def search_hash(h1, arr):
lowest = -math.inf
for index, h in enumerate(arr):
hamming = hamming_distance(h1, h)
if h != h1 and hamming > lowest:
result = h
lowest = hamming
lowest_idx = index
return [lowest, lowest_idx, result]
def hamming_dist(self, x, y):
'''
:param x: hex_str, e.g. 'f012d208' (a 32bits binary code)
:param y: list, whose elements are hex_str
:return: list
'''
results = [None] * len(y)
for idx, yi in enumerate(y):
results[idx] = hamming_distance(x, yi)
return results
def hammingsimilarity_countingsort(self, x, y, max_dist, threshold):
'''
jointly compute hamming distance and counting sort
return the sorting results, and the top result whose distances are less than the threshold
:param x: hex_str, e.g. 'f012d208' (a 32bits binary code)
:param y: list, whose elements are hex_str
:param max_dist: int, equal to code length
:param threshold: int, the samples with distances less than it should be further refined
'''
# compute hamming distance and counting sort
results = [[] for _ in range(max_dist + 1)]
for idx, yi in enumerate(y):
hamming_distance(x, yi)
results[hamming_distance(x, yi)].append(idx)
# return final sorting result and topk sorting result
final_result = []
for idx, value in enumerate(results):
final_result += value
top_result = None
if idx == threshold:
top_result = copy.deepcopy(final_result)
return top_result, final_result
def func(x, sub_y, start_idx, suby_len):
result = [None for _ in range(suby_len)]
for idx, yi in enumerate(sub_y):
result[idx] = (hamming_distance(x, yi), start_idx + idx)
return result
def all_hamming(h1, arr):
result = []
for h in arr:
result.append(hamming_distance(h1, h))
return result
def test_hamming_distance_errors(hex1, hex2, exception, msg):
with pytest.raises(exception) as excinfo:
_ = hamming_distance(hex1, hex2)
assert msg in str(excinfo.value)
def test_hamming_distance(hex1, hex2, expected):
assert hamming_distance(hex1, hex2) == expected
