def test_value_counts_null(null_obj, index_or_series_obj):
orig = index_or_series_obj
obj = orig.copy()
if not allow_na_ops(obj):
pytest.skip("type doesn't allow for NA operations")
elif len(obj) < 1:
pytest.skip("Test doesn't make sense on empty data")
elif isinstance(orig, pd.MultiIndex):
pytest.skip(f"MultiIndex can't hold '{null_obj}'")
values = obj.values
if needs_i8_conversion(obj.dtype):
values[0:2] = iNaT
else:
values[0:2] = null_obj
klass = type(obj)
repeated_values = np.repeat(values, range(1, len(values) + 1))
obj = klass(repeated_values, dtype=obj.dtype)
# because np.nan == np.nan is False, but None == None is True
# np.nan would be duplicated, whereas None wouldn't
counter = collections.Counter(obj.dropna())
expected = Series(dict(counter.most_common()), dtype=np.int64)
expected.index = expected.index.astype(obj.dtype)
result = obj.value_counts()
if obj.duplicated().any():
# TODO:
# Order of entries with the same count is inconsistent on CI (gh-32449)
expected = expected.sort_index()
result = result.sort_index()
tm.assert_series_equal(result, expected)
# can't use expected[null_obj] = 3 as
# IntervalIndex doesn't allow assignment
new_entry = Series({np.nan: 3}, dtype=np.int64)
expected = expected.append(new_entry)
result = obj.value_counts(dropna=False)
if obj.duplicated().any():
# TODO:
# Order of entries with the same count is inconsistent on CI (gh-32449)
expected = expected.sort_index()
result = result.sort_index()
tm.assert_series_equal(result, expected)
def test_unique_null(null_obj, index_or_series_obj):
obj = index_or_series_obj
if not allow_na_ops(obj):
pytest.skip("type doesn't allow for NA operations")
elif len(obj) < 1:
pytest.skip("Test doesn't make sense on empty data")
elif isinstance(obj, pd.MultiIndex):
pytest.skip(f"MultiIndex can't hold '{null_obj}'")
values = obj.values
if needs_i8_conversion(obj.dtype):
values[0:2] = iNaT
else:
values[0:2] = null_obj
klass = type(obj)
repeated_values = np.repeat(values, range(1, len(values) + 1))
obj = klass(repeated_values, dtype=obj.dtype)
result = obj.unique()
unique_values_raw = dict.fromkeys(obj.values)
# because np.nan == np.nan is False, but None == None is True
# np.nan would be duplicated, whereas None wouldn't
unique_values_not_null = [
val for val in unique_values_raw if not pd.isnull(val)
]
unique_values = [null_obj] + unique_values_not_null
if isinstance(obj,
pd.Index) and obj._is_backward_compat_public_numeric_index:
expected = NumericIndex(unique_values, dtype=obj.dtype)
tm.assert_index_equal(result, expected, exact=True)
elif isinstance(obj, pd.Index):
expected = pd.Index(unique_values, dtype=obj.dtype)
if is_datetime64tz_dtype(obj.dtype):
result = result.normalize()
expected = expected.normalize()
tm.assert_index_equal(result, expected, exact=True)
else:
expected = np.array(unique_values, dtype=obj.dtype)
tm.assert_numpy_array_equal(result, expected)
def test_nunique_null(null_obj, index_or_series_obj):
obj = index_or_series_obj
if not allow_na_ops(obj):
pytest.skip("type doesn't allow for NA operations")
elif isinstance(obj, pd.MultiIndex):
pytest.skip(f"MultiIndex can't hold '{null_obj}'")
values = obj._values
values[0:2] = null_obj
klass = type(obj)
repeated_values = np.repeat(values, range(1, len(values) + 1))
obj = klass(repeated_values, dtype=obj.dtype)
if isinstance(obj, pd.CategoricalIndex):
assert obj.nunique() == len(obj.categories)
assert obj.nunique(dropna=False) == len(obj.categories) + 1
else:
num_unique_values = len(obj.unique())
assert obj.nunique() == max(0, num_unique_values - 1)
assert obj.nunique(dropna=False) == max(0, num_unique_values)
