def test_fit_default_distribution(self):
"""On fit, a distribution is created for each column along the covariance and means"""
copula = GaussianMultivariate(GaussianUnivariate)
copula.fit(self.data)
for i, key in enumerate(self.data.columns):
assert copula.columns[i] == key
assert copula.univariates[i].__class__ == GaussianUnivariate
assert copula.univariates[i]._params['loc'] == self.data[key].mean()
assert copula.univariates[i]._params['scale'] == np.std(self.data[key])
expected_covariance = copula._get_covariance(self.data)
assert (copula.covariance == expected_covariance).all().all()
def test__get_covariance_numpy_array(self):
"""_get_covariance computes the covariance matrix of normalized values."""
# Setup
copula = GaussianMultivariate()
copula.fit(self.data.values)
expected_covariance = np.array([[1.04347826, -0.01316681, -0.20683455],
[-0.01316681, 1.04347826, -0.176307],
[-0.20683455, -0.176307, 1.04347826]])
# Run
covariance = copula._get_covariance(self.data.values)
# Check
assert np.isclose(covariance, expected_covariance).all().all()
def test__get_covariance(self):
"""_get_covariance computes the covariance matrix of normalized values."""
# Setup
copula = GaussianMultivariate(GaussianUnivariate)
copula.fit(self.data)
expected_covariance = np.array([[1., -0.01261819, -0.19821644],
[-0.01261819, 1., -0.16896087],
[-0.19821644, -0.16896087, 1.]])
# Run
covariance = copula._get_covariance(self.data)
# Check
assert np.isclose(covariance, expected_covariance).all().all()
def test_fit_numpy_array(self):
"""Fit should work indistinctly with numpy arrays and pandas dataframes """
# Setup
copula = GaussianMultivariate(
distribution='copulas.univariate.gaussian.GaussianUnivariate')
# Run
copula.fit(self.data.values)
# Check
for key, (column, univariate) in enumerate(zip(self.data.columns, copula.univariates)):
assert univariate._params['loc'] == np.mean(self.data[column])
assert univariate._params['scale'] == np.std(self.data[column])
expected_covariance = copula._get_covariance(pd.DataFrame(self.data.values))
assert (copula.covariance == expected_covariance).all().all()
def test_fit(self):
"""On fit, a distribution is created for each column along the covariance and means"""
# Setup
copula = GaussianMultivariate()
# Run
copula.fit(self.data)
# Check
for key in self.data.columns:
assert copula.distribs[key]
assert copula.distribs[key].mean == self.data[key].mean()
assert copula.distribs[key].std == np.std(self.data[key])
expected_covariance = copula._get_covariance(self.data)
assert (copula.covariance == expected_covariance).all().all()
def test_fit_numpy_array(self):
"""Fit should work indistinctly with numpy arrays and pandas dataframes """
# Setup
copula = GaussianMultivariate()
# Run
copula.fit(self.data.values)
# Check
for key, column in enumerate(self.data.columns):
assert copula.distribs[key]
assert copula.distribs[key].mean == np.mean(self.data[column])
assert copula.distribs[key].std == np.std(self.data[column])
expected_covariance = copula._get_covariance(
pd.DataFrame(self.data.values))
assert (copula.covariance == expected_covariance).all().all()
def test_fit_distribution_arg(self):
"""On fit, the distributions for each column use instances of copula.distribution."""
# Setup
distribution = 'copulas.univariate.gaussian_kde.GaussianKDE'
copula = GaussianMultivariate(distribution=distribution)
# Run
copula.fit(self.data)
# Check
assert copula.distribution == 'copulas.univariate.gaussian_kde.GaussianKDE'
for i, key in enumerate(self.data.columns):
assert copula.columns[i] == key
assert get_qualified_name(copula.univariates[i].__class__) == copula.distribution
expected_covariance = copula._get_covariance(self.data)
assert (copula.covariance == expected_covariance).all().all()
def test_to_dict(self):
"""To_dict returns the parameters to replicate the copula."""
# Setup
copula = GaussianMultivariate()
copula.fit(self.data)
# Run
result = copula.to_dict()
# Asserts
assert result['type'] == 'copulas.multivariate.gaussian.GaussianMultivariate'
assert result['columns'] == ['column1', 'column2', 'column3']
assert len(result['univariates']) == 3
expected_cov = copula._get_covariance(self.data).to_numpy().tolist()
np.testing.assert_equal(result['covariance'], expected_cov)
for univariate, result_univariate in zip(copula.univariates, result['univariates']):
assert univariate.to_dict() == result_univariate
def test_fit_distribution_arg(self):
"""On fit, the distributions for each column use instances of copula.distribution."""
# Setup
distribution = 'copulas.univariate.kde.KDEUnivariate'
copula = GaussianMultivariate(distribution=distribution)
# Run
copula.fit(self.data)
# Check
assert copula.distribution == 'copulas.univariate.kde.KDEUnivariate'
for key in self.data.columns:
assert key in copula.distribs
assert get_qualified_name(
copula.distribs[key].__class__) == copula.distribution
expected_covariance = copula._get_covariance(self.data)
assert (copula.covariance == expected_covariance).all().all()
def test_fit_default_distribution(self):
"""On fit, a distribution is created for each column along the covariance and means"""
# Setup
copula = GaussianMultivariate()
# Run
copula.fit(self.data)
# Check
assert copula.distribution == 'copulas.univariate.gaussian.GaussianUnivariate'
for key in self.data.columns:
assert key in copula.distribs
assert get_qualified_name(
copula.distribs[key].__class__) == copula.distribution
assert copula.distribs[key].mean == self.data[key].mean()
assert copula.distribs[key].std == np.std(self.data[key])
expected_covariance = copula._get_covariance(self.data)
assert (copula.covariance == expected_covariance).all().all()
