Skip to content

type dataframe.replace #1129

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.

Sign up for GitHub

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 7 commits into from
Feb 24, 2025
+180 −25
Merged

type dataframe.replace #1129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
c4f0d96
type dataframe.replace
MarcoGorelli Feb 21, 2025
3ffef4f
the typing never stops
MarcoGorelli Feb 24, 2025
b04f5e6
remove unused ReplaceMethod
MarcoGorelli Feb 24, 2025
5706029
finish dataframe.replace typing
MarcoGorelli Feb 24, 2025
148afe8
use typealias
MarcoGorelli Feb 24, 2025
be6ff22
mypy fixup
MarcoGorelli Feb 24, 2025
3b77209
comment
MarcoGorelli Feb 24, 2025
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
14 changes: 13 additions & 1 deletion pandas-stubs/_typing.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ from collections.abc import (
import datetime
from datetime import tzinfo
from os import PathLike
from re import Pattern
import sys
from typing import (
Any,
Expand All @@ -36,6 +37,7 @@ from typing_extensions import (
)

from pandas._libs.interval import Interval
from pandas._libs.missing import NAType
from pandas._libs.tslibs import (
BaseOffset,
Period,
Expand Down Expand Up @@ -731,7 +733,17 @@ InterpolateOptions: TypeAlias = Literal[
"cubicspline",
"from_derivatives",
]
ReplaceMethod: TypeAlias = Literal["pad", "ffill", "bfill"]
# Can be passed to `to_replace`, `value`, or `regex` in `Series.replace`.
# `DataFrame.replace` also accepts mappings of these.
ReplaceValue: TypeAlias = (
Scalar
| Pattern
| NAType
| Sequence[Scalar | Pattern]
| Mapping[Hashable, Scalar]
| Series[Any]
| None
)
SortKind: TypeAlias = Literal["quicksort", "mergesort", "heapsort", "stable"]
NaPosition: TypeAlias = Literal["first", "last"]
JoinHow: TypeAlias = Literal["left", "right", "outer", "inner"]
Expand Down
19 changes: 7 additions & 12 deletions pandas-stubs/core/frame.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@ from collections.abc import (
Sequence,
)
import datetime as dt
from re import Pattern
import sys
from typing import (
Any,
Expand Down Expand Up @@ -113,7 +112,7 @@ from pandas._typing import (
RandomState,
ReadBuffer,
Renamer,
ReplaceMethod,
ReplaceValue,
Scalar,
ScalarT,
SequenceNotStr,
Expand Down Expand Up @@ -799,24 +798,20 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
@overload
def replace(
self,
to_replace=...,
value: Scalar | NAType | Sequence | Mapping | Pattern | None = ...,
to_replace: ReplaceValue | Mapping[Hashable, ReplaceValue] = ...,
value: ReplaceValue | Mapping[Hashable, ReplaceValue] = ...,
*,
inplace: Literal[True],
limit: int | None = ...,
regex=...,
method: ReplaceMethod = ...,
regex: ReplaceValue | Mapping[Hashable, ReplaceValue] = ...,
) -> None: ...
@overload
def replace(
self,
to_replace=...,
value: Scalar | NAType | Sequence | Mapping | Pattern | None = ...,
to_replace: ReplaceValue | Mapping[Hashable, ReplaceValue] = ...,
value: ReplaceValue | Mapping[Hashable, ReplaceValue] = ...,
*,
inplace: Literal[False] = ...,
limit: int | None = ...,
regex=...,
method: ReplaceMethod = ...,
regex: ReplaceValue | Mapping[Hashable, ReplaceValue] = ...,
) -> Self: ...
def shift(
self,
Expand Down
22 changes: 10 additions & 12 deletions pandas-stubs/core/series.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,10 @@ from typing import (
overload,
)

from _typing import TimeZones
from _typing import (
ReplaceValue,
TimeZones,
)
from matplotlib.axes import (
Axes as PlotAxes,
SubplotBase,
Expand Down Expand Up @@ -141,7 +144,6 @@ from pandas._typing import (
QuantileInterpolation,
RandomState,
Renamer,
ReplaceMethod,
Scalar,
ScalarT,
SequenceNotStr,
Expand Down Expand Up @@ -1089,24 +1091,20 @@ class Series(IndexOpsMixin[S1], NDFrame):
@overload
def replace(
self,
to_replace: _str | list | dict | Series[S1] | float | None = ...,
value: Scalar | NAType | dict | list | _str | None = ...,
to_replace: ReplaceValue = ...,
value: ReplaceValue = ...,
*,
limit: int | None = ...,
regex=...,
method: ReplaceMethod = ...,
regex: ReplaceValue = ...,
inplace: Literal[True],
) -> None: ...
@overload
def replace(
self,
to_replace: _str | list | dict | Series[S1] | float | None = ...,
value: Scalar | NAType | dict | list | _str | None = ...,
to_replace: ReplaceValue = ...,
value: ReplaceValue = ...,
*,
regex: ReplaceValue = ...,
inplace: Literal[False] = ...,
limit: int | None = ...,
regex=...,
method: ReplaceMethod = ...,
) -> Series[S1]: ...
def shift(
self,
Expand Down
116 changes: 116 additions & 0 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
import io
import itertools
from pathlib import Path
import re
import string
import sys
from typing import (
Expand Down Expand Up @@ -2570,6 +2571,121 @@ def test_types_replace() -> None:
assert assert_type(df.replace(1, 2, inplace=True), None) is None


