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 __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 __get_symptom_distributions_and_states(self, known_symptoms: List):
symptom_distributions = list()
symptom_states = list()
for (
symptom,
probability,
not_symptom,
not_probability,
) in known_symptoms:
symptom_distribution = DiscreteDistribution({
"1":
float(probability),
"0":
float(not_probability)
})
symptom_distributions.append(symptom_distribution)
symptom_states.append((Node(symptom_distribution, name=symptom)))
return symptom_distributions, symptom_states
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 __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
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
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],
)
sAnxiety = Node(anxiety, name="Anxiety")
sPeerPressure = Node(peer_pressure, name="Peer_Pressure")
sSmoking = Node(smoking, name="Smoking")
sGenetics = Node(genetics, name="Genetics")
sLungCancer = Node(lung_cancer, name="Lung_cancer")
sYellowFingers = Node(yellow_fingers, name="Yellow_Fingers")
sAttentionDisorder = Node(attention_disorder, name="Attention_Disorder")
sCoughing = Node(coughing, name="Coughing")
sFatigue = Node(fatigue, name="Fatigue")
sCarAccident = Node(car_accident, name="Car_Accident")
sAllergy = Node(allergy, name="Allergy")
model = BayesianNetwork("Smoking Risk")
model.add_nodes(
sAnxiety,
sPeerPressure,
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],