def _all_pairs_similarity(self, machine1, machine2):
words1 = set(
MachineTraverser.get_nodes(machine1, exclude_words=self.stopwords))
words2 = set(
MachineTraverser.get_nodes(machine2, exclude_words=self.stopwords))
pair_sims_by_word = defaultdict(dict)
for word1 in words1:
for word2 in words2:
sim = self.word_similarity(word1,
word2,
-1,
-1,
sim_type="strict_links_and_nodes")
pair_sims_by_word[word1][word2] = sim if sim else 0.0
pair_sims_by_word[word2][word1] = sim if sim else 0.0
max_sims_by_word = dict(
((word, my_max(pair_sims_by_word[word].itervalues()))
for word in words1 | words2))
sim = average((average((max_sims_by_word[w] for w in words1)),
average((max_sims_by_word[w] for w in words2))))
#sim = max((my_max((max_sims_by_word[w] for w in words1)),
# my_max((max_sims_by_word[w] for w in words2))))
if sim:
self.log(
"{0} - {1} all_pairs similarity: {2} based on: {3}".format(
machine1.printname(), machine2.printname(), sim,
pair_sims_by_word))
return sim
def _all_pairs_similarity(self, machine1, machine2):
words1 = set(MachineTraverser.get_nodes(machine1,
exclude_words=self.stopwords))
words2 = set(MachineTraverser.get_nodes(machine2,
exclude_words=self.stopwords))
pair_sims_by_word = defaultdict(dict)
for word1 in words1:
for word2 in words2:
sim = self.word_similarity(word1, word2, -1, -1,
sim_type="strict_links_and_nodes")
pair_sims_by_word[word1][word2] = sim if sim else 0.0
pair_sims_by_word[word2][word1] = sim if sim else 0.0
max_sims_by_word = dict((
(word, my_max(pair_sims_by_word[word].itervalues()))
for word in words1 | words2))
sim = average((average((max_sims_by_word[w] for w in words1)),
average((max_sims_by_word[w] for w in words2))))
#sim = max((my_max((max_sims_by_word[w] for w in words1)),
# my_max((max_sims_by_word[w] for w in words2))))
if sim:
self.log(
"{0} - {1} all_pairs similarity: {2} based on: {3}".format(
machine1.printname(), machine2.printname(), sim,
pair_sims_by_word))
return sim
def directional_sen_similarity(self, sen1, sen2, fallback):
return average((
my_max((self.word_sim.word_similarity(
word1['token'], word2['token'], -1, -1,
fallback=fallback)
for word2 in sen2))
for word1 in sen1))
def directional_sen_similarity(self, sen1, sen2, fallback):
return average((
my_max((self.word_sim.word_similarity(
word1['token'], word2['token'], -1, -1,
fallback=fallback)
for word2 in sen2))
for word1 in sen1))
