class TestBayesianModelCPD(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('d', 'g'), ('i', 'g'), ('g', 'l'),
('i', 's')])
def test_active_trail_nodes(self):
self.assertEqual(sorted(self.G.active_trail_nodes('d')),
['d', 'g', 'l'])
self.assertEqual(sorted(self.G.active_trail_nodes('i')),
['g', 'i', 'l', 's'])
def test_active_trail_nodes_args(self):
self.assertEqual(sorted(self.G.active_trail_nodes('d', observed='g')),
['d', 'i', 's'])
self.assertEqual(sorted(self.G.active_trail_nodes('l', observed='g')),
['l'])
self.assertEqual(
sorted(self.G.active_trail_nodes('s', observed=['i', 'l'])), ['s'])
self.assertEqual(
sorted(self.G.active_trail_nodes('s', observed=['d', 'l'])),
['g', 'i', 's'])
def test_is_active_trail_triplets(self):
self.assertTrue(self.G.is_active_trail('d', 'l'))
self.assertTrue(self.G.is_active_trail('g', 's'))
self.assertFalse(self.G.is_active_trail('d', 'i'))
self.assertTrue(self.G.is_active_trail('d', 'i', observed='g'))
self.assertFalse(self.G.is_active_trail('d', 'l', observed='g'))
self.assertFalse(self.G.is_active_trail('i', 'l', observed='g'))
self.assertTrue(self.G.is_active_trail('d', 'i', observed='l'))
self.assertFalse(self.G.is_active_trail('g', 's', observed='i'))
def test_is_active_trail(self):
self.assertFalse(self.G.is_active_trail('d', 's'))
self.assertTrue(self.G.is_active_trail('s', 'l'))
self.assertTrue(self.G.is_active_trail('d', 's', observed='g'))
self.assertFalse(self.G.is_active_trail('s', 'l', observed='g'))
def test_is_active_trail_args(self):
self.assertFalse(self.G.is_active_trail('s', 'l', 'i'))
self.assertFalse(self.G.is_active_trail('s', 'l', 'g'))
self.assertTrue(self.G.is_active_trail('d', 's', 'l'))
self.assertFalse(self.G.is_active_trail('d', 's', ['i', 'l']))
def test_get_cpds(self):
cpd_d = TabularCPD('d', 2, values=np.random.rand(2, 1))
cpd_i = TabularCPD('i', 2, values=np.random.rand(2, 1))
cpd_g = TabularCPD('g',
2,
values=np.random.rand(2, 4),
evidence=['d', 'i'],
evidence_card=[2, 2])
cpd_l = TabularCPD('l',
2,
values=np.random.rand(2, 2),
evidence=['g'],
evidence_card=[2])
cpd_s = TabularCPD('s',
2,
values=np.random.rand(2, 2),
evidence=['i'],
evidence_card=[2])
self.G.add_cpds(cpd_d, cpd_i, cpd_g, cpd_l, cpd_s)
self.assertEqual(self.G.get_cpds('d').variable, 'd')
def test_get_cpds1(self):
self.model = BayesianModel([('A', 'AB')])
cpd_a = TabularCPD('A', 2, values=np.random.rand(2, 1))
cpd_ab = TabularCPD('AB',
2,
values=np.random.rand(2, 2),
evidence=['A'],
evidence_card=[2])
self.model.add_cpds(cpd_a, cpd_ab)
self.assertEqual(self.model.get_cpds('A').variable, 'A')
self.assertEqual(self.model.get_cpds('AB').variable, 'AB')
def test_add_single_cpd(self):
cpd_s = TabularCPD('s', 2, np.random.rand(2, 2), ['i'], 2)
self.G.add_cpds(cpd_s)
self.assertListEqual(self.G.get_cpds(), [cpd_s])
def test_add_multiple_cpds(self):
cpd_d = TabularCPD('d', 2, values=np.random.rand(2, 1))
cpd_i = TabularCPD('i', 2, values=np.random.rand(2, 1))
cpd_g = TabularCPD('g',
2,
values=np.random.rand(2, 4),
evidence=['d', 'i'],
evidence_card=[2, 2])
cpd_l = TabularCPD('l',
2,
values=np.random.rand(2, 2),
evidence=['g'],
evidence_card=[2])
cpd_s = TabularCPD('s',
2,
values=np.random.rand(2, 2),
evidence=['i'],
evidence_card=[2])
self.G.add_cpds(cpd_d, cpd_i, cpd_g, cpd_l, cpd_s)
self.assertEqual(self.G.get_cpds('d'), cpd_d)
self.assertEqual(self.G.get_cpds('i'), cpd_i)
self.assertEqual(self.G.get_cpds('g'), cpd_g)
self.assertEqual(self.G.get_cpds('l'), cpd_l)
self.assertEqual(self.G.get_cpds('s'), cpd_s)
def test_check_model(self):
cpd_g = TabularCPD('g',
2,
values=np.array([[0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4]]),
evidence=['d', 'i'],
evidence_card=[2, 2])
cpd_s = TabularCPD('s',
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=['i'],
evidence_card=[2])
cpd_l = TabularCPD('l',
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=['g'],
evidence_card=[2])
self.G.add_cpds(cpd_g, cpd_s, cpd_l)
self.assertTrue(self.G.check_model())
def test_check_model1(self):
cpd_g = TabularCPD('g',
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=['i'],
evidence_card=[2])
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_g = TabularCPD('g',
2,
values=np.array([[0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4]]),
evidence=['d', 's'],
evidence_card=[2, 2])
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_g = TabularCPD('g',
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=['l'],
evidence_card=[2])
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_l = TabularCPD('l',
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=['d'],
evidence_card=[2])
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
cpd_l = TabularCPD('l',
2,
values=np.array([[0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4]]),
evidence=['d', 'i'],
evidence_card=[2, 2])
