def matchBlocks(self, blocks, threshold=.5, *args, **kwargs):
"""
Partitions blocked data and generates a sequence of clusters, where
each cluster is a tuple of record ids
Keyword arguments:
blocks -- Sequence of tuples of records, where each tuple is a
set of records covered by a blocking predicate
threshold -- Number between 0 and 1 (default is .5). We will
only consider as duplicates record pairs as
duplicates if their estimated duplicate
likelihood is greater than the threshold.
Lowering the number will increase recall,
raising it will increase precision
"""
candidate_records = self._blockedPairs(blocks)
matches = core.scoreGazette(candidate_records,
self.data_model,
self.classifier,
self.num_cores,
threshold=threshold)
logger.debug("matching done, begin clustering")
return self._cluster(matches, *args, **kwargs)
def matchBlocks(self, blocks, threshold=.5, *args, **kwargs):
"""
Partitions blocked data and generates a sequence of clusters, where
each cluster is a tuple of record ids
Keyword arguments:
blocks -- Sequence of tuples of records, where each tuple is a
set of records covered by a blocking predicate
threshold -- Number between 0 and 1 (default is .5). We will
only consider as duplicates record pairs as
duplicates if their estimated duplicate
likelihood is greater than the threshold.
Lowering the number will increase recall,
raising it will increase precision
"""
candidate_records = self._blockedPairs(blocks)
matches = core.scoreGazette(candidate_records,
self.data_model,
self.classifier,
self.num_cores,
threshold=threshold)
logger.debug("matching done, begin clustering")
return self._cluster(matches, *args, **kwargs)