def test_compare_clinical_kernel(self):
x_full, y, _, _ = load_arff_file(WHAS500_FILE, ['fstat', 'lenfol'], '1',
standardize_numeric=False, to_numeric=False)
trans = ClinicalKernelTransform()
trans.fit(x_full)
x = encode_categorical(standardize(x_full))
kpca = KernelPCA(kernel=trans.pairwise_kernel)
xt = kpca.fit_transform(x)
nrsvm = FastSurvivalSVM(optimizer='rbtree', tol=1e-8, max_iter=1000, random_state=0)
nrsvm.fit(xt, y)
rsvm = FastKernelSurvivalSVM(optimizer='rbtree', kernel=trans.pairwise_kernel,
tol=1e-8, max_iter=1000, random_state=0)
rsvm.fit(x, y)
pred_nrsvm = nrsvm.predict(kpca.transform(x))
pred_rsvm = rsvm.predict(x)
self.assertEqual(len(pred_nrsvm), len(pred_rsvm))
c1 = concordance_index_censored(y['fstat'], y['lenfol'], pred_nrsvm)
c2 = concordance_index_censored(y['fstat'], y['lenfol'], pred_rsvm)
self.assertAlmostEqual(c1[0], c2[0])
self.assertTupleEqual(c1[1:], c2[1:])
def test_compare_rbf(self):
x, y, _, _ = load_arff_file(WHAS500_FILE, ['fstat', 'lenfol'], '1')
kpca = KernelPCA(kernel="rbf")
xt = kpca.fit_transform(x)
nrsvm = FastSurvivalSVM(optimizer='rbtree',
tol=1e-8,
max_iter=1000,
random_state=0)
nrsvm.fit(xt, y)
rsvm = FastKernelSurvivalSVM(optimizer='rbtree',
kernel="rbf",
tol=1e-8,
max_iter=1000,
random_state=0)
rsvm.fit(x, y)
pred_nrsvm = nrsvm.predict(kpca.transform(x))
pred_rsvm = rsvm.predict(x)
self.assertEqual(len(pred_nrsvm), len(pred_rsvm))
c1 = concordance_index_censored(y['fstat'], y['lenfol'], pred_nrsvm)
c2 = concordance_index_censored(y['fstat'], y['lenfol'], pred_rsvm)
self.assertAlmostEqual(c1[0], c2[0])
self.assertTupleEqual(c1[1:], c2[1:])
def test_predict_precomputed_kernel_invalid_shape(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", kernel='precomputed', random_state=0)
x = numpy.dot(self.x.values, self.x.values.T)
ssvm.fit(x, self.y)
x_new = numpy.empty((100, 14))
self.assertRaisesRegex(ValueError, r"Precomputed metric requires shape \(n_queries, n_indexed\)\. "
r"Got \(100, 14\) for 500 indexed\.",
ssvm.predict, x_new)
def test_fit_and_predict_rbf_rbtree(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", kernel='rbf', random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(self.x.shape[0], ssvm.coef_.shape[0])
c = ssvm.score(self.x.values, self.y)
self.assertAlmostEqual(0.92230102862313534, c, 3)
def test_fit_and_predict_rbf_avltree(self):
ssvm = FastKernelSurvivalSVM(optimizer="avltree", kernel='rbf', random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(self.x.shape[0], ssvm.coef_.shape[0])
c = ssvm.score(self.x.values, self.y)
self.assertLessEqual(abs(0.92460312179802795 - c), 1e-3)
def test_fit_and_predict_linear_regression_no_intercept(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", rank_ratio=0.0, kernel="linear",
max_iter=50, fit_intercept=False, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(15837.658418546907, rmse, 4)
def test_fit_and_predict_linear(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", kernel='linear', random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(self.x.shape[0], ssvm.coef_.shape[0])
i = numpy.arange(250)
numpy.random.RandomState(0).shuffle(i)
c = ssvm.score(self.x.values[i], self.y[i])
self.assertAlmostEqual(0.76923445664157997, c, 6)
def test_fit_and_predict_hybrid_rbf(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", rank_ratio=0.5, kernel="rbf",
max_iter=50, fit_intercept=True, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertLessEqual(abs(5.0289145697617164 - ssvm.intercept_), 0.04)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertLessEqual(abs(880.20361811281487 - rmse), 75)
def test_fit_and_predict_rbf_avltree(self):
ssvm = FastKernelSurvivalSVM(optimizer="avltree",
kernel='rbf',
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(self.x.shape[0], ssvm.coef_.shape[0])
