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 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 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 __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 __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 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 pomegranate_User_pref():
door_lock = DiscreteDistribution({'True': 0.7, 'False': 0.3})
thermostate = ConditionalProbabilityTable(
[['True', 'True', 0.2], ['True', 'False', 0.8],
['False', 'True', 0.01], ['False', 'False', 0.99]], [door_lock])
clock_alarm = DiscreteDistribution({'True': 0.8, 'False': 0.2})
light = ConditionalProbabilityTable(
[['True', 'True', 'True', 0.96], ['True', 'True', 'False', 0.04],
['True', 'False', 'True', 0.89], ['True', 'False', 'False', 0.11],
['False', 'True', 'True', 0.96], ['False', 'True', 'False', 0.04],
['False', 'False', 'True', 0.89], ['False', 'False', 'False', 0.11]],
[door_lock, clock_alarm])
coffee_maker = ConditionalProbabilityTable(
[['True', 'True', 0.92], ['True', 'False', 0.08],
['False', 'True', 0.03], ['False', 'False', 0.97]], [clock_alarm])
window = ConditionalProbabilityTable(
[['True', 'True', 0.885], ['True', 'False', 0.115],
['False', 'True', 0.04], ['False', 'False', 0.96]], [thermostate])
s0_door_lock = State(door_lock, name="door_lock")
s1_clock_alarm = State(clock_alarm, name="clock_alarm")
s2_light = State(light, name="light")
s3_coffee_maker = State(coffee_maker, name="coffee_maker")
s4_thermostate = State(thermostate, name="thermostate")
s5_window = State(window, name="Window")
network = BayesianNetwork("User_pref")
network.add_nodes(s0_door_lock, s1_clock_alarm, s2_light, s3_coffee_maker,
s4_thermostate, s5_window)
network.add_edge(s0_door_lock, s2_light)
network.add_edge(s0_door_lock, s4_thermostate)
network.add_edge(s1_clock_alarm, s3_coffee_maker)
network.add_edge(s1_clock_alarm, s2_light)
network.add_edge(s4_thermostate, s5_window)
network.bake()
return network
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 __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
class User_model:
def __init__(self, is_gen_task, n_alter_dev_per_func):
self.is_gen_task = is_gen_task
self.n_alter_dev_per_func = n_alter_dev_per_func
self.task_dict = {}
# BN
self.BN_node_orders = []
self.devices = None
self.nodes = None
self.func_alter_devices = None
def build_model(self, req_task_len):
# 1,2 are based on montcarlo experimnet for tasklen(2 to 10)
# which return a DAG with less than 100 triels.
#1-req_task_len is 20% of total fucntions.
n_nodes = 5 * req_task_len
#2- edges three times the task len
n_edges = req_task_len * 3
min_dev_caps = 2
# number of funcitons for each device
self.devices, self.nodes, self.func_alter_devices = get_dev_funcs(n_nodes, \
min_dev_caps, self.n_alter_dev_per_func )
# pprint(self.func_alter_devices,width=1 )
rand_dag = RandomDAG(self.nodes, n_edges)
DAG, child_parent = rand_dag.get_custom_DAG(req_task_len)
# print("Child_parents returns by custom DAG: ")
# pprint(child_parent, width=1)
for f in rand_dag.dag_longest_path(DAG):
self.task_dict[f] = ''
# check if we get the task length the at we want
for f in self.task_dict.keys():
func_devices = self.func_alter_devices[f]
self.task_dict[f] = random.choice(func_devices)
self.task_fucs = self.task_dict.keys()
# print(self.task_dict)
self.network = self.get_BN(DAG, child_parent)
self.network.bake()
def get_score(self, cand_list):
can_dev = self.build_BN_query(cand_list)
# try:
return self.network.probability(can_dev),
