def test_correlation(self):
base_estimators = [('gbm',
ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
correlation=None)
self.assertRaisesRegex(
ValueError,
"correlation must be one of 'pearson', 'kendall', and 'spearman', but got None",
meta.fit, self.x, self.y)
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
correlation=2143)
self.assertRaisesRegex(
ValueError,
"correlation must be one of 'pearson', 'kendall', and 'spearman', but got 2143",
meta.fit, self.x, self.y)
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
correlation="clearly wrong")
self.assertRaisesRegex(
ValueError,
"correlation must be one of 'pearson', 'kendall', and 'spearman', but got 'clearly wrong'",
meta.fit, self.x, self.y)
def test_correlation(make_whas500):
whas500 = make_whas500(with_mean=False,
with_std=False,
to_numeric=True)
base_estimators = [('gbm',
ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
correlation=None)
with pytest.raises(
ValueError,
match="correlation must be one of 'pearson', 'kendall', "
"and 'spearman', but got None"):
meta.fit(whas500.x, whas500.y)
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
correlation=2143)
with pytest.raises(
ValueError,
match="correlation must be one of 'pearson', 'kendall', "
"and 'spearman', but got 2143"):
meta.fit(whas500.x, whas500.y)
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
correlation="clearly wrong")
with pytest.raises(
ValueError,
match="correlation must be one of 'pearson', 'kendall', "
"and 'spearman', but got 'clearly wrong'"):
meta.fit(whas500.x, whas500.y)
def _create_survival_ensemble(**kwargs):
boosting_grid = ParameterGrid({
"n_estimators": [100, 250],
"subsample": [1.0, 0.75, 0.5]
})
alphas = numpy.exp(numpy.linspace(numpy.log(0.001), numpy.log(2), 5))
svm_grid = ParameterGrid({"alpha": alphas})
base_estimators = []
for i, params in enumerate(boosting_grid):
model = ComponentwiseGradientBoostingSurvivalAnalysis(random_state=0,
**params)
base_estimators.append(("gbm_%d" % i, model))
for i, params in enumerate(svm_grid):
model = FastSurvivalSVM(max_iter=100,
tol=1e-6,
random_state=0,
**params)
base_estimators.append(("svm_%d" % i, model))
cv = KFold(n_splits=3, shuffle=True, random_state=0)
meta = EnsembleSelection(base_estimators,
n_estimators=0.4,
scorer=score_cindex,
cv=cv,
**kwargs)
return meta
def test_min_correlation(make_whas500):
whas500 = make_whas500(with_mean=False,
with_std=False,
to_numeric=True)
base_estimators = [('gbm',
ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators,
scorer=score_cindex,
min_correlation=1.2)
with pytest.raises(
ValueError,
match=r"min_correlation must be in \[-1; 1\], but was 1.2"):
meta.fit(whas500.x, whas500.y)
meta.set_params(min_correlation=-2.1)
with pytest.raises(
ValueError,
match=r"min_correlation must be in \[-1; 1\], but was -2.1"):
meta.fit(whas500.x, whas500.y)
meta.set_params(min_correlation=numpy.nan)
with pytest.raises(
ValueError,
match=r"min_correlation must be in \[-1; 1\], but was nan"):
meta.fit(whas500.x, whas500.y)
def test_fit_custom_kernel(make_whas500):
whas500 = make_whas500(with_mean=False, with_std=False, to_numeric=True)
alphas = numpy.exp(numpy.linspace(numpy.log(0.001), numpy.log(0.5), 5))
svm_grid = ParameterGrid({"alpha": alphas})
transform = ClinicalKernelTransform(fit_once=True)
transform.prepare(whas500.x_data_frame)
base_estimators = []
for i, params in enumerate(svm_grid):
model = FastSurvivalSVM(max_iter=100, random_state=0, **params)
base_estimators.append(("svm_linear_%d" % i, model))
for i, params in enumerate(svm_grid):
model = FastKernelSurvivalSVM(kernel=transform.pairwise_kernel, max_iter=45, tol=1e-5,
random_state=0, **params)
base_estimators.append(("svm_kernel_%d" % i, model))
cv = KFold(n_splits=3, shuffle=True, random_state=0)
meta = EnsembleSelection(base_estimators, n_estimators=0.4, scorer=score_cindex, cv=cv, n_jobs=4)
meta.fit(whas500.x, whas500.y)
assert len(meta) == 10
assert meta.scores_.shape == (10,)
p = meta.predict(whas500.x)
assert_cindex_almost_equal(whas500.y['fstat'], whas500.y['lenfol'], p,
(0.7978084, 59938, 15178, 33, 119))
def test_fit_custom_kernel(self):
alphas = numpy.exp(numpy.linspace(numpy.log(0.001), numpy.log(0.5), 5))
svm_grid = ParameterGrid({"alpha": alphas})
transform = ClinicalKernelTransform(fit_once=True)
transform.prepare(self.x)