c = ssvm.score(self.x.values, self.y)
self.assertLessEqual(abs(0.92460312179802795 - c), 1e-3)
def test_fit_and_predict_rbf_rbtree(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
kernel='rbf',
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(self.x.shape[0], ssvm.coef_.shape[0])
c = ssvm.score(self.x.values, self.y)
self.assertAlmostEqual(0.92230102862313534, c, 3)
def test_fit_and_predict_regression_rbf(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", rank_ratio=0.0, kernel="rbf",
max_iter=50, fit_intercept=True, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertAlmostEqual(4.9267218894089533, ssvm.intercept_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(783.525277, rmse, 6)
def test_predict_precomputed_kernel_invalid_shape(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
kernel='precomputed',
random_state=0)
x = numpy.dot(self.x.values, self.x.values.T)
ssvm.fit(x, self.y)
x_new = numpy.empty((100, 14))
self.assertRaisesRegex(
ValueError,
r"Precomputed metric requires shape \(n_queries, n_indexed\)\. "
r"Got \(100, 14\) for 500 indexed\.", ssvm.predict, x_new)
def test_fit_and_predict_linear(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
kernel='linear',
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(self.x.shape[0], ssvm.coef_.shape[0])
i = numpy.arange(250)
numpy.random.RandomState(0).shuffle(i)
c = ssvm.score(self.x.values[i], self.y[i])
self.assertAlmostEqual(0.76923445664157997, c, 6)
def test_fit_and_predict_linear_regression_precomputed(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", rank_ratio=0.0, kernel="precomputed",
max_iter=50, fit_intercept=True, random_state=0)
x = numpy.dot(self.x.values, self.x.values.T)
ssvm.fit(x, self.y)
self.assertTrue(ssvm._pairwise)
self.assertAlmostEqual(6.3979746625712295, ssvm.intercept_, 5)
i = numpy.arange(250)
numpy.random.RandomState(0).shuffle(i)
pred = ssvm.predict(x[i])
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'][i], pred))
self.assertLessEqual(abs(1339.3006854574726 - rmse), 0.25)
def test_fit_and_predict_linear_regression_no_intercept(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
rank_ratio=0.0,
kernel="linear",
max_iter=50,
fit_intercept=False,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(15837.658418546907, rmse, 4)
def test_fit_and_predict_hybrid_rbf(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
rank_ratio=0.5,
kernel="rbf",
max_iter=50,
fit_intercept=True,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertLessEqual(abs(5.0289145697617164 - ssvm.intercept_), 0.04)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertLessEqual(abs(880.20361811281487 - rmse), 75)
def test_fit_and_predict_regression_rbf(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
rank_ratio=0.0,
kernel="rbf",
max_iter=50,
fit_intercept=True,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(ssvm._pairwise)
self.assertAlmostEqual(4.9267218894089533, ssvm.intercept_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(783.525277, rmse, 6)
def test_fit_and_predict_clinical_kernel(self):
x_full, y, _, _ = load_arff_file(WHAS500_FILE, ['fstat', 'lenfol'], '1',
standardize_numeric=False, to_numeric=False)
trans = ClinicalKernelTransform()
trans.fit(x_full)
x = encode_categorical(standardize(x_full))
ssvm = FastKernelSurvivalSVM(optimizer="rbtree", kernel=trans.pairwise_kernel, max_iter=100, random_state=0)
ssvm.fit(x.values, y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(x.shape[0], ssvm.coef_.shape[0])
c = ssvm.score(x.values, y)
self.assertLessEqual(abs(0.83699051218246412 - c), 1e-3)
def test_unknown_optimizer(self):
x = numpy.zeros((100, 10))
y = numpy.empty(dtype=[('event', bool), ('time', float)], shape=100)
y['event'] = numpy.ones(100, dtype=bool)
y['time'] = numpy.arange(1, 101, dtype=float)
