class SuperBase:
superbase = None
lematizer = None
def __init__(self, lemat_dict_file):
self.lematizer = Lematizer(lemat_dict_file)
self.superbase = UnionFind()
lemats = self.lematizer.all_lemats()
for l in lemats:
self.superbase.make_set(l)
for (_, lems) in self.lematizer.items():
sofar = None
for l in lems:
if sofar:
self.superbase.union(sofar, l)
sofar = self.superbase.find(l)
def __getitem__(self, word):
try:
# trick
for lem in self.lematizer[word]:
break
# confused?
# above code is the best way I know to extract an element from the set
return self.superbase.find(lem)
except KeyError:
return word
def items(self):
return ((w, self[w]) for (w, _) in self.lematizer.items())
def kruskal_mst(self):
assert self.is_connected(), "Can only find MST of a connected graph"
uf = UnionFind()
mst = set()
for v in self.vs:
uf.make_set(v)
half = set()
for u, v in sorted(self.es):
if (v, u) not in half:
half.add((u, v))
w = 0
vs = set()
for u, v in sorted(half, key = lambda e : self.weights[e]):
if len(vs) == len(self.vs):
return mst, w
if uf.find_set(u) != uf.find_set(v):
uf.union(u, v)
mst.add((u, v))
vs.add(u)
vs.add(v)
w += self.weights[(u, v)]