def test_load(self):
X, y = reader.load_data_and_labels(self.filename)
p = WordPreprocessor()
p.fit(X, y)
filepath = os.path.join(os.path.dirname(__file__), 'data/preprocessor.pkl')
p.save(filepath)
self.assertTrue(os.path.exists(filepath))
loaded_p = WordPreprocessor.load(filepath)
x_test1, y_test1 = p.transform(X, y)
x_test2, y_test2 = loaded_p.transform(X, y)
np.testing.assert_array_equal(x_test1[0], x_test2[0]) # word
np.testing.assert_array_equal(x_test1[1], x_test2[1]) # char
np.testing.assert_array_equal(y_test1, y_test2)
if os.path.exists(filepath):
os.remove(filepath)
def test_unknown_word(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=False)
p = preprocessor.fit(X, y)
X = [['$unknownword$', 'あ']]
y = [['O', 'O']]
X, y = p.transform(X, y)
def test_vocab_init(self):
X, y = reader.load_data_and_labels(self.filename)
unknown_word = 'unknownword'
X_test, y_test = [[unknown_word]], [['O']]
preprocessor = WordPreprocessor(padding=False)
p = preprocessor.fit(X, y)
X_pred, _ = p.transform(X_test, y_test)
words = X_pred[0][1]
self.assertEqual(words, [p.vocab_word[UNK]])
vocab_init = {unknown_word}
preprocessor = WordPreprocessor(vocab_init=vocab_init, padding=False)
p = preprocessor.fit(X, y)
X_pred, _ = p.transform(X_test, y_test)
words = X_pred[0][1]
self.assertNotEqual(words, [p.vocab_word[UNK]])
def test_calc_sequence_lengths(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=True)
p = preprocessor.fit(X, y)
_, y = p.transform(X, y)
y_t = np.argmax(y, -1)
y_t = y_t.astype(np.int32)
sequence_lengths = np.argmin(y_t, -1)
def test_transform_with_padding(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=True)
p = preprocessor.fit(X, y)
X = p.transform(X)
words, chars = X
word, char = words[0][0], chars[0][0][0]
self.assertIsInstance(int(word), int)
self.assertIsInstance(int(char), int)
def test_transform_only_words(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=False)
p = preprocessor.fit(X, y)
X = p.transform(X)
words, chars = X
char, word = chars[0][0][0], words[0][0]
self.assertIsInstance(word, int)
self.assertIsInstance(char, int)
def test_preprocessor(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=False)
p = preprocessor.fit(X, y)
X, y = p.transform(X, y)
words, chars = X
char, word = chars[0][0][0], words[0][0]
tag = y[0][0]
self.assertIsInstance(word, int)
self.assertIsInstance(char, int)
self.assertIsInstance(tag, int)
self.assertIsInstance(p.inverse_transform(y[0])[0], str)
def test_pad_sequences(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=True)
p = preprocessor.fit(X, y)
X, y = p.transform(X, y)
def test_to_numpy_array(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor(padding=False)
p = preprocessor.fit(X, y)
X, y = p.transform(X, y)
y = np.asarray(y)
def test_fit(self):
X, y = reader.load_data_and_labels(self.filename)
preprocessor = WordPreprocessor()
p = preprocessor.fit(X, y)