def test_empty_dataset_and_empty_attribute_set(self):
self._dataset = DummyEmptyDataset()
self._df_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
self._attribute_set = AttributeSet()
with self.assertRaises(ValueError):
self.check_entropy_result(WONT_COMPUTE)
class TestBestConditionalEntropic(unittest.TestCase):
def setUp(self):
self._attribute_set = AttributeSet(ATTRIBUTES)
self._dataset = DummyCleanDataset()
self._df_w_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
def test_best_conditional_entropic_attribute(self):
# This will just take the first attribute which is sufficient as it has
# unique values
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser, current_attributes=AttributeSet(),
candidate_attributes=self._attribute_set)
self.assertEqual(best_cond_ent_attr[0], ATTRIBUTES[1])
def test_best_conditional_entropic_attribute_all_taken(self):
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=self._attribute_set,
candidate_attributes=self._attribute_set)
self.assertIsNone(best_cond_ent_attr[0])
def test_best_conditional_entropic_attribute_empty_attribute_set(self):
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=AttributeSet({ATTRIBUTES[0], ATTRIBUTES[1]}),
candidate_attributes=AttributeSet())
self.assertIsNone(best_cond_ent_attr[0])
def test_best_conditional_entropic_attribute_empty_dataset(self):
self._dataset = DummyEmptyDataset()
self._df_w_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
with self.assertRaises(ValueError):
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=AttributeSet({ATTRIBUTES[0],
ATTRIBUTES[1]}),
candidate_attributes=self._attribute_set)
def test_best_conditional_entropic_attribute_empty_parameters(self):
self._dataset = DummyEmptyDataset()
self._df_w_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=AttributeSet({ATTRIBUTES[0], ATTRIBUTES[1]}),
candidate_attributes=AttributeSet())
self.assertIsNone(best_cond_ent_attr[0])
def test_best_conditional_entropic_attribute_unexistent_attribute(self):
self._attribute_set.add(UNEXISTENT_ATTRIBUTE)
with self.assertRaises(KeyError):
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=AttributeSet({ATTRIBUTES[0],
ATTRIBUTES[1]}),
candidate_attributes=self._attribute_set)
def test_best_conditional_entropic_attribute_empty_parameters(self):
self._dataset = DummyEmptyDataset()
self._df_w_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=AttributeSet({ATTRIBUTES[0], ATTRIBUTES[1]}),
candidate_attributes=AttributeSet())
self.assertIsNone(best_cond_ent_attr[0])
def test_best_conditional_entropic_attribute_empty_dataset(self):
self._dataset = DummyEmptyDataset()
self._df_w_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
with self.assertRaises(ValueError):
best_cond_ent_attr = _best_conditional_entropic_attribute(
self._df_w_one_fp_per_browser,
current_attributes=AttributeSet({ATTRIBUTES[0],
ATTRIBUTES[1]}),
candidate_attributes=self._attribute_set)
class TestAttributeSetEntropyFunction(unittest.TestCase):
def setUp(self):
self._dataset = DummyCleanDataset()
self._df_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
self._attribute_set = AttributeSet(ATTRIBUTES)
def check_entropy_result(self, expected_entropy: float):
computed_entropy = attribute_set_entropy(self._df_one_fp_per_browser,
self._attribute_set)
self.assertAlmostEqual(expected_entropy, computed_entropy)
def test_empty_dataset_and_empty_attribute_set(self):
self._dataset = DummyEmptyDataset()
self._df_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
self._attribute_set = AttributeSet()
with self.assertRaises(ValueError):
self.check_entropy_result(WONT_COMPUTE)
def test_empty_dataset(self):
self._dataset = DummyEmptyDataset()
self._df_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
