def test_squared_loss_staged_predict(self):
# Test whether staged decision function eventually gives
# the same prediction.
model = GradientBoostingSurvivalAnalysis(loss="squared",
n_estimators=100,
max_depth=3,
random_state=0)
model.fit(self.x, self.y)
y_pred = model.predict(self.x)
# test if prediction for last stage equals ``predict``
for y in model.staged_predict(self.x):
self.assertTupleEqual(y.shape, y_pred.shape)
assert_array_equal(y_pred, y)
model.set_params(dropout_rate=0.03)
model.fit(self.x, self.y)
y_pred = model.predict(self.x)
# test if prediction for last stage equals ``predict``
for y in model.staged_predict(self.x):
self.assertTupleEqual(y.shape, y_pred.shape)
assert_array_equal(y_pred, y)
def test_squared_loss_staged_predict(make_whas500):
whas500_data = make_whas500(with_std=False, to_numeric=True)
# Test whether staged decision function eventually gives
# the same prediction.
model = GradientBoostingSurvivalAnalysis(loss="squared", n_estimators=100, max_depth=3, random_state=0)
model.fit(whas500_data.x, whas500_data.y)
y_pred = model.predict(whas500_data.x)
# test if prediction for last stage equals ``predict``
for y in model.staged_predict(whas500_data.x):
assert y.shape == y_pred.shape
assert_array_equal(y_pred, y)
model.set_params(dropout_rate=0.03)
model.fit(whas500_data.x, whas500_data.y)
y_pred = model.predict(whas500_data.x)
# test if prediction for last stage equals ``predict``
for y in model.staged_predict(whas500_data.x):
assert y.shape == y_pred.shape
assert_array_equal(y_pred, y)
def test_fit_int_param_as_float(make_whas500):
whas500_data = make_whas500(with_std=False, to_numeric=True)
if _sklearn_version_under_0p21:
max_depth = 3
else:
# Account for https://github.com/scikit-learn/scikit-learn/pull/12344
max_depth = 4
model = GradientBoostingSurvivalAnalysis(n_estimators=100.0,
max_depth=float(max_depth),
min_samples_split=10.0,
random_state=0)
params = model.get_params()
assert 100 == params["n_estimators"]
assert max_depth == params["max_depth"]
assert 10 == params["min_samples_split"]
model.set_params(max_leaf_nodes=15.0)
assert 15 == model.get_params()["max_leaf_nodes"]
model.fit(whas500_data.x, whas500_data.y)
p = model.predict(whas500_data.x)
assert_cindex_almost_equal(whas500_data.y['fstat'],
whas500_data.y['lenfol'], p,
(0.90256690042449006, 67826, 7321, 2, 14))
def test_negative_ccp_alpha(make_whas500):
whas500_data = make_whas500(with_std=False, to_numeric=True)
clf = GradientBoostingSurvivalAnalysis()
msg = "ccp_alpha must be greater than or equal to 0"
with pytest.raises(ValueError, match=msg):
clf.set_params(ccp_alpha=-1.0)
clf.fit(whas500_data.x, whas500_data.y)
def test_fit_int_param_as_float(self):
model = GradientBoostingSurvivalAnalysis(n_estimators=100.0, max_depth=3.0, min_samples_split=10.0,
random_state=0)
params = model.get_params()
self.assertEqual(100, params["n_estimators"])
self.assertEqual(3, params["max_depth"])
self.assertEqual(10, params["min_samples_split"])
model.set_params(max_leaf_nodes=15.0)
self.assertEqual(15, model.get_params()["max_leaf_nodes"])
model.fit(self.x, self.y)
p = model.predict(self.x)
expected_cindex = numpy.array([0.90256690042449006, 67826, 7321, 2, 119])
result = concordance_index_censored(self.y['fstat'], self.y['lenfol'], p)
assert_array_almost_equal(expected_cindex, numpy.array(result))
