Fix nightly (#904)

* CI nightly

* pre-commit

* remove deprecated arguments

* remove deprecated Timedelta units

* remove list from unique

* remove more undocumented/deprecated units

Author: twoertwein

.pre-commit-config.yaml

@@ -3,15 +3,15 @@ ci:
     autofix_prs: false
 repos:
 -   repo: https://github.com/python/black
-    rev: 24.2.0
+    rev: 24.3.0
     hooks:
     -   id: black
 -   repo: https://github.com/PyCQA/isort
     rev: 5.13.2
     hooks:
     -   id: isort
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.0
+    rev: v0.3.5
     hooks:
     -   id: ruff
         args: [

pandas-stubs/_libs/tslibs/timedeltas.pyi

@@ -48,12 +48,6 @@ class Components(NamedTuple):
 # This should be kept consistent with the keys in the dict timedelta_abbrevs
 # in pandas/_libs/tslibs/timedeltas.pyx
 TimeDeltaUnitChoices: TypeAlias = Literal[
-    "H",
-    "T",
-    "S",
-    "L",
-    "U",
-    "N",
     "W",
     "w",
     "D",
@@ -68,7 +62,6 @@ TimeDeltaUnitChoices: TypeAlias = Literal[
     "minute",
     "min",
     "minutes",
-    "t",
     "s",
     "seconds",
     "sec",
@@ -78,20 +71,17 @@ TimeDeltaUnitChoices: TypeAlias = Literal[
     "millisecond",
     "milli",
     "millis",
-    "l",
     "us",
     "microseconds",
     "microsecond",
     "µs",
     "micro",
     "micros",
-    "u",
     "ns",
     "nanoseconds",
     "nano",
     "nanos",
     "nanosecond",
-    "n",
 ]
 
 UnitChoices: TypeAlias = (

pandas-stubs/core/algorithms.pyi

@@ -1,4 +1,3 @@
-from collections.abc import Sequence
 from typing import (
     Literal,
     overload,
@@ -37,12 +36,12 @@ def unique(values: Categorical) -> Categorical: ...
 @overload
 def unique(values: Series) -> np.ndarray | ExtensionArray: ...
 @overload
-def unique(values: np.ndarray | list) -> np.ndarray: ...
+def unique(values: np.ndarray) -> np.ndarray: ...
 @overload
 def unique(values: ExtensionArray) -> ExtensionArray: ...
 @overload
 def factorize(
-    values: Sequence | np.recarray,
+    values: np.ndarray,
     sort: bool = ...,
     use_na_sentinel: bool = ...,
     size_hint: int | None = ...,

pandas-stubs/core/indexes/timedeltas.pyi

@@ -40,7 +40,6 @@ class TimedeltaIndex(DatetimeTimedeltaMixin[Timedelta], TimedeltaIndexProperties
             | list[str]
             | Sequence[dt.timedelta | Timedelta | np.timedelta64 | float]
         ) = ...,
-        unit: Literal["D", "h", "m", "s", "ms", "us", "ns"] = ...,
         freq: str | BaseOffset = ...,
         closed: object = ...,
         dtype: Literal["<m8[ns]"] = ...,

pandas-stubs/core/reshape/merge.pyi

@@ -32,7 +32,6 @@ def merge(
     suffixes: (
         list[str | None] | tuple[str, str] | tuple[None, str] | tuple[str, None]
     ) = ...,
-    copy: bool = ...,
     indicator: bool | str = ...,
     validate: ValidationOptions = ...,
 ) -> DataFrame: ...

