def test_easy_shape(self):
n1 = DiscreteNode("Some Node", [True, False])
n2 = DiscreteNode("Second Node" , [True, False])
s = n1.get_cpd().multiplication(n2.get_cpd())
self.assertEqual(s.table.shape, (2,2));
s = n1.get_cpd().multiplication(n1.get_cpd())
self.assertEqual(s.table.shape,(2,))
def test_complicated_multi(self):
n1 = DiscreteNode("Some Node", [True, False])
n2 = DiscreteNode("Second Node" , [True, False,"noIdea"])
cpt1 = numpy.array([2,3])
cpt2 = numpy.array([5,7,9])
n1.set_probability_table(cpt1,[n1])
n2.set_probability_table(cpt2,[n2])
c3 = n1.get_cpd().multiplication(n2.get_cpd())
c3 = n1.get_cpd().multiplication(c3)
cptN = numpy.array([[20, 28, 36],[45, 63, 81]])
numpy.testing.assert_array_equal(c3.table,cptN)
def test_easy_values(self):
n1 = DiscreteNode("Some Node", [True, False])
n2 = DiscreteNode("Second Node" , [True, False])
cpt1 = numpy.array([2,3])
cpt2 = numpy.array([5,7])
n1.set_probability_table(cpt1,[n1])
n2.set_probability_table(cpt2,[n2])
s = n1.get_cpd().multiplication(n2.get_cpd())
cptN = numpy.array([[10,14],[15,21]])
numpy.testing.assert_array_equal(s.table,cptN)
self.assertEqual(s.variables[0],n1)
def test_easy_marginalize(self):
n1 = DiscreteNode("Some Node", [True, False])
n2 = DiscreteNode("Second Node" , [True, False, "other"])
cpt1 = numpy.array([2,3])
cpt2 = numpy.array([5,7,3])
n1.set_probability_table(cpt1,[n1])
n2.set_probability_table(cpt2,[n2])
s = n1.get_cpd().multiplication(n2.get_cpd())
s =s.marginalization(n2)
print s.table
cptN = numpy.array([30,45])
numpy.testing.assert_array_equal(s.table,cptN)
self.assertEqual(s.variables[0],n1)
burglary.set_probability_table(burglary_cpt, [burglary])
alarm_cpt=numpy.array([[0.8,0.15,0.05],[0.05,0.9,0.05]])
alarm.set_probability_table(alarm_cpt, [burglary,alarm])
#Construct a Markov Chain by sampling states from this Network
transition_model = GibbsTransitionModel()
mcs = MarkovChainSampler()
initial_state={burglary:"Safe",alarm:"Silent"}
chain = mcs.generateMarkovChain(bn, 5000, transition_model, initial_state)
#for c in chain:
# print c
pt = ProbabilityTable()
pt.add_variable(burglary)
pt.add_variable(alarm)
pt.to_jpt_by_states(chain)
print "----joint-probability----"
print pt
print "----burglary----"
print pt.marginalization(alarm)
print "----alarm----"
print pt.division(burglary.get_cpd())
bn.draw()
