class TimeSampling:
timeout = 600.0
def setup(self):
self.model = get_example_model('alarm')
self.s = BayesianModelSampling(self.model)
def time_forward_sample(self):
self.model.simulate(n_samples=int(1e4), show_progress=False)
def time_rejection_sample(self):
self.model.simulate(n_samples=int(1e4),
evidence={
"HISTORY": "TRUE",
"HR": "NORMAL"
},
show_progress=False)
def time_likelihood_sample(self):
self.s.likelihood_weighted_sample(evidence=[("HISTORY", "TRUE"),
("HR", "NORMAL")],
size=int(1e4))
def time_gibbs_sampling(self):
gibbs_samples = GibbsSampling(model=self.model)
gibbs_sampling.sample(size=int(1e4))
def bayesian_net():
musicianship_model = BayesianModel([('Difficulty', 'Rating'),
('Musicianship', 'Rating'),
('Musicianship', 'Exam'),
('Rating', 'Letter')])
cpd_diff = TabularCPD(variable='Difficulty',
variable_card=2,
values=[[0.6], [0.4]]) #0->Low, 1->High
cpd_music = TabularCPD(variable='Musicianship',
variable_card=2,
values=[[0.7], [0.3]]) #0->Weak 1->Strong
cpd_rating = TabularCPD(variable='Rating',
variable_card=3,
values=[[0.3, 0.05, 0.9, 0.5],
[0.4, 0.25, 0.08, 0.3],
[0.3, 0.7, 0.02, 0.2]],
evidence=['Difficulty', 'Musicianship'],
evidence_card=[2, 2]) #0->* 1->** 2-->***
cpd_exam = TabularCPD(variable='Exam',
variable_card=2,
values=[[0.95, 0.2], [0.05, 0.8]],
evidence=['Musicianship'],
evidence_card=[2]) #0-->Low 1-->High
cpd_letter = TabularCPD(variable='Letter',
variable_card=2,
values=[[0.1, 0.4, 0.99], [0.9, 0.6, 0.01]],
evidence=['Rating'],
evidence_card=[3]) #0-->Weak 1-->Strong
musicianship_model.add_cpds(cpd_diff, cpd_music, cpd_rating, cpd_exam,
cpd_letter)
musicianship_model.check_model()
infer = SimpleInference(musicianship_model) # query without normalization
print('------------------------')
print(' EXACT INFERENCE')
print('------------------------')
print('--------------------')
print(
' QUERY Letter with evidence Difficulty: 0, Musicianship: 1, Rating: 1, Exam:1 NOT NORMALIZED'
)
print('--------------------')
print(
infer.query(['Letter'],
evidence={('Difficulty', 0), ('Musicianship', 1),
('Rating', 1), ('Exam', 1)}))
print('--------------------')
print(
' QUERY Letter with evidence Difficulty: 0, Musicianship: 1, Rating: 1, Exam:1 NORMALIZED'
)
print('--------------------')
infer = VariableElimination(musicianship_model) # query normalized
print(
infer.query(['Letter'],
evidence={
'Difficulty': 0,
'Musicianship': 1,
'Rating': 1,
'Exam': 1
})['Letter'])
print('--------------------')
print(' QUERY Letter with no evidence')
print('--------------------')
print(infer.query(['Letter'])['Letter'])
print('--------------------')
print(' QUERY Letter with evidence Musicianship: 0 NORMALIZED')
print('--------------------')
print(infer.query(['Letter'], evidence={'Musicianship': 0})['Letter'])
sampling = BayesianModelSampling(musicianship_model)
data = sampling.likelihood_weighted_sample(evidence={},
size=2000,
return_type='dataframe')
musicianship_model_bis = BayesianModel([('Difficulty', 'Rating'),
('Musicianship', 'Rating'),
('Rating', 'Letter'),
('Musicianship', 'Exam')])
musicianship_model_bis.fit(data, estimator=BayesianEstimator)
musicianship_model_bis.check_model()
infer = VariableElimination(musicianship_model_bis) # query normalized
for cpd in musicianship_model_bis.get_cpds():
print("CPD of {variable}:".format(variable=cpd.variable))
print(cpd)
print('------------------------')
print(' APPROXIMATE INFERENCE')
print('------------------------')
print('--------------------')
print(
' QUERY Letter with evidence Difficulty: 0, Musicianship: 1, Rating: 1, Exam:1 NORMALIZED'
)
print('--------------------')
print(
infer.query(['Letter'],
evidence={
'Difficulty': 0,
'Musicianship': 1,
'Rating': 1,
'Exam': 1
})['Letter'])
print('--------------------')
print(' QUERY Letter with no evidence')
print('--------------------')
print(infer.query(['Letter'])['Letter'])
print('--------------------')
print(' QUERY Letter with evidence Musicianship: 0 NORMALIZED')
print('--------------------')
print(infer.query(['Letter'], evidence={'Musicianship': 0})['Letter'])
model.fit(trainData, estimator=MaximumLikelihoodEstimator)
#for cpd in model.get_cpds():
# print("CPD of {variable}:".format(variable=cpd.variable))
# print(cpd)
model_sample = BayesianModelSampling(model)
pickle.dump(model_sample, open('results/sampler.p', 'wb'))
# open the nhts sample and add the inferred resType requirements
nhtsSample = pd.read_csv('results/nhtsSample.csv')
resType = []
for ind, row in nhtsSample.iterrows():
evidence = [
State('IncomeQ', min(row['hh_income'] - 1, 10)),
State('HhSize', min(row['hh_size'] - 1, 5))
]
sample = model_sample.likelihood_weighted_sample(evidence=evidence, size=1)
resType.extend([int(sample['Bedrooms']) * 3 + int(sample['RentQ'])])
nhtsSample['resType'] = resType
os.chdir('..')
