]+)\}",
v)
v_opts_n = int(m.group(1))
v_opts = m.group(2).replace(',', ' ').split()
assert v_opts_n == len(v_opts)
# print(v_name, v_opts_n, v_opts)
m = re.search(r"probability\s*\(([^)]+)\)", p)
cond = m.group(1).replace('|', ' ').replace(',', ' ').split()
assert cond[0] == v_name
# print(cond)
self.meta.append({
"name": v_name,
"type": "categorical",
"size": v_opts_n,
"i2s": v_opts
})
if len(cond) == 1:
m = re.search(r"table([e\-\d\.\s,]*);", p)
margin_p = m.group(1).replace(',', ' ').split()
margin_p = [float(x) for x in margin_p]
assert abs(sum(margin_p) - 1) < 1e-6
assert len(margin_p) == v_opts_n
margin_p = dict(zip(v_opts, margin_p))
var_index_to_name.append(v_name)
tmp = DiscreteDistribution(margin_p)
# print(tmp)
var_nodes[v_name] = tmp
else:
m_iter = re.finditer(r"\(([^)]*)\)([\s\d\.,\-e]+);", p)
cond_p_table = []
for m in m_iter:
cond_values = m.group(1).replace(',', ' ').split()
cond_p = m.group(2).replace(',', ' ').split()
cond_p = [float(x) for x in cond_p]
assert len(cond_values) == len(cond) - 1
assert len(cond_p) == v_opts_n
assert abs(sum(cond_p) - 1) < 1e-6
for opt, opt_p in zip(v_opts, cond_p):
cond_p_table.append(cond_values + [opt, opt_p])
var_index_to_name.append(v_name)
tmp = (cond_p_table, cond)
# print(tmp)
var_nodes[v_name] = tmp
for x in cond[1:]:
edges.append((x, v_name))
todo.add(v_name)
while len(todo) > 0:
# print(todo)
for v_name in todo:
# print(v_name, type(var_nodes[v_name]))
cond_p_table, cond = var_nodes[v_name]
flag = True
for y in cond[1:]:
if y in todo:
flag = False
break
if flag:
cond_t = [var_nodes[x] for x in cond[1:]]
var_nodes[v_name] = ConditionalProbabilityTable(
cond_p_table, cond_t)
todo.remove(v_name)
break
for x in var_index_to_name:
var_nodes[x] = Node(var_nodes[x], name=x)
var_nodes_list = [var_nodes[x] for x in var_index_to_name]
# print(var_nodes_list)
model = BayesianNetwork("tmp")
model.add_states(*var_nodes_list)
for edge in edges:
model.add_edge(var_nodes[edge[0]], var_nodes[edge[1]])
model.bake()
# print(model.to_json())
self.model = model
def get_BN(self, DAG, child_parent):
#1. get DAG structure as an arguments
################################################
node_without_parents = [
e for e in self.nodes if e not in child_parent.keys()
]
# 2 Build BN probability model
# 2.1 get probabilityDist or conditional prob table
# bais the prob to task_dict choices
node_prob_dict = self.get_nodes_prob_dist(node_without_parents,
child_parent)
self.npd = node_prob_dict
# 2.2 Create nodes linked to its parent, parent should be processed first.
# all node state saved to be added to the BN later
nodes_state = {}
# all node dist or CPT saved to link child to parents when building child CPT
nodes_dist = {}
# start with root nodes (don't have parents then link child to them)
# list the list to copy it, otherwise it will point to the self.nodes
remaining_nodes_list = list(self.nodes)
for node in node_without_parents:
prob_dist = node_prob_dict[node]
# print("Parent", node, prob_dist)
node_dist = DiscreteDistribution(prob_dist)
nodes_dist[node] = node_dist
nodes_state[node] = State(node_dist, name=node)
# remove from nodes_list
remaining_nodes_list.remove(node)
# rest of the node should have parents
while len(remaining_nodes_list) > 0:
for node, parent_lst in child_parent.items():
# if node's parents already created then it can be created now
if set(parent_lst).issubset(nodes_state.keys()) and \
node in remaining_nodes_list:
# print("parent child", parent_lst, node, node_prob_dict[node])
node_dist = ConditionalProbabilityTable(node_prob_dict[node], \
[nodes_dist[i] for i in parent_lst])
nodes_dist[node] = node_dist
nodes_state[node] = State(node_dist, name=node)
# remove from the node_list
remaining_nodes_list.remove(node)
# 3 Create BN and add the nodes_state
self.network = BayesianNetwork("User_pref")
for node, state in nodes_state.items():
self.network.add_node(state)
#print("node ", node, " is added!")
