Skip to content

BUG: fix Categorical.astype for dtype=np.int32 argument #39615

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Feb 8, 2021
6 changes: 3 additions & 3 deletions pandas/core/arrays/categorical.py
Original file line number Diff line number Diff line change
Expand Up @@ -466,16 +466,16 @@ def astype(self, dtype: Dtype, copy: bool = True) -> ArrayLike:
else:
# GH8628 (PERF): astype category codes instead of astyping array
try:
astyped_cats = self.categories.astype(dtype=dtype, copy=copy)
new_cats = extract_array(self.categories, extract_numpy=True)
new_cats = new_cats.astype(dtype=dtype, copy=copy)
except (
TypeError, # downstream error msg for CategoricalIndex is misleading
ValueError,
):
msg = f"Cannot cast {self.categories.dtype} dtype to {dtype}"
raise ValueError(msg)

astyped_cats = extract_array(astyped_cats, extract_numpy=True)
result = take_1d(astyped_cats, libalgos.ensure_platform_int(self._codes))
result = take_1d(new_cats, libalgos.ensure_platform_int(self._codes))

return result

Expand Down
2 changes: 1 addition & 1 deletion pandas/tests/arrays/categorical/test_dtypes.py
Original file line number Diff line number Diff line change
Expand Up @@ -138,7 +138,7 @@ def test_astype(self, ordered):
tm.assert_numpy_array_equal(result, expected)

result = cat.astype(int)
expected = np.array(cat, dtype="int64")
expected = np.array(cat, dtype="int")
tm.assert_numpy_array_equal(result, expected)

result = cat.astype(float)
Expand Down
10 changes: 9 additions & 1 deletion pandas/tests/series/test_dtypes.py
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ def test_astype_categorical_to_other(self):
exp = Series(["a", "b", "b", "a", "a", "c", "c", "c"])
tm.assert_series_equal(cat.astype("str"), exp)
s2 = Series(Categorical(["1", "2", "3", "4"]))
exp2 = Series([1, 2, 3, 4]).astype("int64")
exp2 = Series([1, 2, 3, 4]).astype("int")
tm.assert_series_equal(s2.astype("int"), exp2)

# object don't sort correctly, so just compare that we have the same
Expand All @@ -94,6 +94,14 @@ def cmp(a, b):
result = ser.astype("object").astype(CategoricalDtype())
tm.assert_series_equal(result, roundtrip_expected)

def test_categorical_int_to_int32(self):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should be named test_categorical_astype_to_int

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you parameterize on the any_int_dtype, ideally this also works on any_int_nullable_dtype (but not sure that will just work).

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done - created a new fixture any_int_or_nullable_int_dtype

# GH 39402

df = DataFrame(data={"col1": [2.0, -1.0, 3.0]})
df.col1 = df.col1.astype("category")
df.col1 = df.col1.astype(np.int32)
assert df.col1.dtype.type is np.int32

def test_series_to_categorical(self):
# see gh-16524: test conversion of Series to Categorical
series = Series(["a", "b", "c"])
Expand Down