def test_encode_char(self):
encoder = OneHotMatrixEncoder(1)
sequences = np.array([[1], [4], [0]])
encoded_vectors = encoder.encode_sequences(sequences)
expected_vectors = np.array([[[0, 1, 0, 0, 0]], [[0, 0, 0, 0, 1]],
[[1, 0, 0, 0, 0]]])
np.testing.assert_array_equal(encoded_vectors, expected_vectors)
def test_encode_sequences(self):
encoder = OneHotMatrixEncoder(4)
sequences = np.array([[2, 1, 4, 3], [1, 4, 3, 2], [1, 4, 0, 2]])
encoded_vectors = encoder.encode_sequences(sequences)
expected_vectors = np.array([[[0, 0, 1, 0, 0], [0, 1, 0, 0, 0],
[0, 0, 0, 0, 1], [0, 0, 0, 1, 0]],
[[0, 1, 0, 0, 0], [0, 0, 0, 0, 1],
[0, 0, 0, 1, 0], [0, 0, 1, 0, 0]],
[[0, 1, 0, 0, 0], [0, 0, 0, 0, 1],
[1, 0, 0, 0, 0], [0, 0, 1, 0, 0]]])
np.testing.assert_array_equal(encoded_vectors, expected_vectors)
def test_encode_bad_prediction_length(self):
try:
encoder = OneHotMatrixEncoder(1, -1)
except NegativePredictionLengthException as e:
pass
except Exception as e:
self.fail()
def test_encode_bad_length(self):
try:
encoder = OneHotMatrixEncoder(0)
except NonpositiveLengthException as e:
pass
except Exception as e:
self.fail()
class OneHotVectorEncoder(_OneHotVectorUtil):
def __init__(self, sequence_length, encoding_constants=CONSTANTS):
super().__init__(sequence_length,
encoding_constants=encoding_constants)
self.encoder = OneHotMatrixEncoder(
sequence_length, encoding_constants=self.encoding_constants)
def encode_sequences(self, integer_encoding):
if len(integer_encoding) == 0:
return np.array([])
cube = self.encoder.encode_sequences(integer_encoding)
encoding_length = len(self.encoding_constants.ONE_HOT_ENCODING)
dimensions = (len(cube), encoding_length * self.sequence_length)
encoded_matrix = cube.reshape(dimensions)
return encoded_matrix
def __init__(self, sequence_length, encoding_constants=CONSTANTS):
super().__init__(sequence_length,
encoding_constants=encoding_constants)
self.encoder = OneHotMatrixEncoder(
sequence_length, encoding_constants=self.encoding_constants)
def test_encode_empty_array(self):
encoder = OneHotMatrixEncoder(4)
sequences = np.array([])
encoded_vectors = encoder.encode_sequences(sequences)
expected_vectors = np.array([])
np.testing.assert_array_equal(encoded_vectors, expected_vectors)