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
cpd_l = TabularCPD('l',
2,
values=np.array(
[[0.2, 0.3, 0.4, 0.6, 0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4, 0.8, 0.7, 0.6, 0.4]]),
evidence=['g', 'd', 'i'],
evidence_card=[2, 2, 2])
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
def test_check_model2(self):
cpd_s = TabularCPD('s',
2,
values=np.array([[0.5, 0.3], [0.8, 0.7]]),
evidence=['i'],
evidence_card=2)
self.G.add_cpds(cpd_s)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_s)
cpd_g = TabularCPD('g',
2,
values=np.array([[0.2, 0.3, 0.4, 0.6],
[0.3, 0.7, 0.6, 0.4]]),
evidence=['d', 'i'],
evidence_card=[2, 2])
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_l = TabularCPD('l',
2,
values=np.array([[0.2, 0.3], [0.1, 0.7]]),
evidence=['g'],
evidence_card=[2])
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
def tearDown(self):
del self.G
class TestDirectedGraphCPDOperations(unittest.TestCase):
def setUp(self):
self.graph = BayesianModel()
def test_add_single_cpd(self):
cpd = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd)
self.assertListEqual(self.graph.get_cpds(), [cpd])
def test_add_multiple_cpds(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertListEqual(self.graph.get_cpds(), [cpd1, cpd2, cpd3])
def test_remove_single_cpd(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds(cpd1)
self.assertListEqual(self.graph.get_cpds(), [cpd2, cpd3])
def test_remove_multiple_cpds(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds(cpd1, cpd3)
self.assertListEqual(self.graph.get_cpds(), [cpd2])
def test_remove_single_cpd_string(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds('diff')
self.assertListEqual(self.graph.get_cpds(), [cpd2, cpd3])
def test_remove_multiple_cpds_string(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds('diff', 'grade')
self.assertListEqual(self.graph.get_cpds(), [cpd2])
def test_get_cpd_for_node(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertEqual(self.graph.get_cpds('diff'), cpd1)
self.assertEqual(self.graph.get_cpds('intel'), cpd2)
self.assertEqual(self.graph.get_cpds('grade'), cpd3)
def test_get_cpd_raises_error(self):
cpd1 = TabularCPD('diff', 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD('grade',
2,
values=np.random.rand(2, 4),
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertRaises(ValueError, self.graph.get_cpds, 'sat')
def tearDown(self):
del self.graph
class TestBayesianModelMethods(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('a', 'd'), ('b', 'd'), ('d', 'e'),
('b', 'c')])
self.G1 = BayesianModel([('diff', 'grade'), ('intel', 'grade')])
diff_cpd = TabularCPD('diff', 2, values=[[0.2], [0.8]])
intel_cpd = TabularCPD('intel', 3, values=[[0.5], [0.3], [0.2]])
grade_cpd = TabularCPD('grade',
3,
values=[[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'],
evidence_card=[2, 3])
self.G1.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.G2 = BayesianModel([('d', 'g'), ('g', 'l'), ('i', 'g'),
('i', 'l')])
def test_moral_graph(self):
moral_graph = self.G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('a', 'd'), ('b', 'c'),
('d', 'b'), ('e', 'd')]
or (edge[1], edge[0]) in [('a', 'b'), ('a', 'd'),
('b', 'c'), ('d', 'b'),
('e', 'd')])
def test_moral_graph_with_edge_present_over_parents(self):
G = BayesianModel([('a', 'd'), ('d', 'e'), ('b', 'd'), ('b', 'c'),
('a', 'b')])
moral_graph = G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('c', 'b'), ('d', 'a'),
('d', 'b'), ('d', 'e')]
or (edge[1], edge[0]) in [('a', 'b'), ('c', 'b'),
('d', 'a'), ('d', 'b'),
('d', 'e')])
def test_get_ancestors_of_success(self):
ancenstors1 = self.G2._get_ancestors_of('g')
ancenstors2 = self.G2._get_ancestors_of('d')
ancenstors3 = self.G2._get_ancestors_of(['i', 'l'])
self.assertEqual(ancenstors1, {'d', 'i', 'g'})
self.assertEqual(ancenstors2, {'d'})
self.assertEqual(ancenstors3, {'g', 'i', 'l', 'd'})
def test_get_ancestors_of_failure(self):
self.assertRaises(ValueError, self.G2._get_ancestors_of, 'h')
def test_local_independencies(self):
self.assertEqual(self.G.local_independencies('a'),
Independencies(['a', ['b', 'c']]))
self.assertEqual(self.G.local_independencies('c'),
Independencies(['c', ['a', 'd', 'e'], 'b']))
self.assertEqual(self.G.local_independencies('d'),
Independencies(['d', 'c', ['b', 'a']]))
self.assertEqual(self.G.local_independencies('e'),
Independencies(['e', ['c', 'b', 'a'], 'd']))
self.assertEqual(self.G.local_independencies('b'),
Independencies(['b', 'a']))
self.assertEqual(self.G1.local_independencies('grade'),
Independencies())
def test_get_independencies(self):
chain = BayesianModel([('X', 'Y'), ('Y', 'Z')])
self.assertEqual(chain.get_independencies(),
Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
fork = BayesianModel([('Y', 'X'), ('Y', 'Z')])
self.assertEqual(fork.get_independencies(),
Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
collider = BayesianModel([('X', 'Y'), ('Z', 'Y')])
self.assertEqual(collider.get_independencies(),
Independencies(('X', 'Z'), ('Z', 'X')))
def test_is_imap(self):
val = [
0.01, 0.01, 0.08, 0.006, 0.006, 0.048, 0.004, 0.004, 0.032, 0.04,
0.04, 0.32, 0.024, 0.024, 0.192, 0.016, 0.016, 0.128
]
JPD = JointProbabilityDistribution(['diff', 'intel', 'grade'],
[2, 3, 3], val)
fac = DiscreteFactor(['diff', 'intel', 'grade'], [2, 3, 3], val)
self.assertTrue(self.G1.is_imap(JPD))
self.assertRaises(TypeError, self.G1.is_imap, fac)
def test_get_immoralities(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertEqual(G.get_immoralities(), {('w', 'x'), ('w', 'z')})
G1 = BayesianModel([('x', 'y'), ('z', 'y'), ('z', 'x'), ('w', 'y')])
self.assertEqual(G1.get_immoralities(), {('w', 'x'), ('w', 'z')})
G2 = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y'),
('w', 'x')])
self.assertEqual(G2.get_immoralities(), {('w', 'z')})
def test_is_iequivalent(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertRaises(TypeError, G.is_iequivalent, MarkovModel())
G1 = BayesianModel([('V', 'W'), ('W', 'X'), ('X', 'Y'), ('Z', 'Y')])
G2 = BayesianModel([('W', 'V'), ('X', 'W'), ('X', 'Y'), ('Z', 'Y')])
self.assertTrue(G1.is_iequivalent(G2))
G3 = BayesianModel([('W', 'V'), ('W', 'X'), ('Y', 'X'), ('Z', 'Y')])
self.assertFalse(G3.is_iequivalent(G2))
def test_copy(self):
model_copy = self.G1.copy()
self.assertEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
self.assertNotEqual(id(self.G1.get_cpds('diff')),
id(model_copy.get_cpds('diff')))
self.G1.remove_cpds('diff')
diff_cpd = TabularCPD('diff', 2, values=[[0.3], [0.7]])
self.G1.add_cpds(diff_cpd)
self.assertNotEqual(self.G1.get_cpds('diff'),
model_copy.get_cpds('diff'))
self.G1.remove_node('intel')
self.assertNotEqual(sorted(self.G1.nodes()),
sorted(model_copy.nodes()))
self.assertNotEqual(sorted(self.G1.edges()),
sorted(model_copy.edges()))
def test_remove_node(self):
self.G1.remove_node('diff')
self.assertEqual(sorted(self.G1.nodes()), sorted(['grade', 'intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
def test_remove_nodes_from(self):
self.G1.remove_nodes_from(['diff', 'grade'])
self.assertEqual(sorted(self.G1.nodes()), sorted(['intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
self.assertRaises(ValueError, self.G1.get_cpds, 'grade')
def tearDown(self):
del self.G
del self.G1
def __delitem__(self, variable: str) -> None:
super().__delitem__(variable)
try:
BayesianModel.remove_cpds(self.cbn, variable)
except ValueError:
pass
class TestDirectedGraphCPDOperations(unittest.TestCase):
def setUp(self):
self.graph = BayesianModel()
def test_add_single_cpd(self):
cpd = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd)
self.assertListEqual(self.graph.get_cpds(), [cpd])
def test_add_multiple_cpds(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertListEqual(self.graph.get_cpds(), [cpd1, cpd2, cpd3])
def test_remove_single_cpd(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds(cpd1)
self.assertListEqual(self.graph.get_cpds(), [cpd2, cpd3])
def test_remove_multiple_cpds(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds(cpd1, cpd3)
self.assertListEqual(self.graph.get_cpds(), [cpd2])
def test_remove_single_cpd_string(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds('diff')
self.assertListEqual(self.graph.get_cpds(), [cpd2, cpd3])
def test_remove_multiple_cpds_string(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds('diff', 'grade')
self.assertListEqual(self.graph.get_cpds(), [cpd2])
def test_get_cpd_for_node(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertEqual(self.graph.get_cpds('diff'), cpd1)
self.assertEqual(self.graph.get_cpds('intel'), cpd2)
self.assertEqual(self.graph.get_cpds('grade'), cpd3)
def test_get_cpd_raises_error(self):
cpd1 = TabularCPD('diff', 2, np.random.rand(2, 1))
cpd2 = TabularCPD('intel', 2, np.random.rand(2, 1))
cpd3 = TabularCPD('grade', 2, np.random.rand(2, 4),
['diff', 'intel'], [2, 2])
self.graph.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertRaises(ValueError, self.graph.get_cpds, 'sat')
def tearDown(self):
del self.graph
evidence_card=[2, 2])
model.add_cpds(cpd_getting_up_late, cpd_late_for_school)
model.get_cpds()
" [<TabularCPD representing P(rain: 2) at fsjidfsjdfaskdf>, "
" [<TabularCPD representing P(accident: 2) at fsxfgsdfgfsjdfaskdf>, "
" [<TabularCPD representing P(traffic_jam: 2 | rain:2, accident:2) at fsjidf234sjdfaskdf>, "
" [<TabularCPD representing P(long_queues: 2 | traffic_jam:2) at fsjidf234sjdfaskdf>, "
" [<TabularCPD representing P(getting_up_late:2) at fsjidf234sjdfaskdf>, "
" [<TabularCPD representing P(late_for_school: 2 | getting_up_late:2, traffic_jam:2) at fsjidf234sjdfaskdf>, "
# --- Check whether the model and all the associated CPDs are consistent
model.check_model()
