def __init__(self,
data_model,
candidates,
data_1,
data_2,
index_include):
super().__init__(data_model, candidates)
sampled_records_1 = Sample(data_1, 600)
index_data = Sample(data_2, 50000)
sampled_records_2 = Sample(index_data, 600)
preds = self.data_model.predicates(canopies=False)
self.block_learner = training.RecordLinkBlockLearner(preds,
sampled_records_1,
sampled_records_2,
index_data)
examples_to_index = candidates.copy()
if index_include:
examples_to_index += index_include
self._index_predicates(examples_to_index)
def __init__(self, data_model, candidates, data_1, data_2,
original_length_1, original_length_2):
super().__init__(data_model, candidates)
sampled_records_1 = Sample(data_1, 600, original_length_1)
index_data = Sample(data_2, 50000, original_length_2)
sampled_records_2 = Sample(index_data, 600, original_length_2)
preds = self.data_model.predicates(canopies=False)
self.block_learner = training.RecordLinkBlockLearner(
preds, sampled_records_1, sampled_records_2, index_data)
self._index_predicates(self.candidates)
def _blockLearner(self, predicates):
return training.RecordLinkBlockLearner(predicates,
self.sampled_records_1,
self.sampled_records_2)
def _init_product(self, candidates, *args):
preds = self.data_model.predicates(canopies=False)
self.block_learner = training.RecordLinkBlockLearner(preds, *args)
self.candidates = candidates[:]
