def test_valid_serialization_unfit_model(self):
"""For a unfitted model to_dict and from_dict are opposites."""
# Setup
instance = GaussianKDE()
# Run
result = GaussianKDE.from_dict(instance.to_dict())
# Check
assert instance.to_dict() == result.to_dict()
def test_valid_serialization_fit_model(self):
"""For a fitted model to_dict and from_dict are opposites."""
# Setup
instance = GaussianKDE()
X = np.array([1, 2, 3, 4])
instance.fit(X)
# Run
result = GaussianKDE.from_dict(instance.to_dict())
# Check
assert instance.to_dict() == result.to_dict()
def test_to_dict(self, kde_mock):
"""To_dict returns the defining parameters of a distribution in a dict."""
# Setup
column = np.array([[
0.4967141530112327, -0.13826430117118466, 0.6476885381006925,
1.5230298564080254, -0.23415337472333597, -0.23413695694918055,
1.5792128155073915, 0.7674347291529088, -0.4694743859349521,
0.5425600435859647
]])
kde_instance_mock = kde_mock.return_value
kde_instance_mock.dataset = column
kde_instance_mock.resample.return_value = column
distribution = GaussianKDE()
distribution.fit(column)
expected_result = {
'type':
'copulas.univariate.gaussian_kde.GaussianKDE',
'fitted':
True,
'dataset': [[
0.4967141530112327, -0.13826430117118466, 0.6476885381006925,
1.5230298564080254, -0.23415337472333597, -0.23413695694918055,
1.5792128155073915, 0.7674347291529088, -0.4694743859349521,
0.5425600435859647
]],
}
# Run
result = distribution.to_dict()
# Check
compare_nested_dicts(result, expected_result)
def test_to_dict_sample_size(self):
model = GaussianKDE(sample_size=10)
model.fit(self.constant)
params = model.to_dict()
assert params['type'] == 'copulas.univariate.gaussian_kde.GaussianKDE'
assert len(params['dataset']) == 10
def test_to_dict_constant(self):
model = GaussianKDE()
model.fit(self.constant)
params = model.to_dict()
assert params == {
'type': 'copulas.univariate.gaussian_kde.GaussianKDE',
'dataset': [5] * 100
}
def test_to_dict_from_dict(self):
model = GaussianKDE()
model.fit(self.data)
sampled_data = model.sample(50)
params = model.to_dict()
model2 = GaussianKDE.from_dict(params)
pdf = model.probability_density(sampled_data)
pdf2 = model2.probability_density(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
cdf = model.cumulative_distribution(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
def test_to_dict_from_dict_constant(self):
model = GaussianKDE()
model.fit(self.constant)
sampled_data = model.sample(50)
pdf = model.probability_density(sampled_data)
cdf = model.cumulative_distribution(sampled_data)
params = model.to_dict()
model2 = GaussianKDE.from_dict(params)
np.testing.assert_equal(np.full(50, 5), sampled_data)
np.testing.assert_equal(np.full(50, 5), model2.sample(50))
np.testing.assert_equal(np.full(50, 1), pdf)
np.testing.assert_equal(np.full(50, 1), model2.probability_density(sampled_data))
np.testing.assert_equal(np.full(50, 1), cdf)
np.testing.assert_equal(np.full(50, 1), model2.cumulative_distribution(sampled_data))
def test_to_dict(self):
"""To_dict returns the defining parameters of a distribution in a dict."""
# Setup
distribution = GaussianKDE()
column = np.array([[
0.4967141530112327, -0.13826430117118466, 0.6476885381006925,
1.5230298564080254, -0.23415337472333597, -0.23413695694918055,
1.5792128155073915, 0.7674347291529088, -0.4694743859349521,
0.5425600435859647
]])
distribution.fit(column)
expected_result = {
'type':
'copulas.univariate.gaussian_kde.GaussianKDE',
'fitted':
True,
'constant_value':
None,
'd':
1,
'n':
10,
'dataset': [[
0.4967141530112327, -0.13826430117118466, 0.6476885381006925,
1.5230298564080254, -0.23415337472333597, -0.23413695694918055,
1.5792128155073915, 0.7674347291529088, -0.4694743859349521,
0.5425600435859647
]],
'covariance': [[0.20810696044195218]],
'factor':
0.6309573444801932,
'inv_cov': [[4.805221304834407]]
}
# Run
result = distribution.to_dict()
# Check
compare_nested_dicts(result, expected_result)
