def test_sample_conditions(self):
"""Test ``sample_conditions`` method.
Expect the correct args to be passed to ``_sample_conditions``.
Input:
- valid conditions
Side Effects:
- The expected ``_sample_conditions`` call.
"""
# Setup
model = Mock(spec_set=GaussianCopula)
condition = Condition(
{'column1': 'b'},
num_rows=5,
)
batch_size = 1
randomize_samples = False
output_file_path = 'test.csv'
# Run
out = GaussianCopula.sample_conditions(
model,
[condition],
batch_size=batch_size,
randomize_samples=False,
output_file_path=output_file_path,
)
# Assert
model._sample_conditions.assert_called_once_with(
[condition], 100, batch_size, randomize_samples, output_file_path)
assert out == model._sample_conditions.return_value
def test_conditional_sampling_constraint_uses_reject_sampling(
gm_mock, isinstance_mock):
"""Test that the ``sample`` method handles constraints with conditions.
The ``sample`` method is expected to properly apply constraint
transformations by dropping columns that cannot be conditonally sampled
on due to them being part of a constraint.
Setup:
- The model is being passed a ``UniqueCombination`` constraint and then
asked to sample with two conditions, one of which the constraint depends on.
The constraint is expected to skip its transformations since only some of
the columns are provided by the conditions and the model will use reject
sampling to meet the constraint instead.
Input:
- Conditions
Side Effects:
- Correct columns to condition on are passed to underlying sample method
"""
# Setup
isinstance_mock.side_effect = _isinstance_side_effect
constraint = FixedCombinations(column_names=['city', 'state'])
data = pd.DataFrame({
'city': ['LA', 'SF', 'CHI', 'LA', 'LA'],
'state': ['CA', 'CA', 'IL', 'CA', 'CA'],
'age': [27, 28, 26, 21, 30]
})
model = GaussianCopula(constraints=[constraint],
categorical_transformer='label_encoding')
sampled_numeric_data = [
pd.DataFrame({
'city#state.value': [0, 1, 2, 0, 0],
'age.value': [30, 30, 30, 30, 30]
}),
pd.DataFrame({
'city#state.value': [1],
'age.value': [30]
})
]
gm_mock.return_value.sample.side_effect = sampled_numeric_data
model.fit(data)
# Run
conditions = [Condition({'age': 30, 'state': 'CA'}, num_rows=5)]
sampled_data = model.sample_conditions(conditions=conditions)
# Assert
expected_transformed_conditions = {'age.value': 30}
expected_data = pd.DataFrame({
'city': ['LA', 'SF', 'LA', 'LA', 'SF'],
'state': ['CA', 'CA', 'CA', 'CA', 'CA'],
'age': [30, 30, 30, 30, 30]
})
sample_calls = model._model.sample.mock_calls
assert len(sample_calls) == 2
model._model.sample.assert_any_call(
50, conditions=expected_transformed_conditions)
pd.testing.assert_frame_equal(sampled_data, expected_data)
def test_conditional_sampling_two_conditions():
data = pd.DataFrame({
'column1': [1.0, 0.5, 2.5] * 10,
'column2': ['a', 'b', 'c'] * 10,
'column3': ['d', 'e', 'f'] * 10
})
model = GaussianCopula()
model.fit(data)
conditions = [Condition({'column2': 'b', 'column3': 'f'}, num_rows=5)]
samples = model.sample_conditions(conditions=conditions)
assert list(samples.column2) == ['b'] * 5
assert list(samples.column3) == ['f'] * 5
def test_conditional_sampling_dict():
data = pd.DataFrame({
'column1': [1.0, 0.5, 2.5] * 10,
'column2': ['a', 'b', 'c'] * 10
})
model = GaussianCopula()
model.fit(data)
conditions = [Condition({'column2': 'b'}, num_rows=30)]
sampled = model.sample_conditions(conditions=conditions)
assert sampled.shape == data.shape
assert set(sampled['column2'].unique()) == set(['b'])
def test_conditional_sampling_numerical():
data = pd.DataFrame({
'column1': [1.0, 0.5, 2.5] * 10,
'column2': ['a', 'b', 'c'] * 10,
'column3': ['d', 'e', 'f'] * 10
})
model = GaussianCopula()
model.fit(data)
conditions = [Condition({
'column1': 1.0,
}, num_rows=5)]
sampled = model.sample_conditions(conditions=conditions)
assert list(sampled.column1) == [1.0] * 5