def test_unique_util_missing_values_numeric():
# Check missing values in numerical values
values = np.array([3, 1, np.nan, 5, 3, np.nan], dtype=float)
expected_uniques = np.array([1, 3, 5, np.nan], dtype=float)
expected_inverse = np.array([1, 0, 3, 2, 1, 3])
uniques = _unique(values)
assert_array_equal(uniques, expected_uniques)
uniques, inverse = _unique(values, return_inverse=True)
assert_array_equal(uniques, expected_uniques)
assert_array_equal(inverse, expected_inverse)
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, expected_inverse)
def test_unique_util_missing_values_objects(missing_value, pickle_uniques):
# check for _unique and _encode with missing values with object dtypes
values = np.array(['a', 'c', 'c', missing_value, 'b'], dtype=object)
expected_uniques = np.array(['a', 'b', 'c', missing_value], dtype=object)
uniques = _unique(values)
if missing_value is None:
assert_array_equal(uniques, expected_uniques)
else: # missing_value == np.nan
assert_array_equal(uniques[:-1], expected_uniques[:-1])
assert np.isnan(uniques[-1])
if pickle_uniques:
uniques = pickle.loads(pickle.dumps(uniques))
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, np.array([0, 2, 2, 3, 1]))
def test_encode_util(values, expected):
uniques = _unique(values)
assert_array_equal(uniques, expected)
result, encoded = _unique(values, return_inverse=True)
assert_array_equal(result, expected)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
result, counts = _unique(values, return_counts=True)
assert_array_equal(result, expected)
assert_array_equal(counts, np.array([2, 1, 2]))
result, encoded, counts = _unique(values,
return_inverse=True,
return_counts=True)
assert_array_equal(result, expected)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
assert_array_equal(counts, np.array([2, 1, 2]))
def test_encode_with_check_unknown():
# test for the check_unknown parameter of _encode()
uniques = np.array([1, 2, 3])
values = np.array([1, 2, 3, 4])
# Default is True, raise error
with pytest.raises(ValueError, match="y contains previously unseen labels"):
_encode(values, uniques=uniques, check_unknown=True)
# dont raise error if False
_encode(values, uniques=uniques, check_unknown=False)
# parameter is ignored for object dtype
uniques = np.array(["a", "b", "c"], dtype=object)
values = np.array(["a", "b", "c", "d"], dtype=object)
with pytest.raises(ValueError, match="y contains previously unseen labels"):
_encode(values, uniques=uniques, check_unknown=False)
def test_encode_util(values, expected):
uniques = _unique(values)
assert_array_equal(uniques, expected)
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