tests/test_frame.py

@@ -983,12 +983,15 @@ def test_types_groupby() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         "(The provided callable <built-in function sum> is currently using|The behavior of DataFrame.sum with)",
+        upper="2.2.99",
     ):
         with pytest_warns_bounded(
             DeprecationWarning,
             "DataFrameGroupBy.apply operated on the grouping columns",
+            upper="2.2.99",
         ):
-            df7: pd.DataFrame = df.groupby(by="col1").apply(sum)
+            if PD_LTE_22:
+                df7: pd.DataFrame = df.groupby(by="col1").apply(sum)
     df8: pd.DataFrame = df.groupby("col1").transform("sum")
     s1: pd.Series = df.set_index("col1")["col2"]
     s2: pd.Series = s1.groupby("col1").transform("sum")
@@ -1033,7 +1036,7 @@ def wrapped_min(x: Any) -> Any:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <built-in function (min|max)> is currently using",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(df.groupby("col1")["col3"].agg(min), pd.Series), pd.Series)
         check(
@@ -1182,7 +1185,7 @@ def test_types_window() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <built-in function (min|max)> is currently using",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(
             assert_type(df.rolling(2).agg(max), pd.DataFrame),
@@ -1282,7 +1285,7 @@ def test_types_agg() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <(built-in function (min|max|mean)|function mean at 0x\w+)> is currently using",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(df.agg(min), pd.Series), pd.Series)
         check(assert_type(df.agg([min, max]), pd.DataFrame), pd.DataFrame)
@@ -1309,7 +1312,7 @@ def test_types_aggregate() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <built-in function (min|max)> is currently using",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(df.aggregate(min), pd.Series), pd.Series)
         check(assert_type(df.aggregate([min, max]), pd.DataFrame), pd.DataFrame)
@@ -2222,7 +2225,7 @@ def test_frame_stack() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         "The previous implementation of stack is deprecated",
-        lower="2.1.99",
+        upper="2.2.99",
     ):
         check(
             assert_type(
@@ -2593,23 +2596,22 @@ def test_resample() -> None:
     # GH 181
     N = 10
     x = [x for x in range(N)]
-    with pytest_warns_bounded(FutureWarning, "'T' is deprecated", lower="2.1.99"):
-        index = pd.date_range("1/1/2000", periods=N, freq="T")
-        x = [x for x in range(N)]
-        df = pd.DataFrame({"a": x, "b": x, "c": x}, index=index)
-        check(assert_type(df.resample("2T").std(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").var(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").quantile(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").sum(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").prod(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").min(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").max(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").first(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").last(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").mean(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").sem(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").median(), pd.DataFrame), pd.DataFrame)
-        check(assert_type(df.resample("2T").ohlc(), pd.DataFrame), pd.DataFrame)
+    index = pd.date_range("1/1/2000", periods=N, freq="min")
+    x = [x for x in range(N)]
+    df = pd.DataFrame({"a": x, "b": x, "c": x}, index=index)
+    check(assert_type(df.resample("2min").std(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").var(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").quantile(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").sum(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").prod(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").min(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").max(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").first(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").last(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").mean(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").sem(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").median(), pd.DataFrame), pd.DataFrame)
+    check(assert_type(df.resample("2min").ohlc(), pd.DataFrame), pd.DataFrame)
 
 
 def test_loc_set() -> None:
@@ -2916,7 +2918,7 @@ def test_getattr_and_dataframe_groupby() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <built-in function (min|max)> is currently using",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(df.groupby("col1").col3.agg(min), pd.Series), pd.Series)
         check(

