def test_one_hot_encoder_set_params():
X = np.array([[1, 2]]).T
oh = OneHotEncoder()
# set params on not yet fitted object
oh.set_params(categories=[[0, 1, 2, 3]])
assert oh.get_params()['categories'] == [[0, 1, 2, 3]]
assert oh.fit_transform(X).toarray().shape == (2, 4)
# set params on already fitted object
oh.set_params(categories=[[0, 1, 2, 3, 4]])
assert oh.fit_transform(X).toarray().shape == (2, 5)
def check_categorical_onehot(X):
enc = OneHotEncoder(categories='auto')
Xtr1 = enc.fit_transform(X)
enc = OneHotEncoder(categories='auto', sparse=False)
Xtr2 = enc.fit_transform(X)
assert_allclose(Xtr1.toarray(), Xtr2)
assert sparse.isspmatrix_csr(Xtr1)
return Xtr1.toarray()
def test_one_hot_encoder_dtype(input_dtype, output_dtype):
X = np.asarray([[0, 1]], dtype=input_dtype).T
X_expected = np.asarray([[1, 0], [0, 1]], dtype=output_dtype)
oh = OneHotEncoder(categories='auto', dtype=output_dtype)
assert_array_equal(oh.fit_transform(X).toarray(), X_expected)
assert_array_equal(oh.fit(X).transform(X).toarray(), X_expected)
oh = OneHotEncoder(categories='auto', dtype=output_dtype, sparse=False)
assert_array_equal(oh.fit_transform(X), X_expected)
assert_array_equal(oh.fit(X).transform(X), X_expected)
def test_one_hot_encoder_dtype_pandas(output_dtype):
pd = pytest.importorskip('pandas')
X_df = pd.DataFrame({'A': ['a', 'b'], 'B': [1, 2]})
X_expected = np.array([[1, 0, 1, 0], [0, 1, 0, 1]], dtype=output_dtype)
oh = OneHotEncoder(dtype=output_dtype)
assert_array_equal(oh.fit_transform(X_df).toarray(), X_expected)
assert_array_equal(oh.fit(X_df).transform(X_df).toarray(), X_expected)
oh = OneHotEncoder(dtype=output_dtype, sparse=False)
assert_array_equal(oh.fit_transform(X_df), X_expected)
assert_array_equal(oh.fit(X_df).transform(X_df), X_expected)
def test_one_hot_encoder_unsorted_categories():
X = np.array([['a', 'b']], dtype=object).T
enc = OneHotEncoder(categories=[['b', 'a', 'c']])
exp = np.array([[0., 1., 0.], [1., 0., 0.]])
assert_array_equal(enc.fit(X).transform(X).toarray(), exp)
assert_array_equal(enc.fit_transform(X).toarray(), exp)
assert enc.categories_[0].tolist() == ['b', 'a', 'c']
assert np.issubdtype(enc.categories_[0].dtype, np.object_)
# unsorted passed categories still raise for numerical values
X = np.array([[1, 2]]).T
enc = OneHotEncoder(categories=[[2, 1, 3]])
msg = 'Unsorted categories are not supported'
with pytest.raises(ValueError, match=msg):
enc.fit_transform(X)
def test_one_hot_encoder_specified_categories_mixed_columns():
# multiple columns
X = np.array([['a', 'b'], [0, 2]], dtype=object).T
enc = OneHotEncoder(categories=[['a', 'b', 'c'], [0, 1, 2]])
exp = np.array([[1., 0., 0., 1., 0., 0.], [0., 1., 0., 0., 0., 1.]])
assert_array_equal(enc.fit_transform(X).toarray(), exp)
assert enc.categories_[0].tolist() == ['a', 'b', 'c']
assert np.issubdtype(enc.categories_[0].dtype, np.object_)
assert enc.categories_[1].tolist() == [0, 1, 2]
# integer categories but from object dtype data
assert np.issubdtype(enc.categories_[1].dtype, np.object_)
def test_one_hot_encoder_sparse_dense():
# check that sparse and dense will give the same results
X = np.array([[3, 2, 1], [0, 1, 1]])
enc_sparse = OneHotEncoder()
enc_dense = OneHotEncoder(sparse=False)
X_trans_sparse = enc_sparse.fit_transform(X)
X_trans_dense = enc_dense.fit_transform(X)
assert X_trans_sparse.shape == (2, 5)
assert X_trans_dense.shape == (2, 5)
assert sparse.issparse(X_trans_sparse)
assert not sparse.issparse(X_trans_dense)
# check outcome
assert_array_equal(X_trans_sparse.toarray(),
[[0., 1., 0., 1., 1.], [1., 0., 1., 0., 1.]])