self.BN_node_orders.append(node)
# 4 Link nodes with edges using nodes_state and DAG.edge
for a, bs in DAG.edge.items():
for b in bs.keys():
self.network.add_edge(nodes_state[a], nodes_state[b])
# print("Netwoerk:", a, b)
# print("Network has ", self.network.node_count() , " nodes and ", self.network.edge_count(), " edges")
return self.network
def test_monty():
guest = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
# The actual prize is independent of the other distributions
prize = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
# Monty is dependent on both the guest and the prize.
monty = ConditionalProbabilityTable(
[['A', 'A', 'A', 0.0],
['A', 'A', 'B', 0.5],
['A', 'A', 'C', 0.5],
['A', 'B', 'A', 0.0],
['A', 'B', 'B', 0.0],
['A', 'B', 'C', 1.0],
['A', 'C', 'A', 0.0],
['A', 'C', 'B', 1.0],
['A', 'C', 'C', 0.0],
['B', 'A', 'A', 0.0],
['B', 'A', 'B', 0.0],
['B', 'A', 'C', 1.0],
['B', 'B', 'A', 0.5],
['B', 'B', 'B', 0.0],
['B', 'B', 'C', 0.5],
['B', 'C', 'A', 1.0],
['B', 'C', 'B', 0.0],
['B', 'C', 'C', 0.0],
['C', 'A', 'A', 0.0],
['C', 'A', 'B', 1.0],
['C', 'A', 'C', 0.0],
['C', 'B', 'A', 1.0],
['C', 'B', 'B', 0.0],
['C', 'B', 'C', 0.0],
['C', 'C', 'A', 0.5],
['C', 'C', 'B', 0.5],
['C', 'C', 'C', 0.0]], [guest, prize])
assert_equal(monty.log_probability(('A', 'B', 'C')), 0.)
assert_equal(monty.log_probability(('C', 'B', 'A')), 0.)
assert_equal(monty.log_probability(('C', 'C', 'C')), float("-inf"))
assert_equal(monty.log_probability(('A', 'A', 'A')), float("-inf"))
assert_equal(monty.log_probability(('B', 'A', 'C')), 0.)
assert_equal(monty.log_probability(('C', 'A', 'B')), 0.)
data = [['A', 'A', 'C'],
['A', 'A', 'C'],
['A', 'A', 'B'],
['A', 'A', 'A'],
['A', 'A', 'C'],
['B', 'B', 'B'],
['B', 'B', 'C'],
['C', 'C', 'A'],
['C', 'C', 'C'],
['C', 'C', 'C'],
['C', 'C', 'C'],
['C', 'B', 'A']]
monty.fit(data, weights=[1, 1, 3, 3, 1, 1, 3, 7, 1, 1, 1, 1])
assert_equal(monty.log_probability(('A', 'A', 'A')),
monty.log_probability(('A', 'A', 'C')))
assert_equal(monty.log_probability(('A', 'A', 'A')),
monty.log_probability(('A', 'A', 'B')))
assert_equal(monty.log_probability(('B', 'A', 'A')),
monty.log_probability(('B', 'A', 'C')))
assert_equal(monty.log_probability(('B', 'B', 'A')), float("-inf"))
assert_equal(monty.log_probability(('C', 'C', 'B')), float("-inf"))
# ["T", "F", 0.45863],
# ["F", "T", 1 - 0.845],
# ["F", "F", 1 - 0.45863],
# ]
coughing_allergy_lung_cancer = [
["T", "F", "F", 0.13],
["T", "T", "F", 0.64],
["T", "F", "T", 0.76],
["T", "T", "T", 0.99],
["F", "F", "F", 1 - 0.13],
["F", "T", "F", 1 - 0.64],
["F", "F", "T", 1 - 0.76],
["F", "T", "T", 1 - 0.99],
]
Attention_Disorder = ConditionalProbabilityTable(table=attention_genetics, parents=[Genetics])
Smoking = ConditionalProbabilityTable(table=smoking_peer_pressure_anxiety,
parents=[Peer_Pressure, Anxiety])
Lung_cancer = ConditionalProbabilityTable(table=lung_cancer_genetics_smoking,
parents=[Genetics, Smoking])
Coughing = ConditionalProbabilityTable(table=coughing_allergy_lung_cancer,
parents=[Allergy, Lung_cancer])
