def test_gaussian_copula():
users = load_demo(metadata=False)['users']
field_types = {
'age': {
'type': 'numerical',
'subtype': 'integer',
},
'country': {
'type': 'categorical'
}
}
anonymize_fields = {'country': 'country_code'}
gc = GaussianCopula(
field_names=['user_id', 'country', 'gender', 'age'],
field_types=field_types,
primary_key='user_id',
anonymize_fields=anonymize_fields,
categorical_transformer='one_hot_encoding',
)
gc.fit(users)
parameters = gc.get_parameters()
new_gc = GaussianCopula(
table_metadata=gc.get_metadata(),
categorical_transformer='one_hot_encoding',
)
new_gc.set_parameters(parameters)
sampled = new_gc.sample()
# test shape is right
assert sampled.shape == users.shape
# test user_id has been generated as an ID field
assert list(sampled['user_id']) == list(range(0, len(users)))
# country codes have been replaced with new ones
assert set(sampled.country.unique()) != set(users.country.unique())
metadata = gc.get_metadata().to_dict()
assert metadata['fields'] == {
'user_id': {
'type': 'id',
'subtype': 'integer'
},
'country': {
'type': 'categorical'
},
'gender': {
'type': 'categorical'
},
'age': {
'type': 'numerical',
'subtype': 'integer'
}
}
assert 'model_kwargs' in metadata
def test_set_parameters_negative_max_rows(self):
"""Test the ``set_parameters`` method with negative num_rows.
If the max rows value is negative, it is expected to be set
to zero.
The ``GaussianCopula.set_parameters`` method is expected to:
- Transform a flattened dict into its original form with
the unflatten_dict function.
- pass the unflattended dict to the ``self._rebuild_gaussian_copula``
method.
- Store ``0`` in the `self._num_rows` attribute.
- Create a GaussianMultivariate instance from the params dict
and store it in the 'self._model' attribute.
Input:
- flat parameters dict
Output:
- None
Side Effects:
- Call ``_rebuild_gaussian_copula`` with the unflatted dict.
- ``self._num_rows`` is set to ``0``.
- ``GaussianMultivariate`` is called
- ``GaussianMultivariate`` return value is stored as `self._model`
"""
# Setup
gaussian_copula = Mock(autospec=GaussianCopula)
returned = {
'univariates': [{
'scale':
1.0,
'loc':
5,
'type':
'copulas.univariate.gaussian.GaussianUnivariate'
}],
'columns': ['foo'],
'num_rows':
-3,
'covariance': [[0.4, 0.17], [0.17, 0.07]]
}
gaussian_copula._rebuild_gaussian_copula.return_value = returned
# Run
flatten_parameters = {
'univariates__foo__scale': 0.0,
'univariates__foo__loc': 5,
'covariance__0__0': 0.1,
'covariance__1__0': 0.4,
'covariance__1__1': 0.1,
'num_rows': -3
}
GaussianCopula.set_parameters(gaussian_copula, flatten_parameters)
# Asserts
expected = {
'covariance': [[0.1], [0.4, 0.1]],
'num_rows': -3,
'univariates': {
'foo': {
'loc': 5,
'scale': 0.0
}
}
}
gaussian_copula._rebuild_gaussian_copula.assert_called_once_with(
expected)
assert gaussian_copula._num_rows == 0
assert isinstance(gaussian_copula._model, GaussianMultivariate)
def test_gaussian_copula():
users = load_demo(metadata=False)['users']
field_types = {
'age': {
'type': 'numerical',
'subtype': 'integer',
},
'country': {
'type': 'categorical'
}
}
anonymize_fields = {'country': 'country_code'}
# If distribution is non parametric, get_parameters fails
gc = GaussianCopula(
field_names=['user_id', 'country', 'gender', 'age'],
field_types=field_types,
primary_key='user_id',
anonymize_fields=anonymize_fields,
field_distributions={'age': 'gamma'},
default_distribution='gaussian_kde',
)
gc.fit(users)
with pytest.raises(NonParametricError):
parameters = gc.get_parameters()
# If distribution is parametric, copula can be recreated
gc = GaussianCopula(
field_names=['user_id', 'country', 'gender', 'age'],
field_types=field_types,
primary_key='user_id',
anonymize_fields=anonymize_fields,
field_distributions={'age': 'gamma'},
default_distribution='bounded',
)
gc.fit(users)
parameters = gc.get_parameters()
new_gc = GaussianCopula(table_metadata=gc.get_metadata(), )
new_gc.set_parameters(parameters)
# Validate sampled dat
sampled = new_gc.sample()
# test shape is right
assert sampled.shape == users.shape
# test user_id has been generated as an ID field
assert list(sampled['user_id']) == list(range(0, len(users)))
# country codes have been replaced with new ones
assert set(sampled.country.unique()) != set(users.country.unique())
# Validate metadata
metadata = gc.get_metadata().to_dict()
assert metadata['fields'] == {
'user_id': {
'type': 'id',
'subtype': 'integer',
'transformer': 'integer',
},
'country': {
'type': 'categorical',
'pii': True,
'pii_category': 'country_code',
'transformer': 'one_hot_encoding',
},
'gender': {
'type': 'categorical',
'transformer': 'one_hot_encoding',
},
'age': {
'type': 'numerical',
'subtype': 'integer',
'transformer': 'integer',
}
}
assert 'model_kwargs' in metadata
assert 'GaussianCopula' in metadata['model_kwargs']