" True "
# --- if any wrong/additional cpds
model.remove_cpds('wrong_cpds')
model.get_cpds()
" 'wrong cpd gone' "
-------------- P = P(A,R,J,G,L,Q)
= P(A) P(R) P(J|A,R) P(Q|R) P(L|G,J)
# ----- Active Trail
model.is_active_trail('accident', 'rain')
" False "
model.is_active_trail('accident', 'rain',
observed='traffic_jam')
" True "
class TestBayesianModelCPD(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('d', 'g'), ('i', 'g'), ('g', 'l'),
('i', 's')])
def test_active_trail_nodes(self):
self.assertEqual(sorted(self.G.active_trail_nodes('d')), ['d', 'g', 'l'])
self.assertEqual(sorted(self.G.active_trail_nodes('i')), ['g', 'i', 'l', 's'])
def test_active_trail_nodes_args(self):
self.assertEqual(sorted(self.G.active_trail_nodes('d', observed='g')), ['d', 'i', 's'])
self.assertEqual(sorted(self.G.active_trail_nodes('l', observed='g')), ['l'])
self.assertEqual(sorted(self.G.active_trail_nodes('s', observed=['i', 'l'])), ['s'])
self.assertEqual(sorted(self.G.active_trail_nodes('s', observed=['d', 'l'])), ['g', 'i', 's'])
def test_is_active_trail_triplets(self):
self.assertTrue(self.G.is_active_trail('d', 'l'))
self.assertTrue(self.G.is_active_trail('g', 's'))
self.assertFalse(self.G.is_active_trail('d', 'i'))
self.assertTrue(self.G.is_active_trail('d', 'i', observed='g'))
self.assertFalse(self.G.is_active_trail('d', 'l', observed='g'))
self.assertFalse(self.G.is_active_trail('i', 'l', observed='g'))
self.assertTrue(self.G.is_active_trail('d', 'i', observed='l'))
self.assertFalse(self.G.is_active_trail('g', 's', observed='i'))
def test_is_active_trail(self):
self.assertFalse(self.G.is_active_trail('d', 's'))
self.assertTrue(self.G.is_active_trail('s', 'l'))
self.assertTrue(self.G.is_active_trail('d', 's', observed='g'))
self.assertFalse(self.G.is_active_trail('s', 'l', observed='g'))
def test_is_active_trail_args(self):
self.assertFalse(self.G.is_active_trail('s', 'l', 'i'))
self.assertFalse(self.G.is_active_trail('s', 'l', 'g'))
self.assertTrue(self.G.is_active_trail('d', 's', 'l'))
self.assertFalse(self.G.is_active_trail('d', 's', ['i', 'l']))
def test_get_cpds(self):
cpd_d = TabularCPD('d', 2, np.random.rand(2, 1))
cpd_i = TabularCPD('i', 2, np.random.rand(2, 1))
cpd_g = TabularCPD('g', 2, np.random.rand(2, 4), ['d', 'i'], [2, 2])
cpd_l = TabularCPD('l', 2, np.random.rand(2, 2), ['g'], 2)
cpd_s = TabularCPD('s', 2, np.random.rand(2, 2), ['i'], 2)
self.G.add_cpds(cpd_d, cpd_i, cpd_g, cpd_l, cpd_s)
self.assertEqual(self.G.get_cpds('d').variable, 'd')
def test_get_cpds1(self):
self.model = BayesianModel([('A', 'AB')])
cpd_a = TabularCPD('A', 2, np.random.rand(2, 1))
cpd_ab = TabularCPD('AB', 2, np.random.rand(2, 2), evidence=['A'],
evidence_card=[2])
self.model.add_cpds(cpd_a, cpd_ab)
self.assertEqual(self.model.get_cpds('A').variable, 'A')
self.assertEqual(self.model.get_cpds('AB').variable, 'AB')
def test_add_single_cpd(self):
cpd_s = TabularCPD('s', 2, np.random.rand(2, 2), ['i'], 2)
self.G.add_cpds(cpd_s)
self.assertListEqual(self.G.get_cpds(), [cpd_s])
def test_add_multiple_cpds(self):
cpd_d = TabularCPD('d', 2, np.random.rand(2, 1))
cpd_i = TabularCPD('i', 2, np.random.rand(2, 1))
cpd_g = TabularCPD('g', 2, np.random.rand(2, 4), ['d', 'i'], [2, 2])
cpd_l = TabularCPD('l', 2, np.random.rand(2, 2), ['g'], 2)
cpd_s = TabularCPD('s', 2, np.random.rand(2, 2), ['i'], 2)
self.G.add_cpds(cpd_d, cpd_i, cpd_g, cpd_l, cpd_s)
self.assertEqual(self.G.get_cpds('d'), cpd_d)
self.assertEqual(self.G.get_cpds('i'), cpd_i)
self.assertEqual(self.G.get_cpds('g'), cpd_g)
self.assertEqual(self.G.get_cpds('l'), cpd_l)
self.assertEqual(self.G.get_cpds('s'), cpd_s)
def test_check_model(self):
cpd_g = TabularCPD('g', 2,
np.array([[0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4]]),
['d', 'i'], [2, 2])
cpd_s = TabularCPD('s', 2,
np.array([[0.2, 0.3],
[0.8, 0.7]]),
['i'], 2)
cpd_l = TabularCPD('l', 2,
np.array([[0.2, 0.3],
[0.8, 0.7]]),
['g'], 2)
self.G.add_cpds(cpd_g, cpd_s, cpd_l)
self.assertTrue(self.G.check_model())
def test_check_model1(self):
cpd_g = TabularCPD('g', 2,
np.array([[0.2, 0.3],
[0.8, 0.7]]),
['i'], 2)
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_g = TabularCPD('g', 2,
np.array([[0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4]]),
['d', 's'], [2, 2])
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_g = TabularCPD('g', 2,
np.array([[0.2, 0.3],
[0.8, 0.7]]),
['l'], 2)
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_l = TabularCPD('l', 2,
np.array([[0.2, 0.3],
[0.8, 0.7]]),
['d'], 2)
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
cpd_l = TabularCPD('l', 2,
np.array([[0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4]]),
['d', 'i'], [2, 2])
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
cpd_l = TabularCPD('l', 2,