base_estimators = []
for i, params in enumerate(svm_grid):
model = FastSurvivalSVM(max_iter=100, random_state=0, **params)
base_estimators.append(("svm_linear_%d" % i, model))
for i, params in enumerate(svm_grid):
model = FastKernelSurvivalSVM(kernel=transform.pairwise_kernel, max_iter=45, tol=1e-5,
random_state=0, **params)
base_estimators.append(("svm_kernel_%d" % i, model))
cv = KFold(n_splits=3, shuffle=True, random_state=0)
meta = EnsembleSelection(base_estimators, n_estimators=0.4, scorer=score_cindex, cv=cv, n_jobs=4)
meta.fit(self.x.values, self.y)
self.assertEqual(len(meta), 10)
self.assertTupleEqual(meta.scores_.shape, (10,))
p = meta.predict(self.x.values)
score = concordance_index_censored(self.y['fstat'], self.y['lenfol'], p)
expected_score = numpy.array([0.7978084, 59938, 15178, 33, 119])
assert_array_almost_equal(score, expected_score)
def test_min_score(self):
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=score_cindex, min_score=1.0)
self.assertRaisesRegex(ValueError, "no base estimator exceeds min_score, try decreasing it",
meta.fit, self.x, self.y)
def test_min_score(make_whas500):
whas500 = make_whas500(with_mean=False, with_std=False, to_numeric=True)
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=score_cindex, min_score=1.0, cv=3)
with pytest.raises(ValueError,
match="no base estimator exceeds min_score, try decreasing it"):
meta.fit(whas500.x, whas500.y)
def test_n_estimators(self):
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=score_cindex, n_estimators=0)
self.assertRaisesRegex(ValueError, "n_estimators must not be zero or negative",
meta.fit, self.x, self.y)
meta.set_params(n_estimators=1000)
self.assertRaisesRegex(ValueError, r"n_estimators \(1000\) must not exceed number of base learners \(2\)",
meta.fit, self.x, self.y)
def test_scorer(self):
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=None)
self.assertRaisesRegex(TypeError, "scorer is not callable",
meta.fit, self.x, self.y)
meta.set_params(scorer=numpy.zeros(10))
self.assertRaisesRegex(TypeError, "scorer is not callable",
meta.fit, self.x, self.y)
def test_scorer(make_whas500):
whas500 = make_whas500(with_mean=False, with_std=False, to_numeric=True)
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=None)
with pytest.raises(TypeError, match="scorer is not callable"):
meta.fit(whas500.x, whas500.y)
meta.set_params(scorer=numpy.zeros(10))
with pytest.raises(TypeError, match="scorer is not callable"):
meta.fit(whas500.x, whas500.y)
def test_n_estimators(make_whas500):
whas500 = make_whas500(with_mean=False, with_std=False, to_numeric=True)
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=score_cindex, n_estimators=0)
with pytest.raises(ValueError, match="n_estimators must not be zero or negative"):
meta.fit(whas500.x, whas500.y)
meta.set_params(n_estimators=1000)
with pytest.raises(ValueError,
match=r"n_estimators \(1000\) must not exceed number "
r"of base learners \(2\)"):
meta.fit(whas500.x, whas500.y)
def test_min_correlation(self):
base_estimators = [('gbm', ComponentwiseGradientBoostingSurvivalAnalysis()),
('svm', FastSurvivalSVM())]
meta = EnsembleSelection(base_estimators, scorer=score_cindex, min_correlation=1.2)
self.assertRaisesRegex(ValueError, r"min_correlation must be in \[-1; 1\], but was 1.2",
meta.fit, self.x, self.y)
meta.set_params(min_correlation=-2.1)
self.assertRaisesRegex(ValueError, r"min_correlation must be in \[-1; 1\], but was -2.1",
meta.fit, self.x, self.y)
meta.set_params(min_correlation=numpy.nan)
self.assertRaisesRegex(ValueError, r"min_correlation must be in \[-1; 1\], but was nan",
meta.fit, self.x, self.y)
def _create_ensemble(self, **kwargs):
boosting_grid = ParameterGrid({
"n_estimators": [100, 250],
"subsample": [1.0, 0.75, 0.5]
})
svm_grid = ParameterGrid({"alpha": 2.**numpy.arange(-9, 5, 2)})
base_estimators = []
for i, params in enumerate(boosting_grid):
model = ComponentwiseGradientBoostingSurvivalAnalysis(
random_state=0, **params)
base_estimators.append(("gbm_%d" % i, model))
for i, params in enumerate(svm_grid):
model = FastSurvivalSVM(max_iter=100, random_state=0, **params)
base_estimators.append(("svm_%d" % i, model))
cv = KFold(n_splits=4, shuffle=True, random_state=0)
meta = EnsembleSelection(base_estimators,
n_estimators=0.4,
scorer=score_cindex,
cv=cv,
**kwargs)
return meta