def build_BN_query(self, cand_list):
# first cand_list for first func in task
can_dev = [None for f in self.nodes]
# the order of nodes and cand_list should be same
for f, d in zip(self.task_fucs, cand_list):
f_idx = self.BN_node_orders.index(f)
can_dev[f_idx] = d
return can_dev
def get_nodes_prob_dist(self, node_without_parents, child_parent):
node_prob_dict = {}
for node in node_without_parents:
n_alters = len(self.func_alter_devices[node])
dist = {}
# node not in the user preference nodes
# give random probability for all
if node not in self.task_dict.keys():
p = np.random.random(n_alters)
p /= p.sum()
# now the sum of p is 1
# randomly map p to alter devices
dist = dict(zip(self.func_alter_devices[node], p))
else: # set max prob to the perfered alter
pref_alter = self.task_dict[node]
x = 1.7 / n_alters
y = 1.0 / len(self.task_dict)
maxp_for_best_alter = pow(x, y)
dist[pref_alter] = maxp_for_best_alter
alt_list = list(self.func_alter_devices[node])
alt_list.remove(pref_alter)
# generate random prob for the rest of alter
if n_alters == 2:
dist.update(dict(zip(alt_list, [1 - maxp_for_best_alter])))
# print([1.0-maxp_for_best_alter])
else:
rand_rest = np.random.random(n_alters - 1)
# to make the maxp+sum(rand_rest) = 1
rand_prob = [
e / sum(rand_rest) * maxp_for_best_alter
for e in rand_rest
]
#np.delete(p, np.amax(p))
dist.update(dict(zip(alt_list, rand_prob)))
# save node with its prob
node_prob_dict[node] = dist
# these nodes have parents, generate CPT for them
for node, parent_lst in child_parent.items():
# parents + this node condProbTable
condProbTable = self.getCondProbTable(node, parent_lst)
# save node with its prob
node_prob_dict[node] = condProbTable
# print("child node: ", node, " table:", condProbTable)
return node_prob_dict
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 get_permutation_groups(self, parent_node_lst):
# print("Parents,node", parent_node_lst)
alter_dev = []
for n in parent_node_lst:
alter_dev.append(self.func_alter_devices[n])
# list(range(n_att))
# print("dev for all ", alter_dev)
alter_perm = itertools.product(*alter_dev)
# print("alter_perm:", alter_perm)
permutation = list(dict(zip(parent_node_lst, x)) for x in alter_perm)
# print("permutation")
# print(permutation)
# Gruop the permutation of node alter node
n_func_dev = len(self.func_alter_devices[parent_node_lst[-1]])
n_prob_groups = int(len(permutation) / n_func_dev)
perm_groups = [[] for i in range(n_prob_groups)]
c = 0
for perm in permutation:
# add to the begining
perm_groups[c // n_func_dev].append(perm)
c += 1
return perm_groups
def getCondProbTable(self, node, parent_lst):
parent_node_lst = []
parent_node_lst.extend(parent_lst)
parent_node_lst.append(node)
perm_groups_prob = self.get_permutation_groups(parent_node_lst)
condProbTable = []
n_func_dev = len(self.func_alter_devices[node])
#p^(1/N)
maxp_for_best_alter = pow(1.7 / n_func_dev, 1 / len(self.task_dict))
if maxp_for_best_alter < 0.2:
maxp_for_best_alter = 0.2
if self.is_gen_task:
# check if this child_parent or indp node are in the user prefered devices
intersect_dict = {k: v for k, v in self.task_dict.items() \
if k in parent_node_lst}
#print("intersect_dict:", intersect_dict)
# for each permutation generate prob such that the sum of each node CDP is = 1
for perm_group_prob in perm_groups_prob:
if self.is_gen_task and len(intersect_dict) > 1 and \
[True for j in range(n_func_dev) \
if intersect_dict.items() <= perm_group_prob[j].items()]:
# print(intersect_dict)
# generate p such that one value is
rem_alt = n_func_dev - 1