np.array([[0.2, 0.3, 0.4, 0.6, 0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4, 0.8, 0.7, 0.6, 0.4]]),
['g', 'd', 'i'], [2, 2, 2])
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
def test_check_model2(self):
cpd_s = TabularCPD('s', 2,
np.array([[0.5, 0.3],
[0.8, 0.7]]),
['i'], 2)
self.G.add_cpds(cpd_s)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_s)
cpd_g = TabularCPD('g', 2,
np.array([[0.2, 0.3, 0.4, 0.6],
[0.3, 0.7, 0.6, 0.4]]),
['d', 'i'], [2, 2])
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_l = TabularCPD('l', 2,
np.array([[0.2, 0.3],
[0.1, 0.7]]),
['g'], 2)
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
def tearDown(self):
del self.G
class TestBayesianModelCPD(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([("d", "g"), ("i", "g"), ("g", "l"),
("i", "s")])
self.G2 = DAG([("d", "g"), ("i", "g"), ("g", "l"), ("i", "s")])
def test_active_trail_nodes(self):
self.assertEqual(sorted(self.G2.active_trail_nodes("d")["d"]),
["d", "g", "l"])
self.assertEqual(sorted(self.G2.active_trail_nodes("i")["i"]),
["g", "i", "l", "s"])
self.assertEqual(sorted(self.G2.active_trail_nodes(["d", "i"])["d"]),
["d", "g", "l"])
def test_active_trail_nodes_args(self):
self.assertEqual(
sorted(self.G2.active_trail_nodes(["d", "l"], observed="g")["d"]),
["d", "i", "s"],
)
self.assertEqual(
sorted(self.G2.active_trail_nodes(["d", "l"], observed="g")["l"]),
["l"])
self.assertEqual(
sorted(self.G2.active_trail_nodes("s", observed=["i", "l"])["s"]),
["s"])
self.assertEqual(
sorted(self.G2.active_trail_nodes("s", observed=["d", "l"])["s"]),
["g", "i", "s"],
)
def test_is_active_trail_triplets(self):
self.assertTrue(self.G.is_active_trail("d", "l"))
self.assertTrue(self.G.is_active_trail("g", "s"))
self.assertFalse(self.G.is_active_trail("d", "i"))
self.assertTrue(self.G.is_active_trail("d", "i", observed="g"))
self.assertFalse(self.G.is_active_trail("d", "l", observed="g"))
self.assertFalse(self.G.is_active_trail("i", "l", observed="g"))
self.assertTrue(self.G.is_active_trail("d", "i", observed="l"))
self.assertFalse(self.G.is_active_trail("g", "s", observed="i"))
def test_is_active_trail(self):
self.assertFalse(self.G.is_active_trail("d", "s"))
self.assertTrue(self.G.is_active_trail("s", "l"))
self.assertTrue(self.G.is_active_trail("d", "s", observed="g"))
self.assertFalse(self.G.is_active_trail("s", "l", observed="g"))
def test_is_active_trail_args(self):
self.assertFalse(self.G.is_active_trail("s", "l", "i"))
self.assertFalse(self.G.is_active_trail("s", "l", "g"))
self.assertTrue(self.G.is_active_trail("d", "s", "l"))
self.assertFalse(self.G.is_active_trail("d", "s", ["i", "l"]))
def test_get_cpds(self):
cpd_d = TabularCPD("d", 2, values=np.random.rand(2, 1))
cpd_i = TabularCPD("i", 2, values=np.random.rand(2, 1))
cpd_g = TabularCPD(
"g",
2,
values=np.random.rand(2, 4),
evidence=["d", "i"],
evidence_card=[2, 2],
)
cpd_l = TabularCPD("l",
2,
values=np.random.rand(2, 2),
evidence=["g"],
evidence_card=[2])
cpd_s = TabularCPD("s",
2,
values=np.random.rand(2, 2),
evidence=["i"],
evidence_card=[2])
self.G.add_cpds(cpd_d, cpd_i, cpd_g, cpd_l, cpd_s)
self.assertEqual(self.G.get_cpds("d").variable, "d")
def test_get_cpds1(self):
self.model = BayesianModel([("A", "AB")])
cpd_a = TabularCPD("A", 2, values=np.random.rand(2, 1))
cpd_ab = TabularCPD("AB",
2,
values=np.random.rand(2, 2),
evidence=["A"],
evidence_card=[2])
self.model.add_cpds(cpd_a, cpd_ab)
self.assertEqual(self.model.get_cpds("A").variable, "A")
self.assertEqual(self.model.get_cpds("AB").variable, "AB")
self.assertRaises(ValueError, self.model.get_cpds, "B")
self.model.add_node("B")
self.assertIsNone(self.model.get_cpds("B"))
def test_add_single_cpd(self):
cpd_s = TabularCPD("s", 2, np.random.rand(2, 2), ["i"], [2])
self.G.add_cpds(cpd_s)
self.assertListEqual(self.G.get_cpds(), [cpd_s])
def test_add_multiple_cpds(self):
cpd_d = TabularCPD("d", 2, values=np.random.rand(2, 1))
cpd_i = TabularCPD("i", 2, values=np.random.rand(2, 1))
cpd_g = TabularCPD(
"g",
2,
values=np.random.rand(2, 4),
evidence=["d", "i"],
evidence_card=[2, 2],
)
cpd_l = TabularCPD("l",
2,
values=np.random.rand(2, 2),
evidence=["g"],
evidence_card=[2])
cpd_s = TabularCPD("s",
2,
values=np.random.rand(2, 2),
evidence=["i"],
evidence_card=[2])
self.G.add_cpds(cpd_d, cpd_i, cpd_g, cpd_l, cpd_s)
self.assertEqual(self.G.get_cpds("d"), cpd_d)
self.assertEqual(self.G.get_cpds("i"), cpd_i)
self.assertEqual(self.G.get_cpds("g"), cpd_g)
self.assertEqual(self.G.get_cpds("l"), cpd_l)
self.assertEqual(self.G.get_cpds("s"), cpd_s)
def test_check_model(self):
cpd_g = TabularCPD(
"g",
2,
values=np.array([[0.2, 0.3, 0.4, 0.6], [0.8, 0.7, 0.6, 0.4]]),
evidence=["d", "i"],
evidence_card=[2, 2],
)
cpd_s = TabularCPD(
"s",
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=["i"],
evidence_card=[2],
)
cpd_l = TabularCPD(
"l",