def test_fit_int_param_as_float(make_whas500):
whas500_data = make_whas500(with_std=False, to_numeric=True)
model = GradientBoostingSurvivalAnalysis(n_estimators=100.0, max_depth=3.0, min_samples_split=10.0,
random_state=0)
params = model.get_params()
assert 100 == params["n_estimators"]
assert 3 == params["max_depth"]
assert 10 == params["min_samples_split"]
model.set_params(max_leaf_nodes=15.0)
assert 15 == model.get_params()["max_leaf_nodes"]
model.fit(whas500_data.x, whas500_data.y)
p = model.predict(whas500_data.x)
assert_cindex_almost_equal(whas500_data.y['fstat'], whas500_data.y['lenfol'], p,
(0.90256690042449006, 67826, 7321, 2, 119))
def test_max_features(make_whas500):
whas500_data = make_whas500(with_std=False, to_numeric=True)
model = GradientBoostingSurvivalAnalysis(n_estimators=10, max_features="auto", max_depth=3, random_state=0)
model.fit(whas500_data.x, whas500_data.y)
assert model.max_features_ == whas500_data.x.shape[1]
model.set_params(max_features="sqrt")
model.fit(whas500_data.x, whas500_data.y)
assert round(abs(model.max_features_ - int(numpy.sqrt(whas500_data.x.shape[1]))), 7) == 0
model.set_params(max_features="log2")
model.fit(whas500_data.x, whas500_data.y)
assert round(abs(model.max_features_ - int(numpy.log2(whas500_data.x.shape[1]))), 7) == 0
model.set_params(max_features=0.25)
model.fit(whas500_data.x, whas500_data.y)
assert round(abs(model.max_features_ - int(0.25 * whas500_data.x.shape[1])), 7) == 0
model.set_params(max_features=5)
model.fit(whas500_data.x, whas500_data.y)
assert round(abs(model.max_features_ - 5), 7) == 0
model.set_params(max_features=-1)
with pytest.raises(ValueError,
match=r"max_features must be in \(0, n_features\]"):
model.fit(whas500_data.x, whas500_data.y)
model.set_params(max_features=-1.125)
with pytest.raises(ValueError,
match=r"max_features must be in \(0, 1.0\]"):
model.fit(whas500_data.x, whas500_data.y)
model.set_params(max_features="fail_me")
with pytest.raises(ValueError,
match="Invalid value for max_features: 'fail_me'. "
"Allowed string values are 'auto', 'sqrt' "
"or 'log2'"):
model.fit(whas500_data.x, whas500_data.y)
def test_max_features(self):
model = GradientBoostingSurvivalAnalysis(n_estimators=10, max_features="auto", max_depth=3, random_state=0)
model.fit(self.x, self.y)
self.assertEqual(model.max_features_, self.x.shape[1])
model.set_params(max_features="sqrt")
model.fit(self.x, self.y)
self.assertAlmostEqual(model.max_features_, int(numpy.sqrt(self.x.shape[1])))
model.set_params(max_features="log2")
model.fit(self.x, self.y)
self.assertAlmostEqual(model.max_features_, int(numpy.log2(self.x.shape[1])))
model.set_params(max_features=0.25)
model.fit(self.x, self.y)
self.assertAlmostEqual(model.max_features_, int(0.25 * self.x.shape[1]))
model.set_params(max_features=5)
model.fit(self.x, self.y)
self.assertAlmostEqual(model.max_features_, 5)
model.set_params(max_features=-1)
self.assertRaisesRegex(ValueError,
"max_features must be in \(0, n_features\]",
model.fit, self.x, self.y)
model.set_params(max_features=-1.125)
self.assertRaisesRegex(ValueError,
"max_features must be in \(0, 1.0\]",
model.fit, self.x, self.y)
model.set_params(max_features="fail_me")
self.assertRaisesRegex(ValueError,
"Invalid value for max_features: 'fail_me'. "
"Allowed string values are 'auto', 'sqrt' "
"or 'log2'",
model.fit, self.x, self.y)
