def test_refine_empty_subgroup(self):
dataset = pd.DataFrame({'A': [1]})
condition = Condition('`A` == 2') # Condition matches 0 rows
seed = description_factory(condition, dataset)
descriptions = refine(dataset, [], seed)
self.assertEqual(1, len(descriptions), 'No refinements added')
def test_refine_duplicate_splits(self):
dataset = pd.DataFrame({'A': [0, 1, 1, 2]})
# With 3 equal-width bins, the splits will be duplicated. Splits at position 1 and 2
descriptions = refine(dataset, [], description_factory([], dataset))
# Shouldn't contain `A >= 1` and `A <= 1` twice
self.assertEqual(3, len(descriptions),
'Only contains unique inequalities')
def test_refine_boolean(self):
dataset = pd.DataFrame({'A': [True, False]})
descriptions = refine(dataset, [], description_factory([], dataset))
queries = [d.to_querystring() for d in descriptions]
self.assertEqual(len(descriptions), 3, 'Added 2 conditions')
self.assertEqual('`A` == 1' in queries, True,
'Added condition equal to True')
self.assertEqual('`A` == 0' in queries, True,
'Added condition equal to False')
def test_refine_numeric(self):
dataset = pd.DataFrame({'A': [1, 2, 3, 4]})
descriptions = refine(dataset, [], description_factory([], dataset))
queries = [d.to_querystring() for d in descriptions]
self.assertEqual(5, len(descriptions),
'Added 4 conditions (2 * (num_buckets - 1))')
self.assertIn('`A` <= 2', queries)
self.assertIn('`A` >= 2', queries)
self.assertIn('`A` <= 3', queries)
self.assertIn('`A` >= 3', queries)
def test_refine_nominal(self):
dataset = pd.DataFrame({'A': ['foo', 'bar', 'lex']})
descriptions = refine(dataset, [], description_factory([], dataset))
queries = [d.to_querystring() for d in descriptions]
self.assertEqual(7, len(descriptions), 'Added 4 conditions (2g)')
self.assertIn("`A` == 'foo'", queries, 'Added condition equal to g(1)')
self.assertIn("`A` != 'foo'", queries,
'Added condition not equal to g(1)')
self.assertIn("`A` == 'bar'", queries,
'Added condition equal to g(2))')
self.assertIn("`A` != 'bar'", queries,
'Added condition not equal to g(2)')
self.assertIn("`A` == 'lex'", queries,
'Added condition equal to g(3))')
self.assertIn("`A` != 'lex'", queries,
'Added condition not equal to g(3)')
def test_refine_unsupported_type(self):
dataset = pd.DataFrame({'A': [datetime.now()]
}) # No refinement implemented for dates
with self.assertRaises(NotImplementedError):
refine(dataset, [], description_factory([], dataset))
def beam_search(data, targets, quality_measure: QualityMeasure, options={}):
timer = Timer()
timer.start() # Keep track of execution time for debugging
set_options(options)
candidate_queue = Queue(maxsize=0)
candidate_queue.put(get_initial_seed(data))
result_set = MinPriorityQueue(max_size=config.RESULT_SET_SIZE)
# Print settings
print('Settings:')
for var in [x for x in dir(config) if not x.startswith('__')]:
print(f' {var}={getattr(config, var)}')
print('Setting-up quality measure...')
quality_measure.set_data(data)
print('Finding subgroups...')
for depth in range(0, config.SEARCH_DEPTH):
beam = MinPriorityQueue(max_size=config.BEAM_WIDTH)
while not candidate_queue.empty():
seed = candidate_queue.get().description
for description in refine(data, targets, seed):
coverage, quality = quality_measure.calculate(description)
# Check if the description satisfies the constraints
if not satisfies_all(description=description,
coverage=coverage,
quality=quality):
continue # Continue with next candidate description
result = Result(quality=quality, description=description)
# Check if the description is novel
if not result_set.contains(result):
result_set.put(result)
beam.put(result)
print(f'Best subgroups at depth {depth}:')
while not beam.empty():
candidate = beam.get(
) # Not sure about get(), pseudo code uses get_front_element()
print(
f'quality = {round(candidate.quality, 5)}, description = {candidate.description.to_querystring()}'
)
candidate_queue.put(candidate)
top_q = list(result_set)
top_q.reverse() # Sort by descending quality
print('Done.')
print(f'Finished in {round(timer.elapsed_time())} seconds.')
return top_q