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=["g"],
evidence_card=[2],
)
self.G.add_cpds(cpd_g, cpd_s, cpd_l)
self.assertRaises(ValueError, self.G.check_model)
cpd_d = TabularCPD("d", 2, values=[[0.8, 0.2]])
cpd_i = TabularCPD("i", 2, values=[[0.7, 0.3]])
self.G.add_cpds(cpd_d, cpd_i)
self.assertTrue(self.G.check_model())
def test_check_model1(self):
cpd_g = TabularCPD(
"g",
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=["i"],
evidence_card=[2],
)
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_g = TabularCPD(
"g",
2,
values=np.array([[0.2, 0.3, 0.4, 0.6], [0.8, 0.7, 0.6, 0.4]]),
evidence=["d", "s"],
evidence_card=[2, 2],
)
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_g = TabularCPD(
"g",
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=["l"],
evidence_card=[2],
)
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_l = TabularCPD(
"l",
2,
values=np.array([[0.2, 0.3], [0.8, 0.7]]),
evidence=["d"],
evidence_card=[2],
)
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
cpd_l = TabularCPD(
"l",
2,
values=np.array([[0.2, 0.3, 0.4, 0.6], [0.8, 0.7, 0.6, 0.4]]),
evidence=["d", "i"],
evidence_card=[2, 2],
)
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
cpd_l = TabularCPD(
"l",
2,
values=np.array([
[0.2, 0.3, 0.4, 0.6, 0.2, 0.3, 0.4, 0.6],
[0.8, 0.7, 0.6, 0.4, 0.8, 0.7, 0.6, 0.4],
]),
evidence=["g", "d", "i"],
evidence_card=[2, 2, 2],
)
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
def test_check_model2(self):
cpd_s = TabularCPD(
"s",
2,
values=np.array([[0.5, 0.3], [0.8, 0.7]]),
evidence=["i"],
evidence_card=[2],
)
self.G.add_cpds(cpd_s)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_s)
cpd_g = TabularCPD(
"g",
2,
values=np.array([[0.2, 0.3, 0.4, 0.6], [0.3, 0.7, 0.6, 0.4]]),
evidence=["d", "i"],
evidence_card=[2, 2],
)
self.G.add_cpds(cpd_g)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_g)
cpd_l = TabularCPD(
"l",
2,
values=np.array([[0.2, 0.3], [0.1, 0.7]]),
evidence=["g"],
evidence_card=[2],
)
self.G.add_cpds(cpd_l)
self.assertRaises(ValueError, self.G.check_model)
self.G.remove_cpds(cpd_l)
def tearDown(self):
del self.G
class TestBayesianModelMethods(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([("a", "d"), ("b", "d"), ("d", "e"),
("b", "c")])
self.G1 = BayesianModel([("diff", "grade"), ("intel", "grade")])
diff_cpd = TabularCPD("diff", 2, values=[[0.2], [0.8]])
intel_cpd = TabularCPD("intel", 3, values=[[0.5], [0.3], [0.2]])
grade_cpd = TabularCPD(
"grade",
3,
values=[
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8],
],
evidence=["diff", "intel"],
evidence_card=[2, 3],
)
self.G1.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.G2 = BayesianModel([("d", "g"), ("g", "l"), ("i", "g"),
("i", "l")])
def test_moral_graph(self):
moral_graph = self.G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
["a", "b", "c", "d", "e"])
for edge in moral_graph.edges():
self.assertTrue(edge in [("a", "b"), ("a", "d"), ("b", "c"),
("d", "b"), ("e", "d")]
or (edge[1], edge[0]) in [("a", "b"), ("a", "d"),
("b", "c"), ("d", "b"),
("e", "d")])
def test_moral_graph_with_edge_present_over_parents(self):
G = BayesianModel([("a", "d"), ("d", "e"), ("b", "d"), ("b", "c"),
("a", "b")])
moral_graph = G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
["a", "b", "c", "d", "e"])
for edge in moral_graph.edges():
self.assertTrue(edge in [("a", "b"), ("c", "b"), ("d", "a"),
("d", "b"), ("d", "e")]
or (edge[1], edge[0]) in [("a", "b"), ("c", "b"),
("d", "a"), ("d", "b"),
("d", "e")])
def test_get_ancestors_of_success(self):
ancenstors1 = self.G2._get_ancestors_of("g")
ancenstors2 = self.G2._get_ancestors_of("d")
ancenstors3 = self.G2._get_ancestors_of(["i", "l"])
self.assertEqual(ancenstors1, {"d", "i", "g"})
self.assertEqual(ancenstors2, {"d"})
self.assertEqual(ancenstors3, {"g", "i", "l", "d"})
def test_get_ancestors_of_failure(self):
self.assertRaises(ValueError, self.G2._get_ancestors_of, "h")
def test_get_cardinality(self):
self.assertDictEqual(self.G1.get_cardinality(), {
"diff": 2,
"intel": 3,
"grade": 3
})
def test_get_cardinality_with_node(self):
self.assertEqual(self.G1.get_cardinality("diff"), 2)
self.assertEqual(self.G1.get_cardinality("intel"), 3)
self.assertEqual(self.G1.get_cardinality("grade"), 3)
def test_local_independencies(self):
self.assertEqual(self.G.local_independencies("a"),
Independencies(["a", ["b", "c"]]))
self.assertEqual(
self.G.local_independencies("c"),
Independencies(["c", ["a", "d", "e"], "b"]),
)
self.assertEqual(self.G.local_independencies("d"),
Independencies(["d", "c", ["b", "a"]]))
self.assertEqual(
self.G.local_independencies("e"),
Independencies(["e", ["c", "b", "a"], "d"]),
)
self.assertEqual(self.G.local_independencies("b"),
Independencies(["b", "a"]))
self.assertEqual(self.G1.local_independencies("grade"),
Independencies())
