def test_distributions_normal_underflow_probability():
d = NormalDistribution(5, 1e-10)
assert_almost_equal(d.probability(1e100), 0.0)
def test_distributions_normal_underflow_log_probability():
d = NormalDistribution(5, 1e-10)
assert_almost_equal(d.log_probability(1e100),
-4.9999999999999987e+219,
delta=6.270570637641398e+203)
def test_distributions_normal_nan_probability():
d = NormalDistribution(5, 2)
assert_equal(d.probability(nan), 1)
assert_array_almost_equal(d.probability([nan, 5]), [1, 0.199471])
def test_distributions_normal_nan_log_probability():
d = NormalDistribution(5, 2)
assert_equal(d.log_probability(nan), 0)
assert_array_almost_equal(d.log_probability([nan, 5]), [0, -1.61208571])
def test_distributions_normal_initialization():
d = NormalDistribution(5, 2)
assert_equal(d.name, "NormalDistribution")
assert_array_equal(d.parameters, [5, 2])
assert_array_equal(d.summaries, [0, 0, 0])
def test_independent(): d = IndependentComponentsDistribution( [NormalDistribution(5, 2), ExponentialDistribution(2)]) assert_equal(round(d.log_probability((4, 1)), 4), -3.0439) assert_equal(round(d.log_probability((100, 0.001)), 4), -1129.0459) d = IndependentComponentsDistribution([NormalDistribution(5, 2), ExponentialDistribution(2)], weights=[18., 1.]) assert_equal(round(d.log_probability((4, 1)), 4), -32.5744) assert_equal(round(d.log_probability((100, 0.001)), 4), -20334.5764) d.fit([(5, 1), (5.2, 1.7), (4.7, 1.9), (4.9, 2.4), (4.5, 1.2)]) assert_equal(round(d.parameters[0][0].parameters[0], 4), 4.86) assert_equal(round(d.parameters[0][0].parameters[1], 4), 0.2417) assert_equal(round(d.parameters[0][1].parameters[0], 4), 0.6098) d = IndependentComponentsDistribution([NormalDistribution(5, 2), UniformDistribution(0, 10)]) d.fit([(0, 0), (5, 0), (3, 0), (5, -5), (7, 0), (3, 0), (4, 0), (5, 0), (2, 20)], inertia=0.5) assert_equal(round(d.parameters[0][0].parameters[0], 4), 4.3889) assert_equal(round(d.parameters[0][0].parameters[1], 4), 1.9655) assert_equal(d.parameters[0][1].parameters[0], -2.5) assert_equal(d.parameters[0][1].parameters[1], 15) d.fit([(0, 0), (5, 0), (3, 0), (5, -5), (7, 0), (3, 0), (4, 0), (5, 0), (2, 20)], inertia=0.75) assert_not_equal(round(d.parameters[0][0].parameters[0], 4), 4.3889) assert_not_equal(round(d.parameters[0][0].parameters[1], 4), 1.9655) assert_not_equal(d.parameters[0][1].parameters[0], -2.5) assert_not_equal(d.parameters[0][1].parameters[1], 15) d = IndependentComponentsDistribution([NormalDistribution(5, 2), UniformDistribution(0, 10)]) d.summarize([(0, 0), (5, 0), (3, 0)]) d.summarize([(5, -5), (7, 0)]) d.summarize([(3, 0), (4, 0), (5, 0), (2, 20)]) d.from_summaries(inertia=0.5) assert_equal(round(d.parameters[0][0].parameters[0], 4), 4.3889) assert_equal(round(d.parameters[0][0].parameters[1], 4), 1.9655) assert_equal(d.parameters[0][1].parameters[0], -2.5) assert_equal(d.parameters[0][1].parameters[1], 15) d.freeze() d.fit([(1, 7), (7, 2), (2, 4), (2, 4), (1, 4)]) assert_equal(round(d.parameters[0][0].parameters[0], 4), 4.3889) assert_equal(round(d.parameters[0][0].parameters[1], 4), 1.9655) assert_equal(d.parameters[0][1].parameters[0], -2.5) assert_equal(d.parameters[0][1].parameters[1], 15) e = Distribution.from_json(d.to_json()) assert_equal(e.name, "IndependentComponentsDistribution") assert_equal(round(e.parameters[0][0].parameters[0], 4), 4.3889) assert_equal(round(e.parameters[0][0].parameters[1], 4), 1.9655) assert_equal(e.parameters[0][1].parameters[0], -2.5) assert_equal(e.parameters[0][1].parameters[1], 15) f = pickle.loads(pickle.dumps(e)) assert_equal(e.name, "IndependentComponentsDistribution") assert_equal(round(f.parameters[0][0].parameters[0], 4), 4.3889) assert_equal(round(f.parameters[0][0].parameters[1], 4), 1.9655) assert_equal(f.parameters[0][1].parameters[0], -2.5) assert_equal(f.parameters[0][1].parameters[1], 15) X = numpy.array([[0.5, 0.2, 0.7], [0.3, 0.1, 0.9], [0.4, 0.3, 0.8], [0.3, 0.3, 0.9], [0.3, 0.2, 0.6], [0.5, 0.2, 0.8]]) d = IndependentComponentsDistribution.from_samples(X, distributions=NormalDistribution) assert_almost_equal(d.parameters[0][0].parameters[0], 0.38333, 4) assert_almost_equal(d.parameters[0][0].parameters[1], 0.08975, 4) assert_almost_equal(d.parameters[0][1].parameters[0], 0.21666, 4) assert_almost_equal(d.parameters[0][1].parameters[1], 0.06872, 4) assert_almost_equal(d.parameters[0][2].parameters[0], 0.78333, 4) assert_almost_equal(d.parameters[0][2].parameters[1], 0.10672, 4) d = IndependentComponentsDistribution.from_samples(X, distributions=ExponentialDistribution) assert_almost_equal(d.parameters[0][0].parameters[0], 2.6087, 4) assert_almost_equal(d.parameters[0][1].parameters[0], 4.6154, 4) assert_almost_equal(d.parameters[0][2].parameters[0], 1.2766, 4) d = IndependentComponentsDistribution.from_samples(X, distributions=[NormalDistribution, NormalDistribution, NormalDistribution]) assert_almost_equal(d.parameters[0][0].parameters[0], 0.38333, 4) assert_almost_equal(d.parameters[0][0].parameters[1], 0.08975, 4) assert_almost_equal(d.parameters[0][1].parameters[0], 0.21666, 4) assert_almost_equal(d.parameters[0][1].parameters[1], 0.06872, 4) assert_almost_equal(d.parameters[0][2].parameters[0], 0.78333, 4) assert_almost_equal(d.parameters[0][2].parameters[1], 0.10672, 4) d = IndependentComponentsDistribution.from_samples(X, distributions=[NormalDistribution, LogNormalDistribution, ExponentialDistribution]) assert_almost_equal(d.parameters[0][0].parameters[0], 0.38333, 4) assert_almost_equal(d.parameters[0][0].parameters[1], 0.08975, 4) assert_almost_equal(d.parameters[0][1].parameters[0], -1.5898, 4) assert_almost_equal(d.parameters[0][1].parameters[1], 0.36673, 4) assert_almost_equal(d.parameters[0][2].parameters[0], 1.27660, 4)
def test_distributions_normal_underflow_log_probability(): d = NormalDistribution(5, 1e-10) assert_almost_equal(d.log_probability(1e100), -4.9999999999999987e+219)
from pomegranate import (
NaiveBayes,
NormalDistribution,
UniformDistribution,
ExponentialDistribution,
GeneralMixtureModel,
MultivariateGaussianDistribution,
BernoulliDistribution,
)
import pandas as pd
import numpy as np
X = pd.DataFrame({"A": [1, 0, 1, 0, 1], "B": [1, 1, 1, 1, 0]})
x = BernoulliDistribution(0.4)
vals = []
[vals.append(x.sample()) for i in range(1000)]
model = NaiveBayes([
NormalDistribution(5, 2),
UniformDistribution(0, 10),
ExponentialDistribution(1.0)
])
model.predict(np.array([[10]]))
model = GeneralMixtureModel.from_samples(MultivariateGaussianDistribution,
n_components=3,
X=X)