nhtsSample[nhtsSample['occupation_type'] == 1].sample(
n=50, replace=True).to_csv('ABM/includes/pop_occat_1.csv', index=False)
nhtsSample[nhtsSample['occupation_type'] == 2].sample(
n=50, replace=True).to_csv('ABM/includes/pop_occat_2.csv', index=False)
nhtsSample[nhtsSample['occupation_type'] == 3].sample(
n=50, replace=True).to_csv('ABM/includes/pop_occat_3.csv', index=False)
nhtsSample[nhtsSample['occupation_type'] == 4].sample(
n=50, replace=True).to_csv('ABM/includes/pop_occat_4.csv', index=False)
nhtsSample[nhtsSample['occupation_type'] == 5].sample(
n=50, replace=True).to_csv('ABM/includes/pop_occat_5.csv', index=False)
class TestBayesianModelSampling(unittest.TestCase):
def setUp(self):
self.bayesian_model = BayesianModel([('A', 'J'), ('R', 'J'),
('J', 'Q'), ('J', 'L'),
('G', 'L')])
cpd_a = TabularCPD('A', 2, [[0.2], [0.8]])
cpd_r = TabularCPD('R', 2, [[0.4], [0.6]])
cpd_j = TabularCPD('J', 2,
[[0.9, 0.6, 0.7, 0.1], [0.1, 0.4, 0.3, 0.9]],
['R', 'A'], [2, 2])
cpd_q = TabularCPD('Q', 2, [[0.9, 0.2], [0.1, 0.8]], ['J'], [2])
cpd_l = TabularCPD('L', 2,
[[0.9, 0.45, 0.8, 0.1], [0.1, 0.55, 0.2, 0.9]],
['G', 'J'], [2, 2])
cpd_g = TabularCPD('G', 2, [[0.6], [0.4]])
self.bayesian_model.add_cpds(cpd_a, cpd_g, cpd_j, cpd_l, cpd_q, cpd_r)
self.sampling_inference = BayesianModelSampling(self.bayesian_model)
self.markov_model = MarkovModel()
def test_init(self):
with self.assertRaises(TypeError):
BayesianModelSampling(self.markov_model)
def test_forward_sample(self):
sample = self.sampling_inference.forward_sample(25)
self.assertEquals(len(sample), 25)
self.assertEquals(len(sample.columns), 6)
self.assertIn('A', sample.columns)
self.assertIn('J', sample.columns)
self.assertIn('R', sample.columns)
self.assertIn('Q', sample.columns)
self.assertIn('G', sample.columns)
self.assertIn('L', sample.columns)
self.assertTrue(set(sample.A).issubset({0, 1}))
self.assertTrue(set(sample.J).issubset({0, 1}))
self.assertTrue(set(sample.R).issubset({0, 1}))
self.assertTrue(set(sample.Q).issubset({0, 1}))
self.assertTrue(set(sample.G).issubset({0, 1}))
self.assertTrue(set(sample.L).issubset({0, 1}))
def test_rejection_sample_basic(self):
sample = self.sampling_inference.rejection_sample(
[State('A', 1), State('J', 1),
State('R', 1)], 25)
self.assertEquals(len(sample), 25)
self.assertEquals(len(sample.columns), 6)
self.assertIn('A', sample.columns)
self.assertIn('J', sample.columns)
self.assertIn('R', sample.columns)
self.assertIn('Q', sample.columns)
self.assertIn('G', sample.columns)
self.assertIn('L', sample.columns)
self.assertTrue(set(sample.A).issubset({1}))
self.assertTrue(set(sample.J).issubset({1}))
self.assertTrue(set(sample.R).issubset({1}))
self.assertTrue(set(sample.Q).issubset({0, 1}))
self.assertTrue(set(sample.G).issubset({0, 1}))
self.assertTrue(set(sample.L).issubset({0, 1}))
@patch("pgmpy.sampling.BayesianModelSampling.forward_sample",
autospec=True)
def test_rejection_sample_less_arg(self, forward_sample):
sample = self.sampling_inference.rejection_sample(size=5)
forward_sample.assert_called_once_with(self.sampling_inference, 5)
self.assertEqual(sample, forward_sample.return_value)
def test_likelihood_weighted_sample(self):
sample = self.sampling_inference.likelihood_weighted_sample(
[State('A', 0), State('J', 1),
State('R', 0)], 25)
self.assertEquals(len(sample), 25)
self.assertEquals(len(sample.columns), 7)
self.assertIn('A', sample.columns)
self.assertIn('J', sample.columns)
self.assertIn('R', sample.columns)
self.assertIn('Q', sample.columns)
self.assertIn('G', sample.columns)
self.assertIn('L', sample.columns)
self.assertIn('_weight', sample.columns)
self.assertTrue(set(sample.A).issubset({0, 1}))