def test_get_independencies(self):
chain = BayesianModel([("X", "Y"), ("Y", "Z")])
self.assertEqual(chain.get_independencies(),
Independencies(("X", "Z", "Y"), ("Z", "X", "Y")))
fork = BayesianModel([("Y", "X"), ("Y", "Z")])
self.assertEqual(fork.get_independencies(),
Independencies(("X", "Z", "Y"), ("Z", "X", "Y")))
collider = BayesianModel([("X", "Y"), ("Z", "Y")])
self.assertEqual(collider.get_independencies(),
Independencies(("X", "Z"), ("Z", "X")))
def test_is_imap(self):
val = [
0.01,
0.01,
0.08,
0.006,
0.006,
0.048,
0.004,
0.004,
0.032,
0.04,
0.04,
0.32,
0.024,
0.024,
0.192,
0.016,
0.016,
0.128,
]
JPD = JointProbabilityDistribution(["diff", "intel", "grade"],
[2, 3, 3], val)
fac = DiscreteFactor(["diff", "intel", "grade"], [2, 3, 3], val)
self.assertTrue(self.G1.is_imap(JPD))
self.assertRaises(TypeError, self.G1.is_imap, fac)
def test_markov_blanet(self):
G = DAG([
("x", "y"),
("z", "y"),
("y", "w"),
("y", "v"),
("u", "w"),
("s", "v"),
("w", "t"),
("w", "m"),
("v", "n"),
("v", "q"),
])
self.assertEqual(set(G.get_markov_blanket("y")),
set(["s", "w", "x", "u", "z", "v"]))
def test_get_immoralities(self):
G = BayesianModel([("x", "y"), ("z", "y"), ("x", "z"), ("w", "y")])
self.assertEqual(G.get_immoralities(), {("w", "x"), ("w", "z")})
G1 = BayesianModel([("x", "y"), ("z", "y"), ("z", "x"), ("w", "y")])
self.assertEqual(G1.get_immoralities(), {("w", "x"), ("w", "z")})
G2 = BayesianModel([("x", "y"), ("z", "y"), ("x", "z"), ("w", "y"),
("w", "x")])
self.assertEqual(G2.get_immoralities(), {("w", "z")})
def test_is_iequivalent(self):
G = BayesianModel([("x", "y"), ("z", "y"), ("x", "z"), ("w", "y")])
self.assertRaises(TypeError, G.is_iequivalent, MarkovModel())
G1 = BayesianModel([("V", "W"), ("W", "X"), ("X", "Y"), ("Z", "Y")])
G2 = BayesianModel([("W", "V"), ("X", "W"), ("X", "Y"), ("Z", "Y")])
self.assertTrue(G1.is_iequivalent(G2))
G3 = BayesianModel([("W", "V"), ("W", "X"), ("Y", "X"), ("Z", "Y")])
self.assertFalse(G3.is_iequivalent(G2))
def test_copy(self):
model_copy = self.G1.copy()
self.assertEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
self.assertNotEqual(id(self.G1.get_cpds("diff")),
id(model_copy.get_cpds("diff")))
self.G1.remove_cpds("diff")
diff_cpd = TabularCPD("diff", 2, values=[[0.3], [0.7]])
self.G1.add_cpds(diff_cpd)
self.assertNotEqual(self.G1.get_cpds("diff"),
model_copy.get_cpds("diff"))
self.G1.remove_node("intel")
self.assertNotEqual(sorted(self.G1.nodes()),
sorted(model_copy.nodes()))
self.assertNotEqual(sorted(self.G1.edges()),
sorted(model_copy.edges()))
def test_remove_node(self):
self.G1.remove_node("diff")
self.assertEqual(sorted(self.G1.nodes()), sorted(["grade", "intel"]))
self.assertRaises(ValueError, self.G1.get_cpds, "diff")
def test_remove_nodes_from(self):
self.G1.remove_nodes_from(["diff", "grade"])
self.assertEqual(sorted(self.G1.nodes()), sorted(["intel"]))
self.assertRaises(ValueError, self.G1.get_cpds, "diff")
self.assertRaises(ValueError, self.G1.get_cpds, "grade")
def tearDown(self):
del self.G
del self.G1
class TestDAGCPDOperations(unittest.TestCase):
def setUp(self):
self.graph = BayesianModel()
def test_add_single_cpd(self):
cpd = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd)
self.assertListEqual(self.graph.get_cpds(), [cpd])
def test_add_multiple_cpds(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertListEqual(self.graph.get_cpds(), [cpd1, cpd2, cpd3])
def test_remove_single_cpd(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds(cpd1)
self.assertListEqual(self.graph.get_cpds(), [cpd2, cpd3])
def test_remove_multiple_cpds(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds(cpd1, cpd3)
self.assertListEqual(self.graph.get_cpds(), [cpd2])
def test_remove_single_cpd_string(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds("diff")
self.assertListEqual(self.graph.get_cpds(), [cpd2, cpd3])
def test_remove_multiple_cpds_string(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.graph.remove_cpds("diff", "grade")
self.assertListEqual(self.graph.get_cpds(), [cpd2])
def test_get_values_for_node(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertEqual(self.graph.get_cpds("diff"), cpd1)
self.assertEqual(self.graph.get_cpds("intel"), cpd2)
self.assertEqual(self.graph.get_cpds("grade"), cpd3)
def test_get_values_raises_error(self):
cpd1 = TabularCPD("diff", 2, values=np.random.rand(2, 1))
cpd2 = TabularCPD("intel", 2, values=np.random.rand(2, 1))
cpd3 = TabularCPD(
"grade",
2,
values=np.random.rand(2, 4),
evidence=["diff", "intel"],
evidence_card=[2, 2],
)
self.graph.add_edges_from([("diff", "grade"), ("intel", "grade")])
self.graph.add_cpds(cpd1, cpd2, cpd3)
self.assertRaises(ValueError, self.graph.get_cpds, "sat")
def tearDown(self):
del self.graph
class TestBayesianModelMethods(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('a', 'd'), ('b', 'd'),
