def test_HandleUnknown_HaveOnlyKnown_ExpectSecondColumn(self):
train = ['A', 'B']
encoder = encoders.PolynomialEncoder(handle_unknown='indicator')
result = encoder.fit_transform(train)
expected = [a_encoding, b_encoding]
self.assertEqual(deep_round(result.values.tolist()),
deep_round(expected))
def test_HandleUnknown_HaveNoUnknownInTrain_ExpectIndicatorInTest(self):
train = ['A', 'B']
test = ['A', 'B', 'C']
encoder = encoders.PolynomialEncoder(handle_unknown='indicator')
encoder.fit(train)
result = encoder.transform(test)
expected = [a_encoding, b_encoding, c_encoding]
self.assertEqual(deep_round(result.values.tolist()),
deep_round(expected))
def test_HandleMissingIndicator_NanInTrain_ExpectAsColumn(self):
train = ['A', 'B', np.nan]
encoder = encoders.PolynomialEncoder(handle_missing='indicator',
handle_unknown='value')
result = encoder.fit_transform(train)
expected = [a_encoding, b_encoding, c_encoding]
self.assertTrue(
np.array_equal(deep_round(result.values.tolist()),
deep_round(expected)))
def test_polynomial_encoder_preserve_dimension_4(self):
train = ['A', 'B', 'C']
test = ['D', 'B', 'C', None]
encoder = encoders.PolynomialEncoder(handle_unknown='value',
handle_missing='value')
encoder.fit(train)
test_t = encoder.transform(test)
expected = [[1, 0, 0], b_encoding, c_encoding, [1, 0, 0]]
self.assertEqual(deep_round(test_t.values.tolist()),
deep_round(expected))
def test_polynomial_encoder_2cols(self):
train = [['A', 'A'], ['B', 'B'], ['C', 'C']]
encoder = encoders.PolynomialEncoder(handle_unknown='value',
handle_missing='value')
encoder.fit(train)
obtained = encoder.transform(train)
expected = [
[1, a_encoding[1], a_encoding[2], a_encoding[1], a_encoding[2]],
[1, b_encoding[1], b_encoding[2], b_encoding[1], b_encoding[2]],
[1, c_encoding[1], c_encoding[2], c_encoding[1], c_encoding[2]]
]
self.assertEqual(deep_round(obtained.values.tolist()),
deep_round(expected))