Skip to content

Backport PR #35697 on branch 1.1.x (REGR: Don't ignore compiled patterns in replace) #35765

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
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/v1.1.1.rst
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ Fixed regressions
- Fixed regression in :meth:`DataFrame.reset_index` would raise a ``ValueError`` on empty :class:`DataFrame` with a :class:`MultiIndex` with a ``datetime64`` dtype level (:issue:`35606`, :issue:`35657`)
- Fixed regression where :meth:`DataFrame.merge_asof` would raise a ``UnboundLocalError`` when ``left_index`` , ``right_index`` and ``tolerance`` were set (:issue:`35558`)
- Fixed regression in ``.groupby(..).rolling(..)`` where a custom ``BaseIndexer`` would be ignored (:issue:`35557`)
- Fixed regression in :meth:`DataFrame.replace` and :meth:`Series.replace` where compiled regular expressions would be ignored during replacement (:issue:`35680`)
- Fixed regression in :meth:`~pandas.core.groupby.DataFrameGroupBy.agg` where a list of functions would produce the wrong results if at least one of the functions did not aggregate. (:issue:`35490`)

.. ---------------------------------------------------------------------------
Expand Down
23 changes: 18 additions & 5 deletions pandas/core/internals/managers.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,17 @@
import itertools
import operator
import re
from typing import DefaultDict, Dict, List, Optional, Sequence, Tuple, TypeVar, Union
from typing import (
DefaultDict,
Dict,
List,
Optional,
Pattern,
Sequence,
Tuple,
TypeVar,
Union,
)
import warnings

import numpy as np
Expand Down Expand Up @@ -1922,7 +1932,10 @@ def _merge_blocks(


def _compare_or_regex_search(
a: ArrayLike, b: Scalar, regex: bool = False, mask: Optional[ArrayLike] = None
a: ArrayLike,
b: Union[Scalar, Pattern],
regex: bool = False,
mask: Optional[ArrayLike] = None,
) -> Union[ArrayLike, bool]:
"""
Compare two array_like inputs of the same shape or two scalar values
Expand All @@ -1933,7 +1946,7 @@ def _compare_or_regex_search(
Parameters
----------
a : array_like
b : scalar
b : scalar or regex pattern
regex : bool, default False
mask : array_like or None (default)

Expand All @@ -1943,7 +1956,7 @@ def _compare_or_regex_search(
"""

def _check_comparison_types(
result: Union[ArrayLike, bool], a: ArrayLike, b: Scalar,
result: Union[ArrayLike, bool], a: ArrayLike, b: Union[Scalar, Pattern],
):
"""
Raises an error if the two arrays (a,b) cannot be compared.
Expand All @@ -1964,7 +1977,7 @@ def _check_comparison_types(
else:
op = np.vectorize(
lambda x: bool(re.search(b, x))
if isinstance(x, str) and isinstance(b, str)
if isinstance(x, str) and isinstance(b, (str, Pattern))
else False
)

Expand Down
8 changes: 8 additions & 0 deletions pandas/tests/frame/methods/test_replace.py
Original file line number Diff line number Diff line change
Expand Up @@ -1573,3 +1573,11 @@ def test_replace_dict_category_type(self, input_category_df, expected_category_d
result = input_df.replace({"a": "z", "obj1": "obj9", "cat1": "catX"})

tm.assert_frame_equal(result, expected)

def test_replace_with_compiled_regex(self):
# https://github.com/pandas-dev/pandas/issues/35680
df = pd.DataFrame(["a", "b", "c"])
regex = re.compile("^a$")
result = df.replace({regex: "z"}, regex=True)
expected = pd.DataFrame(["z", "b", "c"])
tm.assert_frame_equal(result, expected)
10 changes: 10 additions & 0 deletions pandas/tests/series/methods/test_replace.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
import re

import numpy as np
import pytest

Expand Down Expand Up @@ -415,3 +417,11 @@ def test_replace_extension_other(self):
# https://github.com/pandas-dev/pandas/issues/34530
ser = pd.Series(pd.array([1, 2, 3], dtype="Int64"))
ser.replace("", "") # no exception

def test_replace_with_compiled_regex(self):
# https://github.com/pandas-dev/pandas/issues/35680
s = pd.Series(["a", "b", "c"])
regex = re.compile("^a$")
result = s.replace({regex: "z"}, regex=True)
expected = pd.Series(["z", "b", "c"])
tm.assert_series_equal(result, expected)