('d', 'e'), ('b', 'c')])
self.G1 = BayesianModel([('diff', 'grade'), ('intel', 'grade')])
diff_cpd = TabularCPD('diff', 2, values=[[0.2], [0.8]])
intel_cpd = TabularCPD('intel', 3, values=[[0.5], [0.3], [0.2]])
grade_cpd = TabularCPD('grade', 3, values=[[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'], evidence_card=[2, 3])
self.G1.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.G2 = BayesianModel([('d', 'g'), ('g', 'l'), ('i', 'g'), ('i', 'l')])
def test_moral_graph(self):
moral_graph = self.G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()), ['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('a', 'd'), ('b', 'c'), ('d', 'b'), ('e', 'd')] or
(edge[1], edge[0]) in [('a', 'b'), ('a', 'd'), ('b', 'c'), ('d', 'b'), ('e', 'd')])
def test_moral_graph_with_edge_present_over_parents(self):
G = BayesianModel([('a', 'd'), ('d', 'e'), ('b', 'd'), ('b', 'c'), ('a', 'b')])
moral_graph = G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()), ['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('c', 'b'), ('d', 'a'), ('d', 'b'), ('d', 'e')] or
(edge[1], edge[0]) in [('a', 'b'), ('c', 'b'), ('d', 'a'), ('d', 'b'), ('d', 'e')])
def test_get_ancestors_of_success(self):
ancenstors1 = self.G2._get_ancestors_of('g')
ancenstors2 = self.G2._get_ancestors_of('d')
ancenstors3 = self.G2._get_ancestors_of(['i', 'l'])
self.assertEqual(ancenstors1, {'d', 'i', 'g'})
self.assertEqual(ancenstors2, {'d'})
self.assertEqual(ancenstors3, {'g', 'i', 'l', 'd'})
def test_get_ancestors_of_failure(self):
self.assertRaises(ValueError, self.G2._get_ancestors_of, 'h')
def test_local_independencies(self):
self.assertEqual(self.G.local_independencies('a'), Independencies(['a', ['b', 'c']]))
self.assertEqual(self.G.local_independencies('c'), Independencies(['c', ['a', 'd', 'e'], 'b']))
self.assertEqual(self.G.local_independencies('d'), Independencies(['d', 'c', ['b', 'a']]))
self.assertEqual(self.G.local_independencies('e'), Independencies(['e', ['c', 'b', 'a'], 'd']))
self.assertEqual(self.G.local_independencies('b'), Independencies(['b', 'a']))
self.assertEqual(self.G1.local_independencies('grade'), Independencies())
def test_get_independencies(self):
chain = BayesianModel([('X', 'Y'), ('Y', 'Z')])
self.assertEqual(chain.get_independencies(), Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
fork = BayesianModel([('Y', 'X'), ('Y', 'Z')])
self.assertEqual(fork.get_independencies(), Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
collider = BayesianModel([('X', 'Y'), ('Z', 'Y')])
self.assertEqual(collider.get_independencies(), Independencies(('X', 'Z'), ('Z', 'X')))
def test_is_imap(self):
val = [0.01, 0.01, 0.08, 0.006, 0.006, 0.048, 0.004, 0.004, 0.032,
0.04, 0.04, 0.32, 0.024, 0.024, 0.192, 0.016, 0.016, 0.128]
JPD = JointProbabilityDistribution(['diff', 'intel', 'grade'], [2, 3, 3], val)
fac = DiscreteFactor(['diff', 'intel', 'grade'], [2, 3, 3], val)
self.assertTrue(self.G1.is_imap(JPD))
self.assertRaises(TypeError, self.G1.is_imap, fac)
def test_get_immoralities(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertEqual(G.get_immoralities(), {('w', 'x'), ('w', 'z')})
G1 = BayesianModel([('x', 'y'), ('z', 'y'), ('z', 'x'), ('w', 'y')])
self.assertEqual(G1.get_immoralities(), {('w', 'x'), ('w', 'z')})
G2 = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y'), ('w', 'x')])
self.assertEqual(G2.get_immoralities(), {('w', 'z')})
def test_is_iequivalent(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertRaises(TypeError, G.is_iequivalent, MarkovModel())
G1 = BayesianModel([('V', 'W'), ('W', 'X'), ('X', 'Y'), ('Z', 'Y')])
G2 = BayesianModel([('W', 'V'), ('X', 'W'), ('X', 'Y'), ('Z', 'Y')])
self.assertTrue(G1.is_iequivalent(G2))
G3 = BayesianModel([('W', 'V'), ('W', 'X'), ('Y', 'X'), ('Z', 'Y')])
self.assertFalse(G3.is_iequivalent(G2))
def test_copy(self):
model_copy = self.G1.copy()
self.assertEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
self.assertNotEqual(id(self.G1.get_cpds('diff')),
id(model_copy.get_cpds('diff')))
self.G1.remove_cpds('diff')
diff_cpd = TabularCPD('diff', 2, values=[[0.3], [0.7]])
self.G1.add_cpds(diff_cpd)
self.assertNotEqual(self.G1.get_cpds('diff'),
model_copy.get_cpds('diff'))
self.G1.remove_node('intel')
self.assertNotEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertNotEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
def test_remove_node(self):
self.G1.remove_node('diff')
self.assertEqual(sorted(self.G1.nodes()), sorted(['grade', 'intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
def test_remove_nodes_from(self):
self.G1.remove_nodes_from(['diff', 'grade'])
self.assertEqual(sorted(self.G1.nodes()), sorted(['intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
self.assertRaises(ValueError, self.G1.get_cpds, 'grade')
def tearDown(self):
del self.G
del self.G1
