def test_astype_category(self, name, dtype_ordered, index_ordered):
# GH#18630
index = CategoricalIndex(
list("aabbca"), categories=list("cab"), ordered=index_ordered
)
if name:
index = index.rename(name)
# standard categories
dtype = CategoricalDtype(ordered=dtype_ordered)
result = index.astype(dtype)
expected = CategoricalIndex(
index.tolist(),
name=name,
categories=index.categories,
ordered=dtype_ordered,
)
tm.assert_index_equal(result, expected)
# non-standard categories
dtype = CategoricalDtype(index.unique().tolist()[:-1], dtype_ordered)
result = index.astype(dtype)
expected = CategoricalIndex(index.tolist(), name=name, dtype=dtype)
tm.assert_index_equal(result, expected)
if dtype_ordered is False:
# dtype='category' can't specify ordered, so only test once
result = index.astype("category")
expected = index
tm.assert_index_equal(result, expected)
def test_astype(self):
ci = CategoricalIndex(list("aabbca"),
categories=list("cab"),
ordered=False)
result = ci.astype(object)
tm.assert_index_equal(result, Index(np.array(ci)))
# this IS equal, but not the same class
assert result.equals(ci)
assert isinstance(result, Index)
assert not isinstance(result, CategoricalIndex)
# interval
ii = IntervalIndex.from_arrays(left=[-0.001, 2.0],
right=[2, 4],
inclusive="right")
ci = CategoricalIndex(
Categorical.from_codes([0, 1, -1], categories=ii, ordered=True))
result = ci.astype("interval")
expected = ii.take([0, 1, -1], allow_fill=True, fill_value=np.nan)
tm.assert_index_equal(result, expected)
result = IntervalIndex(result.values)
tm.assert_index_equal(result, expected)
def test_equals_categorical(self):
ci1 = CategoricalIndex(["a", "b"], categories=["a", "b"], ordered=True)
ci2 = CategoricalIndex(["a", "b"],
categories=["a", "b", "c"],
ordered=True)
assert ci1.equals(ci1)
assert not ci1.equals(ci2)
assert ci1.equals(ci1.astype(object))
assert ci1.astype(object).equals(ci1)
assert (ci1 == ci1).all()
assert not (ci1 != ci1).all()
assert not (ci1 > ci1).all()
assert not (ci1 < ci1).all()
assert (ci1 <= ci1).all()
assert (ci1 >= ci1).all()
assert not (ci1 == 1).all()
assert (ci1 == Index(["a", "b"])).all()
assert (ci1 == ci1.values).all()
# invalid comparisons
with pytest.raises(ValueError, match="Lengths must match"):
ci1 == Index(["a", "b", "c"])
msg = "Categoricals can only be compared if 'categories' are the same"
with pytest.raises(TypeError, match=msg):
ci1 == ci2
with pytest.raises(TypeError, match=msg):
ci1 == Categorical(ci1.values, ordered=False)
with pytest.raises(TypeError, match=msg):
ci1 == Categorical(ci1.values, categories=list("abc"))
# tests
# make sure that we are testing for category inclusion properly
ci = CategoricalIndex(list("aabca"), categories=["c", "a", "b"])
assert not ci.equals(list("aabca"))
# Same categories, but different order
# Unordered
assert ci.equals(CategoricalIndex(list("aabca")))
# Ordered
assert not ci.equals(CategoricalIndex(list("aabca"), ordered=True))
assert ci.equals(ci.copy())
ci = CategoricalIndex(list("aabca") + [np.nan],
categories=["c", "a", "b"])
assert not ci.equals(list("aabca"))
assert not ci.equals(CategoricalIndex(list("aabca")))
assert ci.equals(ci.copy())
ci = CategoricalIndex(list("aabca") + [np.nan],
categories=["c", "a", "b"])
assert not ci.equals(list("aabca") + [np.nan])
assert ci.equals(CategoricalIndex(list("aabca") + [np.nan]))
assert not ci.equals(
CategoricalIndex(list("aabca") + [np.nan], ordered=True))
assert ci.equals(ci.copy())
def test_constructor_with_index(self):
ci = CategoricalIndex(list('aabbca'), categories=list('cab'))
tm.assert_categorical_equal(ci.values, Categorical(ci))
ci = CategoricalIndex(list('aabbca'), categories=list('cab'))
tm.assert_categorical_equal(ci.values,
Categorical(ci.astype(object),
categories=ci.categories))
def test_constructor_with_index(self):
ci = CategoricalIndex(list("aabbca"), categories=list("cab"))
tm.assert_categorical_equal(ci.values, Categorical(ci))
ci = CategoricalIndex(list("aabbca"), categories=list("cab"))
tm.assert_categorical_equal(
ci.values, Categorical(ci.astype(object), categories=ci.categories)
)
def test_fillna_categorical(self):
# GH#11343
idx = CategoricalIndex([1.0, np.nan, 3.0, 1.0], name="x")
# fill by value in categories
exp = CategoricalIndex([1.0, 1.0, 3.0, 1.0], name="x")
tm.assert_index_equal(idx.fillna(1.0), exp)
cat = idx._data
# fill by value not in categories raises TypeError on EA, casts on CI
msg = "Cannot setitem on a Categorical with a new category"
with pytest.raises(TypeError, match=msg):
cat.fillna(2.0)
result = idx.fillna(2.0)
expected = idx.astype(object).fillna(2.0)
tm.assert_index_equal(result, expected)
