def test_transform_without_character(self):
# No character feature.
it = IndexTransformer(use_char=False)
x, y = it.fit_transform(self.x, self.y)
# Check sequence length.
self.assertEqual(len(x), len(self.x))
self.assertEqual(len(y), len(self.y))
# Check sequence type.
self.assertIsInstance(x, np.ndarray)
self.assertIsInstance(y, np.ndarray)
def test_transform_with_character(self):
# With character feature.
it = IndexTransformer(use_char=True)
X, y = it.fit_transform(self.x, self.y)
words, chars, length = X
# Check sequence length.
self.assertEqual(len(words), len(self.x))
self.assertEqual(len(chars), len(self.x))
self.assertEqual(len(y), len(self.y))
# Check sequence type.
self.assertIsInstance(words, np.ndarray)
self.assertIsInstance(chars, np.ndarray)
self.assertIsInstance(y, np.ndarray)
def test_save_and_load(self):
it = IndexTransformer(lower=False)
x1, y1 = it.fit_transform(self.x, self.y)
x1_word, x1_char, x1_length = x1
self.assertFalse(os.path.exists(self.preprocessor_file))
it.save(self.preprocessor_file)
self.assertTrue(os.path.exists(self.preprocessor_file))
it = IndexTransformer.load(self.preprocessor_file)
x2, y2 = it.transform(self.x, self.y)
x2_word, x2_char, x2_length = x2
np.testing.assert_array_equal(x1_word, x2_word)
np.testing.assert_array_equal(x1_char, x2_char)
np.testing.assert_array_equal(y1, y2)
def test_inverse_transform(self):
it = IndexTransformer()
x, y = it.fit_transform(self.x, self.y)
_, _, length = x
inv_y = it.inverse_transform(y, length)
self.assertEqual(inv_y, self.y)
def test_inverse_transform(self):
it = IndexTransformer()
x, y = it.fit_transform(self.x, self.y)
lengths = map(len, self.y)
inv_y = it.inverse_transform(y, lengths)
self.assertEqual(inv_y, self.y)