MCPcopy Create free account
hub / github.com/google-research/language / construct_set_pairs

Method construct_set_pairs

language/emql/data_loader.py:307–349  ·  view source on GitHub ↗

Construct pairs of sets from KB with at least one entity in common. Args: train_split: percentage of data for training Returns: a list of train pairs and test pairs

(
      self, train_split)

Source from the content-addressed store, hash-verified

305 return train_data, test_data
306
307 def construct_set_pairs(
308 self, train_split):
309 """Construct pairs of sets from KB with at least one entity in common.
310
311 Args:
312 train_split: percentage of data for training
313
314 Returns:
315 a list of train pairs and test pairs
316 """
317 random.seed(SEED)
318 subj2objs = dict()
319 for subj, facts in self.kb.items():
320 all_objs = set()
321 for unused_rel, objs in facts.items():
322 all_objs.update(objs)
323 subj2objs[subj] = all_objs
324
325 train_pairs = list()
326 test_pairs = list()
327 for target, objs in subj2objs.items():
328 if len(objs) <= 1:
329 continue
330 # Find candidate sets which have at least 2 entities.
331 candidate_sets = list()
332 for obj in objs:
333 for unused_rel, subjs in self.kb[obj].items():
334 if len(subjs) > 1 and target in subjs:
335 candidate_sets.append(subjs)
336 # Randomly pick some pair of sets.
337 num_pairs = int(len(candidate_sets) / 2)
338 for i in range(num_pairs):
339 set1 = candidate_sets[2 * i]
340 set2 = candidate_sets[2 * i + 1]
341 if random.random() < train_split:
342 train_pairs.append((set1, set2))
343 else:
344 test_pairs.append((set1, set2))
345 tf.logging.info(
346 'set_pair (intersection & union) examples: %d train, %d test',
347 len(train_pairs), len(test_pairs))
348
349 return train_pairs, test_pairs
350
351 def construct_set_follow_facts(
352 self, train_split):

Callers 1

construct_datasetMethod · 0.95

Calls 1

seedMethod · 0.80

Tested by

no test coverage detected