def test_mcrank_set_estimator_params():
gb = GradientBoostingClassifier(n_estimators=5,
loss="deviance",
random_state=0)
mc = McRank(gb)
mc.set_params(estimator__n_estimators=10)
assert_equal(gb.n_estimators, 10)
def test_mcrank():
gb = GradientBoostingClassifier(n_estimators=10,
loss="deviance",
random_state=0)
mc = McRank(gb)
mc.fit(X, y)
assert_almost_equal(mc.score(X, y), 48.08, 2)
def test_mcrank_set_estimator_params():
gb = GradientBoostingClassifier(n_estimators=5,
loss="deviance",
random_state=0)
mc = McRank(gb)
mc.set_params(estimator__n_estimators=10)
assert_equal(gb.n_estimators, 10)
def test_mcrank():
gb = GradientBoostingClassifier(n_estimators=10,
loss="deviance",
random_state=0)
mc = McRank(gb)
mc.fit(X, y)
assert_almost_equal(mc.score(X, y), 48.08, 2)
def test_mcrank_warm_start():
gb = GradientBoostingClassifier(n_estimators=5,
loss="deviance",
warm_start=True,
random_state=0)
mc = McRank(gb)
mc.fit(X, y)
assert_almost_equal(mc.score(X, y), 56.06, 1)
mc.set_params(estimator__n_estimators=10)
mc.fit(X, y)
assert_almost_equal(mc.score(X, y), 48.08, 2)
def test_mcrank_warm_start():
gb = GradientBoostingClassifier(n_estimators=5,
loss="deviance",
warm_start=True,
random_state=0)
mc = McRank(gb)
mc.fit(X, y)
assert_almost_equal(mc.score(X, y), 56.06, 1)
mc.set_params(estimator__n_estimators=10)
mc.fit(X, y)
assert_almost_equal(mc.score(X, y), 48.08, 2)