def _get_parameters(self):
"""Get copula model parameters.
Compute model ``covariance`` and ``distribution.std``
before it returns the flatten dict.
Returns:
dict:
Copula parameters.
Raises:
NonParametricError:
If a non-parametric distribution has been used.
"""
for univariate in self._model.univariates:
if type(univariate) is copulas.univariate.Univariate:
univariate = univariate._instance
if univariate.PARAMETRIC == copulas.univariate.ParametricType.NON_PARAMETRIC:
raise NonParametricError(
"This GaussianCopula uses non parametric distributions")
params = self._model.to_dict()
covariance = list()
for index, row in enumerate(params['covariance'][1:]):
covariance.append(row[:index + 1])
params['covariance'] = covariance
params['univariates'] = dict(
zip(params.pop('columns'), params['univariates']))
return flatten_dict(params)
def get_parameters(self):
"""Get copula model parameters.
Compute model ``covariance`` and ``distribution.std``
before it returns the flatten dict.
Returns:
dict:
Copula flatten parameters.
"""
values = list()
triangle = np.tril(self.model.covariance)
for index, row in enumerate(triangle.tolist()):
values.append(row[:index + 1])
self.model.covariance = np.array(values)
params = self.model.to_dict()
univariates = dict()
for name, univariate in zip(params.pop('columns'),
params['univariates']):
univariates[name] = univariate
if 'scale' in univariate:
scale = univariate['scale']
if scale == 0:
scale = EPSILON
univariate['scale'] = np.log(scale)
params['univariates'] = univariates
return flatten_dict(params)
def get_parameters(self):
"""Get copula model parameters.
Compute model ``covariance`` and ``distribution.std``
before it returns the flatten dict.
Returns:
dict:
Copula parameters.
Raises:
NonParametricError:
If a non-parametric distribution has been used.
"""
params = self._model.to_dict()
covariance = list()
for index, row in enumerate(params['covariance']):
covariance.append(row[:index + 1])
univariates = dict()
for name, univariate in zip(params.pop('columns'),
params['univariates']):
univariates[name] = univariate
if 'scale' in univariate:
scale = univariate['scale']
if scale == 0:
scale = copulas.EPSILON
univariate['scale'] = np.log(scale)
params['univariates'] = univariates
params['num_rows'] = self._num_rows
return flatten_dict(params)
def get_parameters(self, flatten=False):
"""Get copula model parameters.
Compute model ``covariance`` and ``distribution.std``
before it returns the flatten dict.
Args:
flatten (bool):
Whether to flatten the parameters or not before
returning them.
Returns:
dict:
Copula parameters.
"""
parameters = self._model.to_dict()
parameters['num_rows'] = self._num_rows
if not flatten:
return parameters
values = list()
triangle = np.tril(self._model.covariance)
for index, row in enumerate(triangle.tolist()):
values.append(row[:index + 1])
self._model.covariance = np.array(values)
params = self._model.to_dict()
univariates = dict()
for name, univariate in zip(params.pop('columns'),
params['univariates']):
univariates[name] = univariate
if 'scale' in univariate:
scale = univariate['scale']
if scale == 0:
scale = copulas.EPSILON
univariate['scale'] = np.log(scale)
params['univariates'] = univariates
return flatten_dict(params)
def test_flatten_dict_with_prefix():
"""Test get flatten dict with some result."""
# Run
nested = {
'foo': 'value',
'bar': {'bar_dict': 'value_bar_dict'},
'tar': ['value_tar_list_0', 'value_tar_list_1'],
'fitted': 'value_1',
'distribution': 'value_2',
'type': 'value_3'
}
result = flatten_dict(nested, prefix='test')
# Asserts
expected = {
'test__foo': 'value',
'test__bar__bar_dict': 'value_bar_dict',
'test__tar__0': 'value_tar_list_0',
'test__tar__1': 'value_tar_list_1'
}
assert result == expected
