def add_synset(self, word): ex = Extractor() word_id = md5.md5(word).hexdigest() if not self.fdb.get(word_id): self.fdb.set(ROOT + word_id, word) synset = ex.getWikiBacklinks(word) if synset: for synonym in synset: self.fdb.set(SYN + synonym.upper(), word_id)
def getWikiDist(self, a, b):
a = a.replace(' ', '_')
b = b.replace(' ', '_')
e = Extractor()
sa = e.getWikiBacklinks(a, filter = "nonredirects")
sb = e.getWikiBacklinks(b, filter = "nonredirects")
n1 = log(max(len(sa), len(sb)))
n2 = log(len(set.intersection(sa, sb)))
d1 = log(10 ** 7)
d2 = log(min(len(sa), len(sb)))
extra1 = extra2 = 0
#if a in sb: extra1 = log(10 ** 7 / len(sb))
#if b in sa: extra2 = log(10 ** 7 / len(sa))
try:
return (n1 - n2) / float(d1 - d2)
except ZeroDivisionError as e:
print e
return self.INF