def test_fit_and_predict_hybrid(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " +
self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER,
rank_ratio=0.5,
max_iter=50,
fit_intercept=True,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertAlmostEqual(6.1409367385513729, ssvm.intercept_)
expected_coef = numpy.array([
-0.0209254120718, -0.265768317208, -0.154254689136,
0.0800600947891, -0.290121131022, -0.0288851785213,
0.0998004550073, 0.0454100937492, -0.125863947621, 0.0343588337797,
-0.000710219364914, 0.0546969104996, -0.5375338235,
-0.0137995110308
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(780.52617631863893, rmse)
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_survival_squared_hinge_loss(self):
nrsvm = NaiveSurvivalSVM(loss='squared_hinge',
dual=False,
tol=1e-8,
max_iter=1000,
random_state=0)
nrsvm.fit(self.x, self.y)
rsvm = FastSurvivalSVM(optimizer='avltree',
tol=1e-8,
max_iter=1000,
random_state=0)
rsvm.fit(self.x, self.y)
assert_array_almost_equal(nrsvm.coef_.ravel(), rsvm.coef_, 3)
pred_nrsvm = nrsvm.predict(self.x)
pred_rsvm = rsvm.predict(self.x)
self.assertEqual(len(pred_nrsvm), len(pred_rsvm))
c1 = concordance_index_censored(self.y['fstat'], self.y['lenfol'],
pred_nrsvm)
c2 = concordance_index_censored(self.y['fstat'], self.y['lenfol'],
pred_rsvm)
self.assertAlmostEqual(c1[0], c2[0])
self.assertTupleEqual(c1[1:], c2[1:])
def test_fit_timeit(self):
rnd = numpy.random.RandomState(0)
idx = rnd.choice(numpy.arange(self.x.shape[0]), replace=False, size=100)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, timeit=3, random_state=0)
ssvm.fit(self.x.values[idx, :], self.y[idx])
self.assertTrue('timings' in ssvm.optimizer_result_)
def test_fit_timeit(self):
rnd = numpy.random.RandomState(0)
idx = rnd.choice(numpy.arange(self.x.shape[0]),
replace=False,
size=100)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER,
timeit=3,
random_state=0)
ssvm.fit(self.x.values[idx, :], self.y[idx])
self.assertTrue('timings' in ssvm.optimizer_result_)
def test_fit_and_predict_ranking(self):
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
expected_coef = numpy.array([-0.02066177, -0.26449933, -0.15205399, 0.0794547, -0.28840498, -0.02864288,
0.09901995, 0.04505302, -0.12512215, 0.03341365, -0.00110442, 0.05446756,
-0.53009875, -0.01394175])
assert_array_almost_equal(expected_coef, ssvm.coef_)
self.assertEquals(self.x.shape[1], ssvm.coef_.shape[0])
c = ssvm.score(self.x.values, self.y)
self.assertAlmostEqual(0.7860650174985695, c, 6)
def test_fit_and_predict_ranking(self):
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
expected_coef = numpy.array([
-0.02066177, -0.26449933, -0.15205399, 0.0794547, -0.28840498,
-0.02864288, 0.09901995, 0.04505302, -0.12512215, 0.03341365,
-0.00110442, 0.05446756, -0.53009875, -0.01394175
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
self.assertEquals(self.x.shape[1], ssvm.coef_.shape[0])
c = ssvm.score(self.x.values, self.y)
self.assertAlmostEqual(0.7860650174985695, c, 6)
def test_fit_and_predict_regression_no_intercept(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " + self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, rank_ratio=0.0,
max_iter=50, fit_intercept=False, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
expected_coef = numpy.array([1.39989875, -1.16903161, -0.40195857, -0.05848903, -0.08421557, 4.11924729,
0.25135451, 1.89067276, -0.25751401, -0.10213143, 1.56333622, 3.10136873,
-2.23644848, -0.11620715])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(15838.510668936022, rmse)
def test_fit_and_predict_hybrid_no_intercept(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " + self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, rank_ratio=0.5,
max_iter=50, fit_intercept=False, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
expected_coef = numpy.array([0.00669121, -0.2754864, -0.14124808, 0.0748376, -0.2812598, 0.07543884,
0.09845683, 0.08398258, -0.12182314, 0.02637739, 0.03060149, 0.11870598,
-0.52688224, -0.01762842])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(1128.4460587629746, rmse)
