def test_compute_distance_matrix(self):
np.random.seed(seed=self.random_seed)
x_train = np.random.rand(self.train_samples, self.dim)
x_test = np.random.rand(self.test_samples, self.dim)
d = utils.compute_distance_matrix(x_train, x_test)
self.assertEqual(d.shape, (self.test_samples, self.train_samples))
for i in range(self.test_samples):
for j in range(self.train_samples):
d_ij = np.linalg.norm(x_train[j, :] - x_test[i, :])**2
self.assertAlmostEqual(d_ij, d[i, j], places=5)
def test_compute_distance_matrix_cosine(self):
if not tf.executing_eagerly():
self.skipTest("Test requires eager mode.")
np.random.seed(seed=self.random_seed)
x_train = np.random.rand(self.train_samples, self.dim)
x_test = np.random.rand(self.test_samples, self.dim)
d = utils.compute_distance_matrix(x_train, x_test, measure="cosine")
self.assertEqual(d.shape, (self.test_samples, self.train_samples))
for i in range(self.test_samples):
for j in range(self.train_samples):
d_ij = spdist.cosine(x_test[i, :], x_train[j, :])
self.assertAlmostEqual(d_ij, d[i, j], places=5)
def knn_errorrate(self, k):
x_train = np.random.rand(self.train_samples, self.dim)
x_test = np.random.rand(self.test_samples, self.dim)
d = utils.compute_distance_matrix(x_train, x_test)
y_test = np.random.randint(self.classes, size=self.test_samples)
y_train = np.random.randint(self.classes, size=self.train_samples)
err = utils.knn_errorrate(d, y_train, y_test, k=k)
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(x_train, y_train)
y_pred = knn.predict(x_test)
acc = metrics.accuracy_score(y_test, y_pred)
self.assertAlmostEqual(1.0 - err, acc, places=5)
def test_knn_errorrate_multik(self):
if not tf.executing_eagerly():
self.skipTest("Test requires eager mode.")
np.random.seed(seed=self.random_seed)
x_train = np.random.rand(self.train_samples, self.dim)
x_test = np.random.rand(self.test_samples, self.dim)
d = utils.compute_distance_matrix(x_train, x_test)
y_test = np.random.randint(self.classes, size=self.test_samples)
y_train = np.random.randint(self.classes, size=self.train_samples)
ks_input = [5, 1, 5, 3]
ks = [5, 3, 1]
vals = []
for val in ks:
err = utils.knn_errorrate(d, y_train, y_test, k=val)
vals.append(err)
comp = utils.knn_errorrate(d, y_train, y_test, k=ks_input)
self.assertEqual(len(vals), len(comp))
for k, v in enumerate(comp):
self.assertAlmostEqual(v, vals[k], places=5)