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_call_function(self):
t = ClinicalKernelTransform(fit_once=True)
t.prepare(self.data)
mat = t(t.X_fit_, t.X_fit_)
expected = _get_expected_matrix()
assert_array_almost_equal(expected, mat, 4)
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_call_function(make_data):
data, expected = make_data()
t = ClinicalKernelTransform(fit_once=True)
t.prepare(data)
mat = t(t.X_fit_, t.X_fit_)
assert_array_almost_equal(expected, mat, 4)
def test_prepare(self):
t = ClinicalKernelTransform(fit_once=True)
t.prepare(self.data)
copy = clone(t).fit(t.X_fit_)
mat = copy.transform(t.X_fit_[:4, :])
expected = _get_expected_matrix()
assert_array_almost_equal(expected[:4, :], mat, 4)
def test_call_function_x_and_y(self):
t = ClinicalKernelTransform(fit_once=True)
t.prepare(self.data)
mat = t(t.X_fit_[:3, :], t.X_fit_[3:, :])
m = _get_expected_matrix()
expected = m[:3:, 3:]
assert_array_almost_equal(expected, mat, 4)
def test_prepare(make_data):
data, expected = make_data()
t = ClinicalKernelTransform(fit_once=True)
t.prepare(data)
copy = clone(t).fit(t.X_fit_)
mat = copy.transform(t.X_fit_[:4, :])
assert_array_almost_equal(expected[:4, :], mat, 4)
def test_call_function_x_and_y(make_data):
data, m = make_data()
t = ClinicalKernelTransform(fit_once=True)
t.prepare(data)
mat = t(t.X_fit_[:3, :], t.X_fit_[3:, :])
expected = m[:3:, 3:]
assert_array_almost_equal(expected, mat, 4)
def test_prepare_error_dtype():
t = ClinicalKernelTransform(fit_once=True)
data = pandas.DataFrame({"age": [12, 61, 18, 21, 57, 17],
"date": numpy.array(
["2016-01-01", "1954-06-30", "1999-03-01", "2005-02-25", "2112-12-31",
"1731-09-16"], dtype='datetime64')})
with pytest.raises(TypeError, match=r'unsupported dtype: dtype\(.+\)'):
t.prepare(data)
def test_prepare_error_fit_once(make_data):
data = make_data()
t = ClinicalKernelTransform(fit_once=False)
with pytest.raises(
ValueError,
match=
"prepare can only be used if fit_once parameter is set to True"
):
t.prepare(data)
def test_kernel_transform_x_and_y(self):
t = ClinicalKernelTransform(fit_once=True)
t.prepare(self.data)
x_num = t.X_fit_.copy()
t.fit(x_num[:3, :])
mat = t.transform(x_num[3:, :])
m = _get_expected_matrix()
expected = m[:3, 3:].T
assert_array_almost_equal(expected, mat, 4)
def test_kernel_transform_x_and_y(make_data):
data, m = make_data()
t = ClinicalKernelTransform(fit_once=True)
t.prepare(data)
x_num = t.X_fit_.copy()
t.fit(x_num[:3, :])
mat = t.transform(x_num[3:, :])
expected = m[:3, 3:].T
assert_array_almost_equal(expected, mat, 4)
def test_prepare_error_type():
t = ClinicalKernelTransform(fit_once=True)
with pytest.raises(TypeError, match='X must be a pandas DataFrame'):
t.prepare([[0, 1], [1, 2], [4, 3], [6, 5]])