Yellow_Fingers = ConditionalProbabilityTable(table=yellow_fingers_smoking,
parents=[Smoking])
Fatigue = ConditionalProbabilityTable(table=fatigue_lung_cancer_coughing, parents=[Lung_cancer,Coughing])
Car_Accident = ConditionalProbabilityTable(table=car_accident_attention_fatigue,
parents=[Attention_Disorder, Fatigue])
states = {}
states['Anxiety'] = State(Anxiety, name="Anxiety")
states['Peer_Pressure'] = State(Peer_Pressure, name="Peer_Pressure")
from pomegranate import DiscreteDistribution
from pomegranate import ConditionalProbabilityTable
from pomegranate import BayesianNetwork
from pomegranate import Node
# Rain node has no parents
rain = Node(DiscreteDistribution({
"none": 0.7,
"light": 0.2,
"heavy": 0.1
}),
name="rain")
# Track maintenance node is coditional on rain
maintenance = Node(ConditionalProbabilityTable(
[["none", "yes", 0.4], ["none", "no", 0.6], ["light", "yes", 0.2],
["light", "no", 0.8], ["heavy", "yes", 0.1], ["heavy", "no", 0.9]],
[rain.distribution]),
name="maintenance")
# Train Node is conditional on rain, and maintenance
train = Node(ConditionalProbabilityTable([
["none", "yes", "on time", 0.8],
["none", "yes", "delayed", 0.2],
["none", "no", "on time", 0.9],
["none", "no", "delayed", 0.1],
["light", "yes", "on time", 0.6],
["light", "yes", "delayed", 0.4],
["light", "no", "on time", 0.7],
["light", "no", "delayed", 0.3],
["heavy", "yes", "on time", 0.4],
["heavy", "yes", "delayed", 0.6],
def setup_huge_monty():
# Build the huge monty hall huge_monty_network. This is an example I made
# up with which may not exactly flow logically, but tests a varied type of
# tables ensures heterogeneous types of data work together.
global huge_monty_network, huge_monty_friend, huge_monty_guest, huge_monty
global huge_monty_remaining, huge_monty_randomize, huge_monty_prize
# Huge_Monty_Friend
huge_monty_friend = DiscreteDistribution({True: 0.5, False: 0.5})
# Huge_Monty_Guest emisisons are completely random
huge_monty_guest = ConditionalProbabilityTable(
[[True, 'A', 0.50],
[True, 'B', 0.25],
[True, 'C', 0.25],
[False, 'A', 0.0],
[False, 'B', 0.7],
[False, 'C', 0.3]], [huge_monty_friend])
# Number of huge_monty_remaining cars
huge_monty_remaining = DiscreteDistribution({0: 0.1, 1: 0.7, 2: 0.2, })
# Whether they huge_monty_randomize is dependent on the numnber of
# huge_monty_remaining cars
huge_monty_randomize = ConditionalProbabilityTable(
[[0, True, 0.05],
[0, False, 0.95],
[1, True, 0.8],
[1, False, 0.2],
[2, True, 0.5],
[2, False, 0.5]], [huge_monty_remaining])
# Where the huge_monty_prize is depends on if they huge_monty_randomize or
# not and also the huge_monty_guests huge_monty_friend
huge_monty_prize = ConditionalProbabilityTable(
[[True, True, 'A', 0.3],
[True, True, 'B', 0.4],
[True, True, 'C', 0.3],
[True, False, 'A', 0.2],
[True, False, 'B', 0.4],
[True, False, 'C', 0.4],
[False, True, 'A', 0.1],
[False, True, 'B', 0.9],
[False, True, 'C', 0.0],
[False, False, 'A', 0.0],
[False, False, 'B', 0.4],
[False, False, 'C', 0.6]], [huge_monty_randomize, huge_monty_friend])