ssvm = FastKernelSurvivalSVM(optimizer='random stuff')
self.assertRaisesRegex(ValueError, "unknown optimizer: random stuff",
ssvm.fit, x, y)
def test_fit_and_predict_linear_regression_precomputed(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
rank_ratio=0.0,
kernel="precomputed",
max_iter=50,
fit_intercept=True,
random_state=0)
x = numpy.dot(self.x.values, self.x.values.T)
ssvm.fit(x, self.y)
self.assertTrue(ssvm._pairwise)
self.assertAlmostEqual(6.3979746625712295, ssvm.intercept_, 5)
i = numpy.arange(250)
numpy.random.RandomState(0).shuffle(i)
pred = ssvm.predict(x[i])
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'][i], pred))
self.assertLessEqual(abs(1339.3006854574726 - rmse), 0.25)
def test_fit_precomputed_kernel_invalid_shape(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
kernel='precomputed',
random_state=0)
x = numpy.empty((100, 14))
y = numpy.fromiter(zip(numpy.ones(100), numpy.ones(100)),
dtype=[('event', bool), ('time', float)])
self.assertRaisesRegex(
ValueError,
r"Precomputed metric requires shape \(n_queries, n_indexed\)\. "
r"Got \(100, 14\) for 100 indexed\.", ssvm.fit, x, y)
def test_fit_precomputed_kernel_not_symmetric(self):
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
kernel='precomputed',
random_state=0)
x = numpy.random.randn(100, 100)
x[10, 12] = -1
x[12, 10] = 9
y = numpy.fromiter(zip(numpy.ones(100), numpy.ones(100)),
dtype=[('event', bool), ('time', float)])
self.assertRaisesRegex(ValueError, "kernel matrix is not symmetric",
ssvm.fit, x, y)
def test_fit_and_predict_clinical_kernel(self):
x_full, y, _, _ = load_arff_file(WHAS500_FILE, ['fstat', 'lenfol'],
'1',
standardize_numeric=False,
to_numeric=False)
trans = ClinicalKernelTransform()
trans.fit(x_full)
x = encode_categorical(standardize(x_full))
ssvm = FastKernelSurvivalSVM(optimizer="rbtree",
kernel=trans.pairwise_kernel,
max_iter=100,
random_state=0)
ssvm.fit(x.values, y)
self.assertFalse(ssvm._pairwise)
self.assertEquals(x.shape[0], ssvm.coef_.shape[0])
c = ssvm.score(x.values, y)
self.assertLessEqual(abs(0.83699051218246412 - c), 1e-3)
def test_compare_rbf(self):
x, y, _, _ = load_arff_file(WHAS500_FILE, ['fstat', 'lenfol'], '1')
kpca = KernelPCA(kernel="rbf")
xt = kpca.fit_transform(x)
nrsvm = FastSurvivalSVM(optimizer='rbtree', tol=1e-8, max_iter=1000, random_state=0)
nrsvm.fit(xt, y)
rsvm = FastKernelSurvivalSVM(optimizer='rbtree', kernel="rbf",
tol=1e-8, max_iter=1000, random_state=0)
rsvm.fit(x, y)
pred_nrsvm = nrsvm.predict(kpca.transform(x))
pred_rsvm = rsvm.predict(x)
self.assertEqual(len(pred_nrsvm), len(pred_rsvm))
c1 = concordance_index_censored(y['fstat'], y['lenfol'], pred_nrsvm)
c2 = concordance_index_censored(y['fstat'], y['lenfol'], pred_rsvm)
self.assertAlmostEqual(c1[0], c2[0])
self.assertTupleEqual(c1[1:], c2[1:])
def test_compare_clinical_kernel(self):
x_full, y, _, _ = load_arff_file(WHAS500_FILE, ['fstat', 'lenfol'],
'1',
standardize_numeric=False,
to_numeric=False)
trans = ClinicalKernelTransform()
trans.fit(x_full)
x = encode_categorical(standardize(x_full))
kpca = KernelPCA(kernel=trans.pairwise_kernel)
xt = kpca.fit_transform(x)
nrsvm = FastSurvivalSVM(optimizer='rbtree',
tol=1e-8,
max_iter=1000,
random_state=0)
nrsvm.fit(xt, y)
rsvm = FastKernelSurvivalSVM(optimizer='rbtree',
kernel=trans.pairwise_kernel,
tol=1e-8,
max_iter=1000,
random_state=0)
rsvm.fit(x, y)
pred_nrsvm = nrsvm.predict(kpca.transform(x))
pred_rsvm = rsvm.predict(x)
self.assertEqual(len(pred_nrsvm), len(pred_rsvm))
c1 = concordance_index_censored(y['fstat'], y['lenfol'], pred_nrsvm)
c2 = concordance_index_censored(y['fstat'], y['lenfol'], pred_rsvm)
self.assertAlmostEqual(c1[0], c2[0])
self.assertTupleEqual(c1[1:], c2[1:])
def test_default_optimizer(self):
self.assertEqual(
'rbtree',
FastKernelSurvivalSVM().fit(self.x.values, self.y).optimizer)
