def test_dedupe_coverage(self):
predicates = self.data_model.predicates()
blocker = dedupe.blocking.Blocker(predicates)
blocker.indexAll({i: x for i, x in enumerate(self.training_records)})
coverage = training.Cover(blocker.predicates,
self.training)
assert self.simple(coverage.keys()).issuperset(
set(["SimplePredicate: (tokenFieldPredicate, name)",
"SimplePredicate: (commonSixGram, name)",
"TfidfTextCanopyPredicate: (0.4, name)",
"SimplePredicate: (sortedAcronym, name)",
"SimplePredicate: (sameThreeCharStartPredicate, name)",
"TfidfTextCanopyPredicate: (0.2, name)",
"SimplePredicate: (sameFiveCharStartPredicate, name)",
"TfidfTextCanopyPredicate: (0.6, name)",
"SimplePredicate: (wholeFieldPredicate, name)",
"TfidfTextCanopyPredicate: (0.8, name)",
"SimplePredicate: (commonFourGram, name)",
"SimplePredicate: (firstTokenPredicate, name)",
"SimplePredicate: (sameSevenCharStartPredicate, name)"]))
def test_compound(self):
start = training.Cover({1: {1, 2, 3}, 2: {1, 2}, 3: {2}, 4: {5}})
before = start.copy()
after = before.copy()
after.update({(1, 2): {1, 2}, (1, 3): {2}, (2, 3): {2}})
before.compound(2)
assert before == after
before = start.copy()
after = start.copy()
after.update({
(1, 2): {1, 2},
(1, 3): {2},
(2, 3): {2},
(1, 2, 3): {2}
})
before.compound(3)
assert before == after
def test_covered_pairs(self):
p1 = lambda x, target=None: (1, ) # noqa: E 731
cover = training.Cover((p1, ), [('a', 'b')] * 2)
assert cover[p1] == {0, 1}