def setUp(self):
# Set a random seed so hash functions are always the same
random.seed(0)
self.family = lsh.HammingDistanceFamily(20)
self.dist_thres = 5
def f(a, b):
assert len(a) == len(b)
return sum(1 for i in range(len(a)) if a[i] != b[i])
self.dist_fn = f
def __init__(self, dist_thres, probe_length):
"""
Args:
dist_thres: only call two probes near-duplicates if their
Hamming distance is within this value; this should be
equal to or commensurate with (but not greater than)
the number of mismatches at/below which a probe is
considered to hybridize to a target sequence so that
candidate probes further apart than this value are not
collapsed as near-duplicates
probe_length: length of probes
"""
super().__init__(k=20)
self.lsh_family = lsh.HammingDistanceFamily(probe_length)
self.dist_thres = dist_thres
def hamming_dist(a, b):
# a and b are probe.Probe objects
return a.mismatches(b)
self.dist_fn = hamming_dist
def setUp(self):
# Set a random seed so hash functions are always the same
random.seed(0)
self.family = lsh.HammingDistanceFamily(20)