def fit_then_transform_dense(self, expected, input,
categorical_features='all',
minimum_fraction=None):
ohe = OneHotEncoder(categorical_features=categorical_features,
sparse=False, minimum_fraction=minimum_fraction)
transformation = ohe.fit_transform(input.copy())
self.assertIsInstance(transformation, np.ndarray)
assert_array_almost_equal(expected, transformation)
ohe2 = OneHotEncoder(categorical_features=categorical_features,
sparse=False, minimum_fraction=minimum_fraction)
ohe2.fit(input.copy())
transformation = ohe2.transform(input.copy())
self.assertIsInstance(transformation, np.ndarray)
assert_array_almost_equal(expected, transformation)
def test_transform_with_unknown_value(self):
input = np.array(((0, 1, 2, 3, 4, 5), (0, 1, 2, 3, 4, 5))).transpose()
ohe = OneHotEncoder()
ohe.fit(input)
test_data = np.array(((0, 1, 2, 6), (0, 1, 6, 7))).transpose()
output = ohe.transform(test_data).todense()
self.assertEqual(5, np.sum(output))
input = np.array(((0, 1, 2, 3, 4, 5), (0, 1, 2, 3, 4, 5))).transpose()
ips = scipy.sparse.csr_matrix(input)
ohe = OneHotEncoder()
ohe.fit(ips)
test_data = np.array(((0, 1, 2, 6), (0, 1, 6, 7))).transpose()
tds = scipy.sparse.csr_matrix(test_data)
output = ohe.transform(tds).todense()
self.assertEqual(3, np.sum(output))
def fit_then_transform(self, expected, input, categorical_features='all',
minimum_fraction=None):
# Test fit_transform
ohe = OneHotEncoder(categorical_features=categorical_features,
minimum_fraction=minimum_fraction)
transformation = ohe.fit_transform(input.copy())
self.assertIsInstance(transformation, scipy.sparse.csr_matrix)
assert_array_almost_equal(expected.astype(float),
transformation.todense())
# Test fit, and afterwards transform
ohe2 = OneHotEncoder(categorical_features=categorical_features,
minimum_fraction=minimum_fraction)
ohe2.fit(input.copy())
transformation = ohe2.transform(input.copy())
self.assertIsInstance(transformation, scipy.sparse.csr_matrix)
assert_array_almost_equal(expected, transformation.todense())
