# Cancer_1 | 0.97 | 0.95 | 0.999 | 0.98
#
# 以0.98所在的单元格为例，Smoker_1代表吸烟，Pullution_1代表有污染，Cancer_1代表患癌症，即在吸烟且环境有污染的情况下，患癌症概率为0.98。其他单元格阅读方式相同。这样，在知道任意情况的条件概率分布表的情况下，就能建立对应结点的参数。
# In[13]:
# 利用add_cpds函数将参数与图连接起来
cancer_model.add_cpds(cpd_poll, cpd_smoke, cpd_cancer, cpd_xray, cpd_dysp)
# 检查模型是否合理，True代表合理
cancer_model.check_model()
# In[14]:
# is_active_trail函数检验两个结点之间是否有有向连接
cancer_model.is_active_trail('Pollution', 'Smoker')
# In[15]:
# 在is_active_trail函数中，设置observed参数，表示两个结点能否通过observed结点实现连接
cancer_model.is_active_trail('Pollution', 'Smoker', observed=['Cancer'])
# # 5 实验练习
# 下面我们将利用一个更为复杂的Bayes网络，通过Pgmpy模块实现计算。网络图如下图：
# <img src="./Img/fig7.png" width = "500" height = "300" alt="Aisa" align=center />
# 首先导入相应的模块和数据集：
# >**注意:**pgmpy模块中，PGM图可以通过bif格式进行存储和阅读，这里已经将上述PGM以asia.bif储存好。
# In[16]:
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
# --- 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 "
# ('activities', 'studytime'),
# ('freetime', 'goout'),
# ('failures', 'absences'),
# ('freetime', 'activities'),
# ('studytime', 'freetime'),
]
model = BayesianModel(bnmodel)
# To test any implied condition in the network, the method `is_active_trail` can be used. Next line tests for
# the condition (Education _|_ MaritalStatus | Age)
var1 = 'subject'
var2 = 'G3'
observed = []
active = model.is_active_trail(var1, var2, observed=observed) # is dependent
# The `get_independencies` method lists all the implied conditions in the model.
#model.get_independencies()
# To perform chi-square test on any of the conditional independencies, the method `test_independence` defined
# above can be used. To test for (Education _|_ HoursPerWeek | 'Age', 'Immigrant', 'Sex')
independent, dependent, questionable = [], [], []
for (var1, var2) in bnmodel:
if var1 == 'IQ' or var2 == 'IQ':
continue
chi_stat, p_value, dof, RMSEA = test_independence(df=df,
var1=var1,
var2=var2,
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')])
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):
from pgmpy.factors import TabularCPD
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):
from pgmpy.factors import TabularCPD
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 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 TestBayesianModelCPD(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('d', 'g'), ('i', 'g'), ('g', 'l'),
('i', 's')])
# self.G.set_states(
# {'d': ['easy', 'hard'], 'g': ['A', 'B', 'C'], 'i': ['dumb', 'smart'], 's': ['bad', 'avg', 'good'],
# 'l': ['yes', 'no']})
# def test_set_cpd(self):
# self.G.set_cpd('g', [[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]])
# self.assertIsInstance(self.G.node['g']['_cpd'], bm.CPD.TabularCPD)
# np.testing.assert_array_equal(self.G.node['g']['_cpd'].cpd, np.array((
# [[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]])))
#
# def test_get_cpd(self):
# self.G.set_cpd('g', [[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]])
# np.testing.assert_array_equal(self.G.get_cpd('g'), np.array((
# [[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]])))
# def test_set_observations_single_state_reset_false(self):
# self.G.set_observations({'d': 'easy'})
# for state in self.G.node['d']['_states']:
# if state['name'] == 'easy':
# break
# self.assertTrue(state['observed_status'])
# self.assertTrue(self.G.node['d']['_observed'])
#
# def test_set_observation_multiple_state_reset_false(self):
# self.G.set_observations({'d': 'easy', 'g': 'A'})
# for state in self.G.node['d']['_states']:
# if state['name'] == 'easy':
# break
# self.assertTrue(state['observed_status'])
# self.assertTrue(self.G.node['d']['_observed'])
# for state in self.G.node['g']['_states']:
# if state['name'] == 'A':