# Monty is dependent on both the huge_monty_guest and the huge_monty_prize.
huge_monty = ConditionalProbabilityTable(
[['A', 'A', 'A', 0.0],
['A', 'A', 'B', 0.5],
['A', 'A', 'C', 0.5],
['A', 'B', 'A', 0.0],
['A', 'B', 'B', 0.0],
['A', 'B', 'C', 1.0],
['A', 'C', 'A', 0.0],
['A', 'C', 'B', 1.0],
['A', 'C', 'C', 0.0],
['B', 'A', 'A', 0.0],
['B', 'A', 'B', 0.0],
['B', 'A', 'C', 1.0],
['B', 'B', 'A', 0.5],
['B', 'B', 'B', 0.0],
['B', 'B', 'C', 0.5],
['B', 'C', 'A', 1.0],
['B', 'C', 'B', 0.0],
['B', 'C', 'C', 0.0],
['C', 'A', 'A', 0.0],
['C', 'A', 'B', 1.0],
['C', 'A', 'C', 0.0],
['C', 'B', 'A', 1.0],
['C', 'B', 'B', 0.0],
['C', 'B', 'C', 0.0],
['C', 'C', 'A', 0.5],
['C', 'C', 'B', 0.5],
['C', 'C', 'C', 0.0]], [huge_monty_guest, huge_monty_prize])
# Make the states
s0 = State(huge_monty_friend, name="huge_monty_friend")
s1 = State(huge_monty_guest, name="huge_monty_guest")
s2 = State(huge_monty_prize, name="huge_monty_prize")
s3 = State(huge_monty, name="huge_monty")
s4 = State(huge_monty_remaining, name="huge_monty_remaining")
s5 = State(huge_monty_randomize, name="huge_monty_randomize")
# Make the bayes net, add the states, and the conditional dependencies.
huge_monty_network = BayesianNetwork("test")
huge_monty_network.add_nodes(s0, s1, s2, s3, s4, s5)
huge_monty_network.add_transition(s0, s1)
huge_monty_network.add_transition(s1, s3)
huge_monty_network.add_transition(s2, s3)
huge_monty_network.add_transition(s4, s5)
huge_monty_network.add_transition(s5, s2)
huge_monty_network.add_transition(s0, s2)
huge_monty_network.bake()
def test_monty():
guest = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
# The actual prize is independent of the other distributions
prize = DiscreteDistribution({'A': 1. / 3, 'B': 1. / 3, 'C': 1. / 3})
# Monty is dependent on both the guest and the prize.
monty = ConditionalProbabilityTable(
[['A', 'A', 'A', 0.0], ['A', 'A', 'B', 0.5], ['A', 'A', 'C', 0.5],
['A', 'B', 'A', 0.0], ['A', 'B', 'B', 0.0], ['A', 'B', 'C', 1.0],
['A', 'C', 'A', 0.0], ['A', 'C', 'B', 1.0], ['A', 'C', 'C', 0.0],
['B', 'A', 'A', 0.0], ['B', 'A', 'B', 0.0], ['B', 'A', 'C', 1.0],
['B', 'B', 'A', 0.5], ['B', 'B', 'B', 0.0], ['B', 'B', 'C', 0.5],
['B', 'C', 'A', 1.0], ['B', 'C', 'B', 0.0], ['B', 'C', 'C', 0.0],
['C', 'A', 'A', 0.0], ['C', 'A', 'B', 1.0], ['C', 'A', 'C', 0.0],
['C', 'B', 'A', 1.0], ['C', 'B', 'B', 0.0], ['C', 'B', 'C', 0.0],
['C', 'C', 'A', 0.5], ['C', 'C', 'B', 0.5], ['C', 'C', 'C', 0.0]],
[guest, prize])
assert_equal(monty.log_probability(('A', 'B', 'C')), 0.)
assert_equal(monty.log_probability(('C', 'B', 'A')), 0.)
assert_equal(monty.log_probability(('C', 'C', 'C')), float("-inf"))
assert_equal(monty.log_probability(('A', 'A', 'A')), float("-inf"))
assert_equal(monty.log_probability(('B', 'A', 'C')), 0.)
assert_equal(monty.log_probability(('C', 'A', 'B')), 0.)
