def levenshtein_graph(reads, tau=1, **kwargs):
"""
Construct Levenshtein(tau) graph using naive O(N**2 d) algorithm
"""
import igraph as ig
import numpy as np
from Levenshtein import distance as levenshtein_dist
N = len(reads)
m = np.zeros((N, N), dtype=int)
for i in range(N):
for j in range(i):
dist = levenshtein_dist(reads[i], reads[j])
m[i, j] = m[j, i] = dist if dist <= tau else 0
# Be careful! Zero elements are not interpreted as zero-length edges
g = ig.Graph.Weighted_Adjacency(m.tolist(),
mode="UNDIRECTED",
attr="weight",
loops=False)
g.vs["read"] = reads
for attr_name, attr_data in kwargs.iteritems():
g.vs[attr_name] = attr_data
return g
def _find_by_vendor_levenshtein(cls, vendor):
matched_macs = []
for mac in cls._macs:
lev_dist = levenshtein_dist(vendor, mac.vendor.lower())
if lev_dist <= cls._levenshtein_max_dist_allowed:
matched_macs.append(mac)
return matched_macs
def _compute_block(self, seqs1, seqs2, origin):
origin_row, origin_col = origin
if seqs2 is not None:
# compute the full matrix
coord_iterator = itertools.product(enumerate(seqs1),
enumerate(seqs2))
else:
# compute only upper triangle in this case
coord_iterator = itertools.combinations_with_replacement(
enumerate(seqs1), r=2)
result = []
for (row, s1), (col, s2) in coord_iterator:
d = levenshtein_dist(s1, s2)
if d <= self.cutoff:
result.append((d + 1, origin_row + row, origin_col + col))
return result
def coord_generator():
for j, s2 in enumerate(seqs[i_row:], start=i_row):
d = levenshtein_dist(target, s2)
if d <= self.cutoff:
yield d + 1, j