rest_prob = np.random.random(rem_alt)
rest_prob /= sum(rest_prob)
rest_prob *= (1 - maxp_for_best_alter)
# the sum of maxp_for_best_alter and rest_prob = 1
for j in range(n_func_dev):
# alter_idx = i * n_att + j
condProbRow = list(perm_group_prob[j].values())
if intersect_dict.items() <= perm_group_prob[j].items():
# print("Best candidate ", perm_group_prob[j], " prob:", maxp_for_best_alter)
condProbRow.append(maxp_for_best_alter)
else:
rem_alt -= 1
#print("NOT candidate ", perm_group_prob[j], " prob:", rest_prob[rem_alt])
condProbRow.append(rest_prob[rem_alt])
condProbTable.append(condProbRow)
else:
# to gurantee best alter, no others should have prob> maxp
a = np.random.random(n_func_dev)
a /= a.sum()
while self.is_gen_task and np.amax(a) >= maxp_for_best_alter:
a = np.random.random(n_func_dev)
a /= a.sum()
# to make sum of alter prob = 1
for j in range(n_func_dev):
condProbRow = list(perm_group_prob[j].values())
condProbRow.append(a[j])
#print(condProbRow)
condProbTable.append(condProbRow)
return condProbTable
states['Peer_Pressure'] = State(Peer_Pressure, name="Peer_Pressure")
states['Smoking'] = State(Smoking, name="Smoking")
states['Yellow_Fingers'] = State(Yellow_Fingers, name="Yellow_Fingers")
states['Genetics'] = State(Genetics, name="Genetics")
states['Lung_cancer'] = State(Lung_cancer, name="Lung_cancer")
states['Attention_Disorder'] = State(Attention_Disorder, name="Attention_Disorder")
states['Allergy'] = State(Allergy, name="Allergy")
states['Coughing'] = State(Coughing, name="Coughing")
states['Born_an_Even_Day'] = State(Born_an_Even_Day, name="Born_an_Even_Day")
states['Fatigue'] = State(Fatigue, name="Fatigue")
states['Car_Accident' ] = State(Car_Accident, name="Car_Accident")
network = BayesianNetwork("Monty hall problem")
network.add_states(*states.values())
network.add_edge(states["Peer_Pressure"],states["Smoking"])
network.add_edge(states["Anxiety"],states["Smoking"])
network.add_edge(states["Smoking"],states["Yellow_Fingers"])
network.add_edge(states["Genetics"],states["Lung_cancer"])
network.add_edge(states["Smoking"],states["Lung_cancer"])
network.add_edge(states["Genetics"],states["Attention_Disorder"])
network.add_edge(states['Lung_cancer'], states["Coughing"])
network.add_edge(states['Allergy'], states["Coughing"])
network.add_edge(states['Coughing'], states["Fatigue"])
network.add_edge(states['Lung_cancer'], states["Fatigue"])
network.add_edge(states["Fatigue"], states["Car_Accident"])
network.add_edge(states["Attention_Disorder"], states["Car_Accident"])
import ast
network.bake()
beliefs = network.predict_proba({"Genetics":"T"},max_iterations=100000)
# print(beliefs)
["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],
["heavy", "no", "on time", 0.5],
["heavy", "no", "delayed", 0.5],
], [rain.distribution, maintenance.distribution]),
name="train")
# Appointment node is conditional on train
appointment = Node(ConditionalProbabilityTable(
[["on time", "attend", 0.9], ["on time", "miss", 0.1],
["delayed", "attend", 0.6], ["delayed", "miss", 0.4]],
[train.distribution]),
name="appointment")
# Create a bayesian network and add the states
model = BayesianNetwork()
model.add_states(rain, maintenance, train, appointment)
# Add edges connecting nodes
model.add_edge(rain, maintenance)
model.add_edge(rain, train)
model.add_edge(maintenance, train)
model.add_edge(train, appointment)
# Finalize model
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, n_nodes, n_alters, n_edges):
