def sample_dag(dag, num):
#zzz this loses disconnected nodes!!!
# bayesmod = BayesianModel(dag.edges())
# bayesmod = BayesianModel(dag)
bayesmod = BayesianModel()
bayesmod.add_nodes_from(dag.nodes())
bayesmod.add_edges_from(dag.edges())
tab_cpds = []
cards = {node: len(dag.node[node]['cpd']) for node in dag.nodes()}
for node in dag.nodes():
parents = dag.predecessors(node)
cpd = dag.node[node]['cpd']
if parents:
parent_cards = [cards[par] for par in parents]
logging.debug("TablularCPD({}, {}, {}, {}, {})".format(
node, cards[node], cpd, parents, parent_cards))
tab_cpds.append(
TabularCPD(node, cards[node], cpd, parents, parent_cards))
else:
logging.debug("TablularCPD({}, {}, {})".format(
node, cards[node], cpd))
tab_cpds.append(TabularCPD(node, cards[node], cpd))
logging.debug("cpds add: {}".format(tab_cpds))
print "model variables:", bayesmod.nodes()
for tab_cpd in tab_cpds:
print "cpd variables:", tab_cpd.variables
bayesmod.add_cpds(*tab_cpds)
logging.debug("cpds get: {}".format(bayesmod.get_cpds()))
inference = BayesianModelSampling(bayesmod)
logging.debug("generating data")
recs = inference.forward_sample(size=num, return_type='recarray')
return recs
from pgmpy.models.BayesianModel import BayesianModel
from pgmpy.factors.discrete import TabularCPD
from pgmpy.sampling import BayesianModelSampling
student = BayesianModel([('diff', 'grade'), ('intel', 'grade')])
cpd_d = TabularCPD('diff', 2, [[0.6], [0.4]])
cpd_i = TabularCPD('intel', 2, [[0.7], [0.3]])
cpd_g = TabularCPD('grade', 3, [[0.3, 0.05, 0.9, 0.5], [0.4, 0.25,0.08, 0.3], [0.3, 0.7, 0.02, 0.2]],['intel', 'diff'], [2, 2])
student.add_cpds(cpd_d, cpd_i, cpd_g)
inference = BayesianModelSampling(student)
print inference.forward_sample(size=3, return_type='recarray')
from pgmpy.sampling import BayesianModelSampling
from pgmpy.inference import VariableElimination
burglary = BayesianModel([('Burglary', 'Alarm'), ('Earthquake', 'Alarm'),
('Alarm', 'Johncalls'), ('Alarm', 'Marycalls')])
cpd_burgary = TabularCPD('Burglary', 2, [[0.001], [0.999]])
cpd_earthquake = TabularCPD('Earthquake', 2, [[0.002], [0.998]])
cpd_alarm = TabularCPD('Alarm', 2,
[[0.99, 0.71, 0.06, 0.05], [0.01, 0.29, 0.94, 0.95]],
['Burglary', 'Earthquake'], [2, 2])
cpd_johncall = TabularCPD('Johncalls', 2, [[0.95, 0.1], [0.05, 0.90]],
['Alarm'], [2])
cpd_marrycall = TabularCPD('Marycalls', 2, [[0.99, 0.30], [0.01, 0.70]],
['Alarm'], [2])
burglary.add_cpds(cpd_burgary, cpd_earthquake, cpd_alarm, cpd_johncall,
cpd_marrycall)
for cpd in burglary.get_cpds():
print(cpd)
#######################################################################
"""inference using variable elimination"""
inference = VariableElimination(burglary)
alarm = inference.query(['Alarm'], {'Johncalls': 0})
print(alarm['Alarm'])
##############################################################
"""inference using likelihood weighting sampling"""
inference = BayesianModelSampling(burglary)
evidence = [State('Johncalls', 0)]
parentsCardList = {}
for node in nodes:
if parents.has_key(node):
tempParentCardList = []
for parent in parents[node]:
tempParentCardList.append(len(cpds[parent]))
parentsCardList[node] = tempParentCardList
print("Adding Tabular CPDs to model")
for node in nodes:
try:
if parents.has_key(node):
model.add_cpds(
TabularCPD(node, variableCard[node], cpds[node],
parents[node], parentsCardList[node]))
else:
model.add_cpds(TabularCPD(node, variableCard[node],
cpds[node]))
except Exception as e:
tempException2 = 0
#print("Tabular cpds added to model")
print "Creating samples using Bayesian model forward Sampling"
inference = BayesianModelSampling(model)
normalSamples = inference.forward_sample(size=5000,
return_type='dataframe')
#print "length ", normalSamples.shape
2, [[0.3, 0.4], [0.7, 0.6]],
evidence=['A'],
evidence_card=[2])
cpd_d = TabularCPD('D',
3, [[0.5, 0.3, 0.1], [0.4, 0.4, 0.8], [0.1, 0.3, 0.1]],
evidence=['B'],
evidence_card=[3])
cpd_e = TabularCPD('E',
2, [[0.3, 0.5, 0.2], [0.7, 0.5, 0.8]],
evidence=['B'],
evidence_card=[3])
cpd_f = TabularCPD('F',
3, [[0.3, 0.6], [0.5, 0.2], [0.2, 0.2]],
evidence=['C'],
evidence_card=[2])
model.add_cpds(cpd_a, cpd_b, cpd_c, cpd_d, cpd_e, cpd_f)
from pgmpy.sampling import BayesianModelSampling
# sample data from BN
inference = BayesianModelSampling(model)
df_data = inference.forward_sample(size=10000, return_type='dataframe')
print(df_data)
from pgmpy.estimators import TreeSearch
# learn graph structure
est = TreeSearch(df_data, root_node="A")
dag = est.estimate(estimator_type="chow-liu")
nx.draw_circular(dag,
with_labels=True,