assert_array_equal(X_trans_sparse.toarray(), X_trans_dense)
def test_one_hot_encoder_inverse(sparse_, drop):
X = [['abc', 2, 55], ['def', 1, 55], ['abc', 3, 55]]
enc = OneHotEncoder(sparse=sparse_, drop=drop)
X_tr = enc.fit_transform(X)
exp = np.array(X, dtype=object)
assert_array_equal(enc.inverse_transform(X_tr), exp)
X = [[2, 55], [1, 55], [3, 55]]
enc = OneHotEncoder(sparse=sparse_, categories='auto', drop=drop)
X_tr = enc.fit_transform(X)
exp = np.array(X)
assert_array_equal(enc.inverse_transform(X_tr), exp)
if drop is None:
# with unknown categories
# drop is incompatible with handle_unknown=ignore
X = [['abc', 2, 55], ['def', 1, 55], ['abc', 3, 55]]
enc = OneHotEncoder(sparse=sparse_,
handle_unknown='ignore',
categories=[['abc', 'def'], [1, 2], [54, 55, 56]])
X_tr = enc.fit_transform(X)
exp = np.array(X, dtype=object)
exp[2, 1] = None
assert_array_equal(enc.inverse_transform(X_tr), exp)
# with an otherwise numerical output, still object if unknown
X = [[2, 55], [1, 55], [3, 55]]
enc = OneHotEncoder(sparse=sparse_,
categories=[[1, 2], [54, 56]],
handle_unknown='ignore')
X_tr = enc.fit_transform(X)
exp = np.array(X, dtype=object)
exp[2, 0] = None
exp[:, 1] = None
assert_array_equal(enc.inverse_transform(X_tr), exp)
# incorrect shape raises
X_tr = np.array([[0, 1, 1], [1, 0, 1]])
msg = re.escape('Shape of the passed X data is not correct')
with pytest.raises(ValueError, match=msg):
enc.inverse_transform(X_tr)
def test_one_hot_encoder_drop_manual():
cats_to_drop = ['def', 12, 3, 56]
enc = OneHotEncoder(drop=cats_to_drop)
X = [['abc', 12, 2, 55], ['def', 12, 1, 55], ['def', 12, 3, 56]]
trans = enc.fit_transform(X).toarray()
exp = [[1, 0, 1, 1], [0, 1, 0, 1], [0, 0, 0, 0]]
assert_array_equal(trans, exp)
dropped_cats = [
cat[feature] for cat, feature in zip(enc.categories_, enc.drop_idx_)
]
assert_array_equal(dropped_cats, cats_to_drop)
assert_array_equal(np.array(X, dtype=object), enc.inverse_transform(trans))
def test_one_hot_encoder_raise_missing(X, as_data_frame, handle_unknown):
if as_data_frame:
pd = pytest.importorskip('pandas')
X = pd.DataFrame(X)
ohe = OneHotEncoder(categories='auto', handle_unknown=handle_unknown)
with pytest.raises(ValueError, match="Input contains NaN"):
ohe.fit(X)
with pytest.raises(ValueError, match="Input contains NaN"):
ohe.fit_transform(X)
if as_data_frame:
X_partial = X.iloc[:1, :]
else:
X_partial = X[:1, :]
ohe.fit(X_partial)
with pytest.raises(ValueError, match="Input contains NaN"):
ohe.transform(X)
def test_one_hot_encoder_specified_categories(X, X2, cats, cat_dtype):
enc = OneHotEncoder(categories=cats)
exp = np.array([[1., 0., 0.], [0., 1., 0.]])
assert_array_equal(enc.fit_transform(X).toarray(), exp)
assert list(enc.categories[0]) == list(cats[0])
assert enc.categories_[0].tolist() == list(cats[0])
# manually specified categories should have same dtype as
# the data when coerced from lists
assert enc.categories_[0].dtype == cat_dtype
# when specifying categories manually, unknown categories should already
# raise when fitting
enc = OneHotEncoder(categories=cats)
with pytest.raises(ValueError, match="Found unknown categories"):
enc.fit(X2)
enc = OneHotEncoder(categories=cats, handle_unknown='ignore')
exp = np.array([[1., 0., 0.], [0., 0., 0.]])
assert_array_equal(enc.fit(X2).transform(X2).toarray(), exp)