Skip to content

To numeric #33411

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

Closed
wants to merge 6 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions doc/source/whatsnew/v1.1.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,7 @@ Other enhancements
- :class:`Series.str` now has a `fullmatch` method that matches a regular expression against the entire string in each row of the series, similar to `re.fullmatch` (:issue:`32806`).
- :meth:`DataFrame.sample` will now also allow array-like and BitGenerator objects to be passed to ``random_state`` as seeds (:issue:`32503`)
- :meth:`MultiIndex.union` will now raise `RuntimeWarning` if the object inside are unsortable, pass `sort=False` to suppress this warning (:issue:`33015`)
- :func:`to_numeric` will now support downcasting of nullable dtypes.
-

.. ---------------------------------------------------------------------------
Expand Down
11 changes: 5 additions & 6 deletions pandas/core/dtypes/cast.py
Original file line number Diff line number Diff line change
Expand Up @@ -143,9 +143,7 @@ def maybe_downcast_to_dtype(result, dtype):

else:
dtype = "object"

dtype = np.dtype(dtype)

converted = maybe_downcast_numeric(result, dtype, do_round)
if converted is not result:
return converted
Expand Down Expand Up @@ -180,7 +178,8 @@ def maybe_downcast_to_dtype(result, dtype):

def maybe_downcast_numeric(result, dtype, do_round: bool = False):
"""
Subset of maybe_downcast_to_dtype restricted to numeric dtypes.
Subset of maybe_downcast_to_dtype restricted to numeric and
nullable dtypes.

Parameters
----------
Expand Down Expand Up @@ -210,9 +209,7 @@ def trans(x):
# don't allow upcasts here (except if empty)
if result.dtype.itemsize <= dtype.itemsize and result.size:
return result

if is_bool_dtype(dtype) or is_integer_dtype(dtype):

if not result.size:
# if we don't have any elements, just astype it
return trans(result).astype(dtype)
Expand All @@ -239,7 +236,9 @@ def trans(x):
if (new_result == result).all():
return new_result
else:
if np.allclose(new_result, result, rtol=0):
# np.allclose raises TypeError on extension arrays
nd_result = np.array(result).astype(result[0].dtype)
if np.allclose(new_result, nd_result, rtol=0):
return new_result

elif (
Expand Down
1 change: 0 additions & 1 deletion pandas/core/tools/numeric.py
Original file line number Diff line number Diff line change
Expand Up @@ -159,7 +159,6 @@ def to_numeric(arg, errors="raise", downcast=None):
# to a numerical dtype and if a downcast method has been specified
if downcast is not None and is_numeric_dtype(values):
typecodes = None

if downcast in ("integer", "signed"):
typecodes = np.typecodes["Integer"]
elif downcast == "unsigned" and (not len(values) or np.min(values) >= 0):
Expand Down
11 changes: 11 additions & 0 deletions pandas/tests/tools/test_to_numeric.py
Original file line number Diff line number Diff line change
Expand Up @@ -649,3 +649,14 @@ def test_failure_to_convert_uint64_string_to_NaN():
ser = Series([32, 64, np.nan])
result = to_numeric(pd.Series(["32", "64", "uint64"]), errors="coerce")
tm.assert_series_equal(result, ser)


def test_support_downcast_of_nullable_dtypes():
# GH 33013
try:
pd.to_numeric(pd.Series([1, 2, 3], dtype="Int32"), downcast="integer")
pd.to_numeric(pd.Series([1, 2, 3], dtype="Int64"), downcast="integer")
pd.to_numeric(pd.Series([1, 2], dtype="Int32"), downcast="signed")
pd.to_numeric(pd.Series([1, 2, 3], dtype="Int32"), downcast="float")
except TypeError:
pytest.fail("TypeError raised.")