# break
# self.assertTrue(state['observed_status'])
# self.assertTrue(self.G.node['g']['_observed'])
#
# def test_set_observation_multiple_state_reset_false_not_found(self):
# self.assertRaises(ValueError, self.G.set_observations, {'d': 'unknow_state'})
#
# def test_reset_observations_single_state(self):
# self.G.reset_observations({'d': 'easy'})
# # TODO change this as the function has changed
# self.G.reset_observations({'d': 'easy'})
# for state in self.G.node['d']['_states']:
# if state['name'] == 'easy':
# break
# self.assertFalse(state['observed_status'])
# self.assertFalse(self.G.node['g']['_observed'])
#
# def test_reset_observations_multiple_state(self):
# self.G.set_observations({'d': 'easy', 'g': 'A', 'i': 'dumb'})
# self.G.reset_observations({'d': 'easy', 'i': 'dumb'})
# for state in self.G.node['d']['_states']:
# if state['name'] == 'easy':
# break
# self.assertFalse(state['observed_status'])
# self.assertFalse(self.G.node['d']['_observed'])
# for state in self.G.node['g']['_states']:
# if state['name'] == 'A':
# break
# self.assertTrue(state['observed_status'])
# self.assertTrue(self.G.node['g']['_observed'])
#
# def test_reset_observation_node_none(self):
# self.G.set_observations({'d': 'easy', 'g': 'A'})
# self.G.reset_observations()
# self.assertFalse(self.G.node['d']['_observed'])
# for state in self.G.node['d']['_states']:
# self.assertFalse(state['observed_status'])
# self.assertFalse(self.G.node['g']['_observed'])
# for state in self.G.node['g']['_states']:
# self.assertFalse(state['observed_status'])
#
# def test_reset_observations_node_not_none(self):
# self.G.set_observations({'d': 'easy', 'g': 'A'})
# self.G.reset_observations('d')
# self.assertFalse(self.G.node['d']['_observed'])
# for state in self.G.node['d']['_states']:
# self.assertFalse(state['observed_status'])
# self.assertTrue(self.G.node['g']['_observed'])
# for state in self.G.node['g']['_states']:
# if state['name'] == 'A':
# self.assertTrue(state['observed_status'])
# else:
# self.assertFalse(state['observed_status'])
#
# def test_reset_observations_node_error(self):
# self.assertRaises(KeyError, self.G.reset_observations, 'j')
#
# def test_is_observed(self):
# self.G.set_observations({'d': 'easy'})
# self.assertTrue(self.G.is_observed('d'))
# self.assertFalse(self.G.is_observed('i'))
#
# # def test_get_ancestros_observation(self):
# # self.G.set_observations({'d': 'easy', 'g': 'A'})
# # self.assertListEqual(list(self.G._get_ancestors_observation(['d'])), [])
# # self.assertListEqual(list(sorted(self.G._get_ancestors_observation(['d', 'g']))), ['d', 'i'])
#
# def test_get_observed_list(self):
# self.G.set_observations({'d': 'hard', 'i': 'smart'})
# self.assertListEqual(sorted(self.G._get_observed_list()), ['d', 'i'])
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 tearDown(self):
del self.G
variable_card=2,
values=[[0.9], [0.1]])
cpd_smoke = TabularCPD(variable='Smoker',
variable_card=2,
values=[[0.3], [0.7]])
cpd_cancer = TabularCPD(variable='Cancer',
variable_card=2,
values=[[0.03, 0.05, 0.001, 0.02],
[0.97, 0.95, 0.999, 0.98]],
evidence=['Smoker', 'Pollution'],
evidence_card=[2, 2])
cpd_xray = TabularCPD(variable='Xray',
variable_card=2,
values=[[0.9, 0.2], [0.1, 0.8]],
evidence=['Cancer'],
evidence_card=[2])
cpd_dysp = TabularCPD(variable='Dyspnoea',
variable_card=2,
values=[[0.65, 0.3], [0.35, 0.7]],
evidence=['Cancer'],
evidence_card=[2])
# Associating the parameters with the model structure.
cancer_model.add_cpds(cpd_poll, cpd_smoke, cpd_cancer, cpd_xray, cpd_dysp)
# Checking if the cpds are valid for the model.
cancer_model.check_model()
# Doing some simple queries on the network
cancer_model.is_active_trail('Pollution', 'Smoker')