data = [['A', 'A', 'C'], ['A', 'A', 'C'], ['A', 'A', 'B'], ['A', 'A', 'A'],
['A', 'A', 'C'], ['B', 'B', 'B'], ['B', 'B', 'C'], ['C', 'C', 'A'],
['C', 'C', 'C'], ['C', 'C', 'C'], ['C', 'C', 'C'], ['C', 'B', 'A']]
monty.fit(data, weights=[1, 1, 3, 3, 1, 1, 3, 7, 1, 1, 1, 1])
assert_equal(monty.log_probability(('A', 'A', 'A')),
monty.log_probability(('A', 'A', 'C')))
assert_equal(monty.log_probability(('A', 'A', 'A')),
monty.log_probability(('A', 'A', 'B')))
assert_equal(monty.log_probability(('B', 'A', 'A')),
monty.log_probability(('B', 'A', 'C')))
assert_equal(monty.log_probability(('B', 'B', 'A')), float("-inf"))
assert_equal(monty.log_probability(('C', 'C', 'B')), float("-inf"))
blanket = set()
for n in node.parents:
blanket.add(n)
for n in node.childeren:
blanket.add(n)
for parN in n.parents:
if n != node:
blanket.add(parN)
return blanket
first = DiscreteDistribution({1: 1. / 2, 0: 1. / 2})
second = DiscreteDistribution({1: 1. / 2, 0: 1. / 2})
mainNode = ConditionalProbabilityTable(
[[1, 1, 1, 0.4], [1, 1, 0, 0.6], [1, 0, 1, 0.9], [1, 0, 0, 0.1],
[0, 1, 1, 0.9], [0, 1, 0, 0.1], [0, 0, 1, 0.4], [0, 0, 0, 0.6]],
[first, second])
four = ConditionalProbabilityTable(
[[1, 1, 0.4], [1, 0, 0.6], [0, 0, 0.6], [0, 1, 0.4]], [mainNode])
five = ConditionalProbabilityTable(
[[1, 1, 0.4], [1, 0, 0.6], [0, 0, 0.6], [0, 1, 0.4]], [mainNode])
s1 = BNode(first, False, name="first")
s2 = BNode(second, False, name="second")
s3 = BNode(mainNode, True, name="mainNode")
s4 = BNode(four, True, name="dd")
s5 = BNode(five, True, name='ee')
rng = RandomNumberGenerator()
rng.add_edge(s1, s3)
print(t)
return t.values.tolist()
def singleVariable(target):
oneValue = df[target].value_counts()[1] / len(df) or 0
return {0: 1 - oneValue, 1: oneValue}
anxiety = DiscreteDistribution(singleVariable("Anxiety"))
peer_pressure = DiscreteDistribution(singleVariable("Peer_Pressure"))
genetics = DiscreteDistribution(singleVariable("Genetics"))
allergy = DiscreteDistribution(singleVariable("Allergy"))
smoking = ConditionalProbabilityTable(
buildCpt("Smoking", ["Anxiety", "Peer_Pressure"]),
[anxiety, peer_pressure])
lung_cancer = ConditionalProbabilityTable(
buildCpt("Lung_cancer", ["Smoking", "Genetics"]), [smoking, genetics])
yellow_fingers = ConditionalProbabilityTable(
buildCpt("Yellow_Fingers", ["Smoking"]), [smoking])
attention_disorder = ConditionalProbabilityTable(
buildCpt("Attention_Disorder", ["Genetics"]), [genetics])
coughing = ConditionalProbabilityTable(
buildCpt("Coughing", ["Allergy", "Lung_cancer"]), [allergy, lung_cancer])
fatigue = ConditionalProbabilityTable(
buildCpt("Fatigue", ["Lung_cancer", "Coughing"]), [lung_cancer, coughing])
car_accident = ConditionalProbabilityTable(
buildCpt("Car_Accident", ["Fatigue", "Attention_Disorder"]),
[fatigue, attention_disorder],
)
condProbDict.append([j, k, val])
return condProbDict
arr = returnConditionalProbability(df, 'Location', 'Ashwin')
arr
arr = returnConditionalProbability(df, 'Toss', 'Bat')
arr
arr = returnConditionalProbability(df, 'Bat', 'Result')
arr
location = DiscreteDistribution(returnPriorProbability(df, 'Location'))
toss = DiscreteDistribution(returnPriorProbability(df, 'Toss'))
ashwin = ConditionalProbabilityTable(
returnConditionalProbability(df, 'Location', 'Ashwin'), [location])
batting = ConditionalProbabilityTable(
returnConditionalProbability(df, 'Toss', 'Bat'), [toss])
result = ConditionalProbabilityTable(
returnConditionalProbability(df, 'Bat', 'Result'), [batting])
sLocation = State(location, name="Location")
sToss = State(toss, name="Toss")
sBatting = State(batting, name="Batting")
sAshwin = State(ashwin, name="Ashwin")
sResult = State(result, name="Result")
# Create the Bayesian network object with a useful name
model = BayesianNetwork("Ashwin Playing Problem")
# Add the three states to the network