def simpleTests():
test = range(10)
uf = UnionFind()
for t in test:
uf.makeSet(t)
# END for
for t in test:
assert uf.find(t) == t, "Parent not initialized correctly."
# END for
assert uf.countGroups() == 10, "Counted wrong number of groups."
uf.union(0,1)
assert uf.find(1) == 0, "Parent not updated correctly."
assert uf.data[0][1] == 1, "Order not updated for equal trees correctly."
assert uf.countGroups() == 9, "Counted wrong number of groups."
uf.union(1,2)
assert uf.find(2) == 0, "Parent not updated correctly."
assert uf.data[0][1] == 1, "Order not updated for unequal trees correctly."
assert uf.countGroups() == 8, "Counted wrong number of groups."
uf.union(3,4)
uf.union(4,5)
uf.union(0,3)
assert uf.data[0][1] == 2, "Order not updated for unequal trees."
assert uf.data[5][0] == 3, "Parent should not be updated until find operation."
assert uf.find(5) == 0, "Find operation returned wrong parent."
assert uf.data[5][0] == 0, "Parent should have been updated."
assert uf.countGroups() == 5, "Counted wrong number of groups."
class Kruskal:
def __init__(self, data):
nodes = int(data[0].split()[0])
self.ufSet = UnionFind()
for n in range(nodes):
self.ufSet.makeSet(n)
# END for
self.edges = []
for k in data[1:]:
row = map(int, k.strip().split())
self.edges.append((row[0] - 1, row[1] - 1, row[2]))
# END for
self.edges.sort(key=itemgetter(2))
# END __init__
def mstKruskal(self):
mst = []
l = 0
for edge in self.edges:
s1 = self.ufSet.find(edge[0])
s2 = self.ufSet.find(edge[1])
if s1 == s2:
continue
# END if
self.ufSet.union(edge[0], edge[1])
mst.append(edge)
l += edge[2]
# END for
self.mst = mst
return l
# END mstKruskal
def clusterKruskal(self, k):
print "Running Clustering, k={0}".format(k)
done = False
for edge in self.edges:
s1 = self.ufSet.find(edge[0])
s2 = self.ufSet.find(edge[1])
if s1 == s2:
continue
# END if
if not done:
self.ufSet.union(edge[0], edge[1])
else:
print "Smallest unallocated edge: {0}".format(edge)
return edge[2]
# END if
if self.ufSet.countGroups() == k:
done = True
class ClusterHamming:
def __init__(self, data):
(nodes, self.bits) = map(int, data.pop(0).split())
self.uf = UnionFind()
for n in range(nodes):
self.uf.makeSet(n)
# END for
self.hammingData = defaultdict(list)
for n in range(nodes):
s = data[n].replace(' ', '')
self.hammingData[s].append(n)
# END for
# END __init__
def flip(self, s, flipbits):
"""
Given an input string (s) and tuple of indices (flipbits), returns a new
string with bits at specified indices flipped.
The length of (flipbits) determines the resulting hamming distance.
"""
result = ''
for i, c in enumerate(s):
if i in flipbits:
if c == '1':
result += '0'
else:
result += '1'
else:
result += c
return result
# END flip
def getHammingPermutations(self, s, n):
"""
Generate permutations of s whose distance is less than or equal to n
"""
result = []
result.append(s)
for d in range(1, n + 1):
for flipbits in combinations(range(self.bits), d):
result.append(self.flip(s, flipbits))
# END for
# END for
return result
# END getHammingPermutations
def printSummary(self):
resultMap = defaultdict(list)
for k, v in self.hammingData.iteritems():
cluster = self.uf.find(v)
resultMap[cluster].append(k)
# END for
for k, v in resultMap.iteritems():
print "\n\nCluster {0}:".format(k)
for key in v:
print "\t{0}".format(key)
# END for
# END for
# END printSummary
def run(self, minDist):
data = copy(self.hammingData)
while data:
(nodeKey, refNodes) = data.popitem()
if len(refNodes) > 1:
for i in range(1, len(refNodes)):
self.uf.union(refNodes[0], refNodes[i])
# END for
# END for
nearestNodes = self.getHammingPermutations(nodeKey, minDist - 1)
for testNodeKey in nearestNodes:
if testNodeKey not in data:
continue
testNodes = self.hammingData[testNodeKey]
for n in testNodes:
if self.uf.find(n) == self.uf.find(refNodes[0]):
continue
self.uf.union(refNodes[0], n)
# END for
# END for
# END while
return self.uf.countGroups()
