def test_sample_empty_transformed_conditions():
"""Test that None is passed to ``_sample_batch`` if transformed conditions are empty.
The ``Sample`` method is expected to:
- Return sampled data and pass None to ``sample_batch`` as the
``transformed_conditions``.
Input:
- Number of rows to sample
- Conditions
Output:
- Sampled data
"""
# Setup
model = GaussianCopula()
data = pd.DataFrame({
'column1': list(range(100)),
'column2': list(range(100)),
'column3': list(range(100))
})
conditions = {'column1': 25}
conditions_series = pd.Series([25, 25, 25, 25, 25], name='column1')
model._sample_batch = Mock()
sampled = pd.DataFrame({
'column1': [28, 28],
'column2': [37, 37],
'column3': [93, 93],
})
model._sample_batch.return_value = sampled
model.fit(data)
model._metadata = Mock()
model._metadata.get_fields.return_value = ['column1', 'column2', 'column3']
model._metadata.transform.return_value = pd.DataFrame()
model._metadata.make_ids_unique.side_effect = lambda x: x
# Run
output = model.sample(5,
conditions=conditions,
graceful_reject_sampling=True)
# Assert
expected_output = pd.DataFrame({
'column1': [28, 28],
'column2': [37, 37],
'column3': [93, 93],
})
_, args, kwargs = model._metadata.transform.mock_calls[0]
pd.testing.assert_series_equal(args[0]['column1'], conditions_series)
assert kwargs['on_missing_column'] == 'drop'
model._metadata.transform.assert_called_once()
model._sample_batch.assert_called_with(5, 100, 10, conditions, None, 0.01)
pd.testing.assert_frame_equal(output, expected_output)
def test__sample_batch_zero_valid(self):
"""Test the `BaseTabularModel._sample_batch` method with zero valid rows.
Expect that the requested number of rows are returned, if the first `_sample_rows` call
returns zero valid rows, and the second one returns enough valid rows.
See https://github.com/sdv-dev/SDV/issues/285.
Input:
- num_rows = 5
- condition on `column1` = 2
Output:
- The requested number of sampled rows (5).
"""
# Setup
gaussian_copula = Mock(spec_set=GaussianCopula)
valid_sampled_data = pd.DataFrame({
"column1": [28, 28, 21, 1, 2],
"column2": [37, 37, 1, 4, 5],
"column3": [93, 93, 6, 4, 12],
})
gaussian_copula._sample_rows.side_effect = [(pd.DataFrame({}), 0),
(valid_sampled_data, 5)]
conditions = {
'column1': 2,
'column1': 2,
'column1': 2,
'column1': 2,
'column1': 2,
}
# Run
output = GaussianCopula._sample_batch(gaussian_copula,
num_rows=5,
conditions=conditions)
# Assert
assert gaussian_copula._sample_rows.call_count == 2
assert len(output) == 5
def test_sample_batches_transform_conditions_correctly():
"""Test that transformed conditions are batched correctly.
The ``Sample`` method is expected to:
- Return sampled data and call ``_sample_batch`` for every unique transformed
condition group.
Input:
- Number of rows to sample
- Conditions
Output:
- Sampled data
"""
# Setup
model = GaussianCopula()
data = pd.DataFrame({
'column1': list(range(100)),
'column2': list(range(100)),
'column3': list(range(100))
})
conditions = {'column1': [25, 25, 25, 30, 30]}
conditions_series = pd.Series([25, 25, 25, 30, 30], name='column1')
model._sample_batch = Mock()
expected_outputs = [
pd.DataFrame({
'column1': [25, 25, 25],
'column2': [37, 37, 37],
'column3': [93, 93, 93],
}),
pd.DataFrame({
'column1': [30],
'column2': [37],
'column3': [93],
}),
pd.DataFrame({
'column1': [30],
'column2': [37],
'column3': [93],
})
]
model._sample_batch.side_effect = expected_outputs
model.fit(data)
model._metadata = Mock()
model._metadata.get_fields.return_value = ['column1', 'column2', 'column3']
model._metadata.transform.return_value = pd.DataFrame(
[[50], [50], [50], [60], [70]], columns=['transformed_column'])
# Run
model.sample(5, conditions=conditions, graceful_reject_sampling=True)
# Assert
_, args, kwargs = model._metadata.transform.mock_calls[0]
pd.testing.assert_series_equal(args[0]['column1'], conditions_series)
assert kwargs['on_missing_column'] == 'drop'
model._metadata.transform.assert_called_once()
model._sample_batch.assert_any_call(3, 100, 10, {'column1': 25},
{'transformed_column': 50}, 0.01)
model._sample_batch.assert_any_call(1, 100, 10, {'column1': 30},
{'transformed_column': 60}, 0.01)
model._sample_batch.assert_any_call(1, 100, 10, {'column1': 30},
{'transformed_column': 70}, 0.01)