self.assertTrue(set(sample.J).issubset({0, 1}))
self.assertTrue(set(sample.R).issubset({0, 1}))
self.assertTrue(set(sample.Q).issubset({0, 1}))
self.assertTrue(set(sample.G).issubset({0, 1}))
self.assertTrue(set(sample.L).issubset({0, 1}))
def tearDown(self):
del self.sampling_inference
del self.bayesian_model
del self.markov_model
class TestBayesianModelSampling(unittest.TestCase):
def setUp(self):
self.bayesian_model = BayesianModel([('A', 'J'), ('R', 'J'), ('J', 'Q'),
('J', 'L'), ('G', 'L')])
cpd_a = TabularCPD('A', 2, [[0.2], [0.8]])
cpd_r = TabularCPD('R', 2, [[0.4], [0.6]])
cpd_j = TabularCPD('J', 2,
[[0.9, 0.6, 0.7, 0.1],
[0.1, 0.4, 0.3, 0.9]],
['R', 'A'], [2, 2])
cpd_q = TabularCPD('Q', 2,
[[0.9, 0.2],
[0.1, 0.8]],
['J'], [2])
cpd_l = TabularCPD('L', 2,
[[0.9, 0.45, 0.8, 0.1],
[0.1, 0.55, 0.2, 0.9]],
['G', 'J'], [2, 2])
cpd_g = TabularCPD('G', 2, [[0.6], [0.4]])
self.bayesian_model.add_cpds(cpd_a, cpd_g, cpd_j, cpd_l, cpd_q, cpd_r)
self.sampling_inference = BayesianModelSampling(self.bayesian_model)
self.markov_model = MarkovModel()
def test_init(self):
with self.assertRaises(TypeError):
BayesianModelSampling(self.markov_model)
def test_forward_sample(self):
sample = self.sampling_inference.forward_sample(25)
self.assertEquals(len(sample), 25)
self.assertEquals(len(sample.columns), 6)
self.assertIn('A', sample.columns)
self.assertIn('J', sample.columns)
self.assertIn('R', sample.columns)
self.assertIn('Q', sample.columns)
self.assertIn('G', sample.columns)
self.assertIn('L', sample.columns)
self.assertTrue(set(sample.A).issubset({0, 1}))
self.assertTrue(set(sample.J).issubset({0, 1}))
self.assertTrue(set(sample.R).issubset({0, 1}))
self.assertTrue(set(sample.Q).issubset({0, 1}))
self.assertTrue(set(sample.G).issubset({0, 1}))
self.assertTrue(set(sample.L).issubset({0, 1}))
def test_rejection_sample_basic(self):
sample = self.sampling_inference.rejection_sample([State('A', 1), State('J', 1), State('R', 1)], 25)
self.assertEquals(len(sample), 25)
self.assertEquals(len(sample.columns), 6)
self.assertIn('A', sample.columns)
self.assertIn('J', sample.columns)
self.assertIn('R', sample.columns)
self.assertIn('Q', sample.columns)
self.assertIn('G', sample.columns)
self.assertIn('L', sample.columns)
self.assertTrue(set(sample.A).issubset({1}))
self.assertTrue(set(sample.J).issubset({1}))
self.assertTrue(set(sample.R).issubset({1}))
self.assertTrue(set(sample.Q).issubset({0, 1}))
self.assertTrue(set(sample.G).issubset({0, 1}))
self.assertTrue(set(sample.L).issubset({0, 1}))
@patch("pgmpy.sampling.BayesianModelSampling.forward_sample", autospec=True)
def test_rejection_sample_less_arg(self, forward_sample):
sample = self.sampling_inference.rejection_sample(size=5)
forward_sample.assert_called_once_with(self.sampling_inference, 5)
self.assertEqual(sample, forward_sample.return_value)
def test_likelihood_weighted_sample(self):
sample = self.sampling_inference.likelihood_weighted_sample([State('A', 0), State('J', 1), State('R', 0)], 25)
self.assertEquals(len(sample), 25)
self.assertEquals(len(sample.columns), 7)
self.assertIn('A', sample.columns)
self.assertIn('J', sample.columns)
self.assertIn('R', sample.columns)
self.assertIn('Q', sample.columns)
self.assertIn('G', sample.columns)
self.assertIn('L', sample.columns)
self.assertIn('_weight', sample.columns)
self.assertTrue(set(sample.A).issubset({0, 1}))
self.assertTrue(set(sample.J).issubset({0, 1}))
self.assertTrue(set(sample.R).issubset({0, 1}))
self.assertTrue(set(sample.Q).issubset({0, 1}))
self.assertTrue(set(sample.G).issubset({0, 1}))
self.assertTrue(set(sample.L).issubset({0, 1}))
def tearDown(self):
del self.sampling_inference
del self.bayesian_model
del self.markov_model