def test_survival_squared_hinge_loss(self):
nrsvm = NaiveSurvivalSVM(loss='squared_hinge', dual=False, tol=1e-8, max_iter=1000, random_state=0)
nrsvm.fit(self.x, self.y)
rsvm = FastSurvivalSVM(optimizer='avltree', tol=1e-8, max_iter=1000, random_state=0)
rsvm.fit(self.x, self.y)
assert_array_almost_equal(nrsvm.coef_.ravel(), rsvm.coef_, 3)
pred_nrsvm = nrsvm.predict(self.x)
pred_rsvm = rsvm.predict(self.x)
self.assertEqual(len(pred_nrsvm), len(pred_rsvm))
c1 = concordance_index_censored(self.y['fstat'], self.y['lenfol'], pred_nrsvm)
c2 = concordance_index_censored(self.y['fstat'], self.y['lenfol'], pred_rsvm)
self.assertAlmostEqual(c1[0], c2[0])
self.assertTupleEqual(c1[1:], c2[1:])
def test_fit_and_predict_regression(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " + self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, rank_ratio=0.0,
max_iter=50, fit_intercept=True, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertAlmostEqual(6.4160179606675278, ssvm.intercept_)
expected_coef = numpy.array(
[-0.0730891368237, -0.536630355029, -0.497411603275, 0.269039958377, -0.730559850692, -0.0148443526234,
0.285916578892, 0.165960302339, -0.301749910087, 0.334855938531, 0.0886214732161, 0.0554890272028,
-2.12680470014, 0.0421466831393
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(1206.6556186869332, rmse)
def test_fit_and_predict_hybrid(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " + self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER, rank_ratio=0.5,
max_iter=50, fit_intercept=True, random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertAlmostEqual(6.1409367385513729, ssvm.intercept_)
expected_coef = numpy.array(
[-0.0209254120718, -0.265768317208, -0.154254689136, 0.0800600947891, -0.290121131022, -0.0288851785213,
0.0998004550073, 0.0454100937492, -0.125863947621, 0.0343588337797, -0.000710219364914, 0.0546969104996,
-0.5375338235, -0.0137995110308
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(780.52617631863893, rmse)
def test_fit_and_predict_hybrid_no_intercept(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " +
self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER,
rank_ratio=0.5,
max_iter=50,
fit_intercept=False,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
expected_coef = numpy.array([
0.00669121, -0.2754864, -0.14124808, 0.0748376, -0.2812598,
0.07543884, 0.09845683, 0.08398258, -0.12182314, 0.02637739,
0.03060149, 0.11870598, -0.52688224, -0.01762842
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(1128.4460587629746, rmse)
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_fit_and_predict_regression_no_intercept(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " +
self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER,
rank_ratio=0.0,
max_iter=50,
fit_intercept=False,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertFalse(hasattr(ssvm, "intercept_"))
expected_coef = numpy.array([
1.39989875, -1.16903161, -0.40195857, -0.05848903, -0.08421557,
4.11924729, 0.25135451, 1.89067276, -0.25751401, -0.10213143,
1.56333622, 3.10136873, -2.23644848, -0.11620715
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(15838.510668936022, rmse)
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_fit_and_predict_regression(self):
if self.OPTIMIZER in {'simple', 'PRSVM'}:
raise unittest.SkipTest("regression not implemented for " +
self.OPTIMIZER)
ssvm = FastSurvivalSVM(optimizer=self.OPTIMIZER,
rank_ratio=0.0,
max_iter=50,
fit_intercept=True,
random_state=0)
ssvm.fit(self.x.values, self.y)
self.assertAlmostEqual(6.4160179606675278, ssvm.intercept_)
expected_coef = numpy.array([
-0.0730891368237, -0.536630355029, -0.497411603275, 0.269039958377,
-0.730559850692, -0.0148443526234, 0.285916578892, 0.165960302339,
-0.301749910087, 0.334855938531, 0.0886214732161, 0.0554890272028,
-2.12680470014, 0.0421466831393
])
assert_array_almost_equal(expected_coef, ssvm.coef_)
pred = ssvm.predict(self.x.values)
rmse = numpy.sqrt(mean_squared_error(self.y['lenfol'], pred))
self.assertAlmostEqual(1206.6556186869332, rmse)