def test_cascade_first_stage_applies_cutoff():
X, _, qid = fixtures.train_data()
cascade = factories.cascade(num_stages=1, cutoffs=[2])
ranker = cascade.rankers[0]
ranker.booster.update()
offsets = group_offsets(qid)
a, b = next(offsets)
cascade.predict(X, qid)
expected = (b - a) * [0.01948363]
np.testing.assert_almost_equal(ranker.kappa[a:b], expected)
def test_cascade_score_mask_does_not_appear_in_first_stage():
X, _, qid = fixtures.train_data()
cascade = factories.cascade(num_stages=2, cutoffs=[4, 2])
cascade.update()
ranker_one = cascade.rankers[0]
ranker_two = cascade.rankers[1]
offsets = group_offsets(qid)
a, b = next(offsets)
cascade.predict(X, qid, is_train=True)
assert Cascade.SCORE_MASK not in ranker_one.predict
def test_cascade_second_stage_applies_cutoff():
X, _, qid = fixtures.train_data()
cascade = factories.cascade(num_stages=2, cutoffs=[4, 2])
cascade.update()
ranker_two = cascade.rankers[1]
offsets = group_offsets(qid)
a, b = next(offsets)
cascade.predict(X, qid)
topk = sorted(ranker_two.predict[a:b], reverse=True)
expected = (b - a) * [topk[1]]
np.testing.assert_almost_equal(ranker_two.kappa[a:b], expected)
def test_cascade_second_stage_applies_mask():
X, _, qid = fixtures.train_data()
cascade = factories.cascade(num_stages=2, cutoffs=[4, 2])
cascade.update()
ranker_one = cascade.rankers[0]
ranker_two = cascade.rankers[1]
offsets = group_offsets(qid)
a, b = next(offsets)
cascade.predict(X, qid)
expected = [1, 0, 1, 1, 1]
np.testing.assert_almost_equal(ranker_one.mask[a:b], expected)
expected = [0, 0, 1, 1, 0]
np.testing.assert_almost_equal(ranker_two.mask[a:b], expected)
def test_cascade_uses_score_mask():
"""As per previous implementation, always use the SCORE_MASK during predict
regardless of whether we are doing training or inference.
"""
X, _, qid = fixtures.train_data()
cascade = factories.cascade(num_stages=2, cutoffs=[4, 2])
cascade.update()
ranker_one = cascade.rankers[0]
ranker_two = cascade.rankers[1]
offsets = group_offsets(qid)
a, b = next(offsets)
for is_train in [True, False]:
cascade.predict(X, qid, is_train=is_train)
assert Cascade.SCORE_MASK in ranker_two.predict
def test_cascade_computed_kappa_when_training():
qid = np.array([1, 1, 1, 1, 1])
offsets = group_offsets(qid)
a, b = next(offsets)
cascade = factories.dummy_cascade()
ranker = factories.ranker()
ranker.cutoff = 2
prev_mask = [1, 1, 0, 1, 1]
scores = np.array([0.1, 1.0, -0.03, 0.5, 0.25])
ranker.predict = np.copy(scores)
# according to previous mask
ranker.predict[2] = Cascade.SCORE_MASK
scores = cascade.ranker_apply_cutoff(ranker,
scores,
prev_mask,
qid,
is_train=True)
expected = [0.5] * 5
np.testing.assert_almost_equal(ranker.kappa[a:b], expected)
assert scores is not ranker.predict