# 1 Build BN DAG structure
DAG, child_parent = RandomDAG().random_dag(n_nodes, n_edges)
for a, bs in DAG.edge.items():
for b in bs.keys():
print(a, "->", b)
print("Key node, value: parents",child_parent)
# 2 Build BN probability model
# 2.1 get probabilityDist or conditional prob table
node_prob_dict = {}
# these nodes have parents, generate CPT for them
for node, parent_lst in child_parent.items():
# parents + this node condProbTable
condProbTable = self.getCondProbTable(len(parent_lst)+1, n_alters)
# save node with its prob
node_prob_dict[str(node)] = condProbTable
#print("Conditional Probability Table: \n", condProbTable)
nodes_list = list(range(n_nodes))
node_with_parent_lst = child_parent.keys()
node_without_parents = [e for e in nodes_list if e not in node_with_parent_lst]
# these nodes have no parents so create random prob for them only no conditional here
for node in node_without_parents:
p = np.random.random(n_alters)
p /= p.sum()
dist = {}
for j in range(n_alters):
dist[j] = p[j]
# save node with its prob
node_prob_dict[str(node)] = dist
#print("Root node: ", node, " dist: ", dist)
# 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)
for node in node_without_parents:
prob_dist = node_prob_dict[str(node)]
node_dist = DiscreteDistribution(prob_dist)
nodes_dist[node] = node_dist
nodes_state[node] = State(node_dist, name = str(node))
# remove from nodes_list
nodes_list.remove(node)
# rest of the node should have parents
count = 100
while len(nodes_list) > 0 and count > 0:
count -= 1
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 nodes_list:
node_dist = ConditionalProbabilityTable(node_prob_dict[str(node)] \
, [nodes_dist[i] for i in parent_lst ])
nodes_dist[node] = node_dist
nodes_state[node] = State(node_dist, name = str(node))
# remove from the node_list
nodes_list.remove(node)
if not nodes_list:
print("States created for all nodes!")
# 3 Create BN and add the nodes_state
network = BayesianNetwork("User_pref")
for node, state in nodes_state.items():
network.add_node(state)
print("Network has ", network.node_count() , " nodes")
# 4 Link nodes with edges using nodes_state and DAG.edge
for a, bs in DAG.edge.items():
for b in bs.keys():
network.add_edge(nodes_state[a], nodes_state[b])
print("Network has ", network.edge_count(), " edges")
return network
sAllergy = Node(allergy, name="Allergy")
model = BayesianNetwork("Smoking Risk")
model.add_nodes(
sAnxiety,
sPeerPressure,
sSmoking,
sGenetics,
sLungCancer,
sAllergy,
sCoughing,
sFatigue,
sAttentionDisorder,
sCarAccident,
)
model.add_edge(sAnxiety, sSmoking)
model.add_edge(sPeerPressure, sSmoking)
model.add_edge(sSmoking, sLungCancer)
model.add_edge(sGenetics, sLungCancer)
model.add_edge(sGenetics, sAttentionDisorder)
model.add_edge(sAllergy, sCoughing)
model.add_edge(sLungCancer, sCoughing)
model.add_edge(sCoughing, sFatigue)
model.add_edge(sLungCancer, sFatigue)
model.add_edge(sFatigue, sCarAccident)
model.add_edge(sAttentionDisorder, sCarAccident)
model.bake()
prediction = model.predict_proba({})
states = [
"Anxiety",
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()
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
model.add_states(sLocation, sToss, sBatting, sAshwin, sResult)
model.add_edge(sLocation, sAshwin)
model.add_edge(sToss, sBatting)
model.add_edge(sBatting, sResult)
model.bake()
model.predict_proba([None, None, '2nd', 'Y', 'won'])[1]
model.predict_proba([None, None, '2nd', 'N', 'won'])[0]
model.predict_proba([None, None, '2nd', 'Y', 'lost'])[1]
model.predict_proba([None, None, '2nd', 'N', 'lost'])[0]
