def test_to_dict_from_dict(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
params = model.to_dict()
model2 = GaussianMultivariate.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 set_parameters(self, parameters):
"""Set copula model parameters.
Add additional keys after unflatte the parameters
in order to set expected parameters for the copula.
Args:
dict:
Copula flatten parameters.
"""
parameters = unflatten_dict(parameters)
parameters.setdefault('fitted', True)
parameters.setdefault('distribution', self.distribution)
parameters = self._unflatten_gaussian_copula(parameters)
self.model = GaussianMultivariate.from_dict(parameters)
def _gaussian(self, dataset):
"""
For the given dataset, this runs "everything but the kitchen sink" (i.e.
every feature of GaussianMultivariate that is officially supported) and
makes sure it doesn't crash.
"""
model = GaussianMultivariate({
dataset.columns[0]: GaussianKDE() # Use a KDE for the first column
})
model.fit(dataset)
for N in [10, 100, 50]:
assert len(model.sample(N)) == N
sampled_data = model.sample(10)
pdf = model.probability_density(sampled_data)
cdf = model.cumulative_distribution(sampled_data)
# Test Save/Load from Dictionary
config = model.to_dict()
model2 = GaussianMultivariate.from_dict(config)
for N in [10, 100, 50]:
assert len(model2.sample(N)) == N
pdf2 = model2.probability_density(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
path_to_model = os.path.join(self.test_dir.name, "model.pkl")
model.save(path_to_model)
model2 = GaussianMultivariate.load(path_to_model)
for N in [10, 100, 50]:
assert len(model2.sample(N)) == N
pdf2 = model2.probability_density(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