with self.assertRaises(ValueError):
self.check_entropy_result(WONT_COMPUTE)
def test_empty_attribute_set(self):
self._attribute_set = AttributeSet()
with self.assertRaises(ValueError):
self.check_entropy_result(WONT_COMPUTE)
def test_unexistent_attribute(self):
self._attribute_set.add(UNEXISTENT_ATTRIBUTE)
with self.assertRaises(KeyError):
self.check_entropy_result(WONT_COMPUTE)
def test_always_the_same_value(self):
self._attribute_set = AttributeSet([ATTRIBUTES[2]])
self.check_entropy_result(0.0)
def test_in_between_entropy(self):
self._attribute_set = AttributeSet([ATTRIBUTES[0]])
expected_entropy = -1 * ((1/5)*log2(1/5) + (2/5)*log2(2/5)
+ (2/5)*log2(2/5))
self.check_entropy_result(expected_entropy)
def test_unique_values(self):
self._attribute_set = AttributeSet([ATTRIBUTES[1]])
expected_entropy = log2(len(self._dataset.dataframe))
self.check_entropy_result(expected_entropy)
def test_get_best_entropic_attribute_empty_candidates_and_dataset(self):
empty_dataset = DummyEmptyDataset()
result = _get_best_conditional_entropic_attribute(
empty_dataset, current_attributes=AttributeSet({ATTRIBUTES[0],
ATTRIBUTES[1]}),
candidate_attributes=AttributeSet())
self.assertIsNone(result)
def test_empty_dataset_and_attributes(self):
self._dataset = DummyEmptyDataset()
self._attributes = AttributeSet({})
grouped_by_browser = self._get_grouped_by_browser()
attributes_instability = _compute_attributes_instability(
grouped_by_browser, self._attributes)
expected_result = {}
self.assertDictEqual(expected_result, attributes_instability)
def test_get_best_entropic_attribute_empty_dataset(self):
empty_dataset = DummyEmptyDataset()
with self.assertRaises(ValueError):
_get_best_conditional_entropic_attribute(
empty_dataset,
current_attributes=AttributeSet({ATTRIBUTES[0],
ATTRIBUTES[1]}),
candidate_attributes=self._attribute_set)
def test_empty_dataset_and_attributes(self):
self._dataset = DummyEmptyDataset()
self._dataframe = self._dataset.dataframe
self._attributes = AttributeSet({})
attributes_avg_size = _compute_attribute_avg_size(
self._dataset, self._attributes)
expected_result = self._get_expected_result()
self.assertDictEqual(expected_result, attributes_avg_size)
def test_empty_dataset(self):
self._dataset = DummyEmptyDataset()
grouped_by_browser = self._get_grouped_by_browser()
attributes_instability = _compute_attributes_instability(
grouped_by_browser, self._attributes)
expected_result = {
ATTRIBUTES[0]: 0.0,
ATTRIBUTES[1]: 0.0,
ATTRIBUTES[2]: 0.0
}
self.assertDictEqual(expected_result, attributes_instability)
def setUp(self):
self._dummy_fp_dataset = DummyFingerprintDataset()
self._empty_dataset = DummyEmptyDataset()
self._clean_dataset = DummyCleanDataset()
def setUp(self):
self._dataset = DummyCleanDataset()
self._df_one_fp_per_browser = (
self._dataset.get_df_w_one_fp_per_browser())
self._attribute_set = AttributeSet(ATTRIBUTES)
def test_empty_dataset(self):
self._dataset = DummyEmptyDataset()
with self.assertRaises(ValueError):
self.check_entropy_result(WONT_COMPUTE)
def test_empty_dataset(self):
self._dataset = DummyEmptyDataset()
self._check_result()
def test_empty_dataset(self):
self._dataset = DummyEmptyDataset()
with self.assertRaises(KeyError): # Attribute is not in the dataset
_compute_attribute_avg_size(self._dataset.dataframe,
self._attributes)
def test_empty_dataset_and_empty_attribute_set(self):
self._dataset = DummyEmptyDataset()
self._attribute_set = AttributeSet()
with self.assertRaises(ValueError):
self.check_unicity_result(WONT_COMPUTE)
def test_empty_dataset(self):
empty_dataset = DummyEmptyDataset()
expected_result = {}
analysis = ProportionOfChanges(empty_dataset)
analysis.execute()
self.assertDictEqual(expected_result, analysis.result)