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
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)]
sample = inference.likelihood_weighted_sample(evidence, 2)
print(sample)
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,
arrowsize=30,
node_size=800,
alpha=0.3,
font_weight='bold')
plt.savefig('fig2.png', bbox_inches='tight')
plt.show()
from pgmpy.estimators import BayesianEstimator
# there are many choices of parametrization, here is one example
model = BayesianModel(dag.edges())
model.fit(df_data,
estimator=BayesianEstimator,
prior_type='dirichlet',
pseudo_counts=0.1)
print(model.get_cpds())