def test_dataframe_replace() -> None:
df = pd.DataFrame({"col1": ["a", "ab", "ba"]})
pattern = re.compile(r"^a.*")
check(assert_type(df.replace("a", "x"), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(pattern, "x"), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace("a", "x", regex=True), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(pattern, "x"), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(regex="a", value="x"), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(regex=pattern, value="x"), pd.DataFrame), pd.DataFrame)

check(assert_type(df.replace(["a"], ["x"]), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace([pattern], ["x"]), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(regex=["a"], value=["x"]), pd.DataFrame), pd.DataFrame)
check(
assert_type(df.replace(regex=[pattern], value=["x"]), pd.DataFrame),
pd.DataFrame,
)

check(assert_type(df.replace({"a": "x"}), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace({pattern: "x"}), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(pd.Series({"a": "x"})), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(regex={"a": "x"}), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace(regex={pattern: "x"}), pd.DataFrame), pd.DataFrame)
check(
assert_type(df.replace(regex=pd.Series({"a": "x"})), pd.DataFrame), pd.DataFrame
)

check(
assert_type(df.replace({"col1": "a"}, {"col1": "x"}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(df.replace({"col1": pattern}, {"col1": "x"}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(
df.replace(pd.Series({"col1": "a"}), pd.Series({"col1": "x"})), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(df.replace(regex={"col1": "a"}, value={"col1": "x"}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(
df.replace(regex={"col1": pattern}, value={"col1": "x"}), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(
df.replace(regex=pd.Series({"col1": "a"}), value=pd.Series({"col1": "x"})),
pd.DataFrame,
),
pd.DataFrame,
)

check(
assert_type(df.replace({"col1": ["a"]}, {"col1": ["x"]}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(df.replace({"col1": [pattern]}, {"col1": ["x"]}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(
df.replace(pd.Series({"col1": ["a"]}), pd.Series({"col1": ["x"]})),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
df.replace(regex={"col1": ["a"]}, value={"col1": ["x"]}), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(
df.replace(regex={"col1": [pattern]}, value={"col1": ["x"]}), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(
df.replace(
regex=pd.Series({"col1": ["a"]}), value=pd.Series({"col1": ["x"]})
),
pd.DataFrame,
),
pd.DataFrame,
)

check(assert_type(df.replace({"col1": {"a": "x"}}), pd.DataFrame), pd.DataFrame)
check(assert_type(df.replace({"col1": {pattern: "x"}}), pd.DataFrame), pd.DataFrame)
check(
assert_type(df.replace({"col1": pd.Series({"a": "x"})}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(df.replace(regex={"col1": {"a": "x"}}), pd.DataFrame), pd.DataFrame
)
check(
assert_type(df.replace(regex={"col1": {pattern: "x"}}), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(df.replace(regex={"col1": pd.Series({"a": "x"})}), pd.DataFrame),
pd.DataFrame,
)


def test_loop_dataframe() -> None:
# GH 70
df = pd.DataFrame({"x": [1, 2, 3]})
Expand Down
34 changes: 34 additions & 0 deletions tests/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1410,6 +1410,40 @@ def test_types_replace() -> None:
assert assert_type(s.replace(1, 2, inplace=True), None) is None


def test_series_replace() -> None:
s: pd.Series[str] = pd.DataFrame({"col1": ["a", "ab", "ba"]})["col1"]
pattern = re.compile(r"^a.*")
check(assert_type(s.replace("a", "x"), "pd.Series[str]"), pd.Series)
check(assert_type(s.replace(pattern, "x"), "pd.Series[str]"), pd.Series)
check(
assert_type(s.replace({"a": "z"}), "pd.Series[str]"),
pd.Series,
)
check(
assert_type(s.replace(pd.Series({"a": "z"})), "pd.Series[str]"),
pd.Series,
)
check(
assert_type(s.replace({pattern: "z"}), "pd.Series[str]"),
pd.Series,
)
check(assert_type(s.replace(["a"], ["x"]), "pd.Series[str]"), pd.Series)
check(assert_type(s.replace([pattern], ["x"]), "pd.Series[str]"), pd.Series)
check(assert_type(s.replace(r"^a.*", "x", regex=True), "pd.Series[str]"), pd.Series)
check(assert_type(s.replace(value="x", regex=r"^a.*"), "pd.Series[str]"), pd.Series)
check(
assert_type(s.replace(value="x", regex=[r"^a.*"]), "pd.Series[str]"), pd.Series
)
check(assert_type(s.replace(value="x", regex=pattern), "pd.Series[str]"), pd.Series)
check(
assert_type(s.replace(value="x", regex=[pattern]), "pd.Series[str]"), pd.Series
)
check(assert_type(s.replace(regex={"a": "x"}), "pd.Series[str]"), pd.Series)
check(
assert_type(s.replace(regex=pd.Series({"a": "x"})), "pd.Series[str]"), pd.Series
)


def test_cat_accessor() -> None:
# GH 43
s: pd.Series[str] = pd.Series(
Expand Down
Loading