def clustering(n, input_data):
"""
args: input_data
input_data = {'0000100110': [1,2], '0110101100': [3,4] ,
'1000100110' : [5], ... }
"""
uf = UF(n)
input_dict = {k: v for k, v in input_data.items()}
# Merge all 0 distance
for bin_str, u_vertices in input_dict.items():
try:
input_dict[bin_str]
except KeyError:
continue
else:
v_vertices = input_dict[bin_str]
for u in u_vertices:
for v in v_vertices:
if (uf.find(u - 1) != uf.find(v - 1)):
uf.union(u - 1, v - 1)
# Merge all 1 distance
for bin_str, u_vertices in input_dict.items():
one_comb = compute_one_distance(bin_str)
for node in one_comb:
try:
input_dict[node]
except KeyError:
continue
else:
v_vertices = input_dict[node]
for u in u_vertices:
for v in v_vertices:
if (uf.find(u - 1) != uf.find(v - 1)):
uf.union(u - 1, v - 1)
# Merge all 2 distances
for bin_str, u_vertices in input_dict.items():
two_comb = compute_two_distance(bin_str)
for node in two_comb:
try:
input_dict[node]
except KeyError:
continue
else:
v_vertices = input_dict[node]
for u in u_vertices:
for v in v_vertices:
if uf.find(u - 1) != uf.find(v - 1):
uf.union(u - 1, v - 1)
return len(uf.get_clusters())
