def two():
"""
Calculates largest value k such that there is a k-clustering
with spacing >= 3
"""
# Read in the file, converting to str of binary number
vert_df = pd.read_csv('clustering_big.txt',
header=0,
names=['vid'],
converters = {'vid' : strip})
vertices = vert_df['vid'].unique()
uf = UnionFind(vertices)
to_visit = set(vertices)
#
while len(to_visit) > 0:
# Every iteration of the while loop corresponds to
# pulling off a new vertex label and attempting to merge
# with all other vertices connected at cost <= 2
this_v = to_visit.pop()
nearby_v = nearby(this_v, to_visit)
for v in nearby_v:
l1 = uf[this_v]
l2 = uf[v]
if l1 != l2:
uf.union(this_v, v)
to_visit.remove(v)
return uf.numleaders()
def one():
mst = set([])
edge_df = pd.read_csv('clustering1.txt',
sep=" ",
header=0,
names=['v1','v2','cost'])
# Sort in order of least cost
edge_df.sort(['cost'], inplace=True)
edge_df.index = range(1,len(edge_df)+1)
# The unique set of vertices...
vertices = pd.concat([edge_df['v1'],
edge_df['v2']]).unique()
# Initialize the UnionFind structure with
# unmerged set of unique vertices
uf = UnionFind(vertices)
# Iterate through Kruskal's until the number
# of groups in the UnionFind struct is K
it = edge_df.iterrows()
while uf.numleaders() > K:
rec = next(it)[1]
v1 = rec['v1']
v2 = rec['v2']
cost = rec['cost']
edge = Edge(v1, v2, cost)
v1_lead = uf[v1]
v2_lead = uf[v2]
if v1_lead != v2_lead:
uf.union(v1, v2)
mst.add(edge)
# Now iterate to the next edge that would be added
# to form the K-1th cluster
cond = True
while cond:
rec = next(it)[1]
v1 = rec['v1']
v2 = rec['v2']
cost = rec['cost']
edge = Edge(v1, v2, cost)
v1_lead = uf[v1]
v2_lead = uf[v2]
cond = (v1_lead == v2_lead)
if not cond:
mks = cost
return mks