tests/test_groupby.py

@@ -130,7 +130,7 @@ def test_frame_groupby_resample() -> None:
         with pytest_warns_bounded(
             FutureWarning,
             r"The provided callable <function (sum|mean) .*> is currently using ",
-            lower="2.0.99",
+            upper="2.2.99",
         ):
             check(
                 assert_type(GB_DF.resample("ME").aggregate(np.sum), DataFrame),
@@ -193,7 +193,7 @@ def df2scalar(val: DataFrame) -> float:
         with pytest_warns_bounded(
             FutureWarning,
             r"The provided callable <function (sum|mean) .*> is currently using ",
-            lower="2.0.99",
+            upper="2.2.99",
         ):
             check(GB_DF.resample("ME").aggregate(np.sum), DataFrame)
             check(GB_DF.resample("ME").aggregate([np.mean]), DataFrame)
@@ -344,7 +344,7 @@ def test_series_groupby_resample() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(
             assert_type(
@@ -421,7 +421,7 @@ def s2scalar(val: Series) -> float:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(GB_S.resample("ME").aggregate(np.sum), Series)
         check(GB_S.resample("ME").aggregate([np.mean]), DataFrame)
@@ -468,7 +468,7 @@ def test_frame_groupby_rolling() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(GB_DF.rolling(1).aggregate(np.sum), DataFrame), DataFrame)
         check(assert_type(GB_DF.rolling(1).agg(np.sum), DataFrame), DataFrame)
@@ -512,7 +512,7 @@ def df2scalar(val: DataFrame) -> float:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(GB_DF.rolling(1).aggregate(np.sum), DataFrame)
         check(GB_DF.rolling(1).aggregate([np.mean]), DataFrame)
@@ -590,7 +590,7 @@ def test_series_groupby_rolling() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(GB_S.rolling(1).aggregate("sum"), Series), Series)
         check(assert_type(GB_S.rolling(1).aggregate(np.sum), Series), Series)
@@ -663,7 +663,7 @@ def test_frame_groupby_expanding() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(GB_DF.expanding(1).aggregate(np.sum), DataFrame), DataFrame)
         check(assert_type(GB_DF.expanding(1).agg(np.sum), DataFrame), DataFrame)
@@ -709,7 +709,7 @@ def df2scalar(val: DataFrame) -> float:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(GB_DF.expanding(1).aggregate(np.sum), DataFrame)
         check(GB_DF.expanding(1).aggregate([np.mean]), DataFrame)
@@ -789,7 +789,7 @@ def test_series_groupby_expanding() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(GB_S.expanding(1).aggregate("sum"), Series), Series)
         check(assert_type(GB_S.expanding(1).aggregate(np.sum), Series), Series)
@@ -857,7 +857,7 @@ def test_frame_groupby_ewm() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(GB_DF.ewm(1).aggregate(np.sum), DataFrame), DataFrame)
         check(assert_type(GB_DF.ewm(1).agg(np.sum), DataFrame), DataFrame)
@@ -888,7 +888,7 @@ def test_frame_groupby_ewm() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(GB_DF.ewm(1).aggregate(np.sum), DataFrame)
         check(GB_DF.ewm(1).aggregate([np.mean]), DataFrame)
@@ -961,7 +961,7 @@ def test_series_groupby_ewm() -> None:
     with pytest_warns_bounded(
         FutureWarning,
         r"The provided callable <function (sum|mean) .*> is currently using ",
-        lower="2.0.99",
+        upper="2.2.99",
     ):
         check(assert_type(GB_S.ewm(1).aggregate("sum"), Series), Series)
         check(assert_type(GB_S.ewm(1).aggregate(np.sum), Series), Series)

tests/test_indexes.py

@@ -14,6 +14,7 @@
 from pandas._typing import Dtype  # noqa: F401
 
 from tests import (
+    PD_LTE_22,
     TYPE_CHECKING_INVALID_USAGE,
     check,
     pytest_warns_bounded,
@@ -866,7 +867,11 @@ def test_getitem() -> None:
     iri = pd.RangeIndex(0, 10)
     check(assert_type(iri, pd.RangeIndex), pd.RangeIndex, int)
     check(assert_type(iri[0], int), int)
-    check(assert_type(iri[[0, 2, 4]], pd.Index), pd.Index, np.integer)
+    check(
+        assert_type(iri[[0, 2, 4]], pd.Index),
+        pd.Index,
+        np.integer if PD_LTE_22 else int,
+    )
 
     mi = pd.MultiIndex.from_product([["a", "b"], ["c", "d"]], names=["ab", "cd"])
     check(assert_type(mi, pd.MultiIndex), pd.MultiIndex)

tests/test_io.py

@@ -49,11 +49,9 @@
 from typing_extensions import assert_type
 
 from tests import (
-    PD_LTE_22,
     TYPE_CHECKING_INVALID_USAGE,
     WINDOWS,
     check,
-    pytest_warns_bounded,
 )
 
 from pandas.io.api import to_pickle
@@ -428,23 +426,15 @@ def test_hdf_series():
 
 
 def test_spss():
-    if PD_LTE_22:
-        warning_class = FutureWarning
-        message = "Placeholder"
-    else:
-        warning_class = pd.errors.ChainedAssignmentError  # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue]
-        message = "A value is trying to be set on a copy of a DataFrame"
-
     path = Path(CWD, "data", "labelled-num.sav")
-    with pytest_warns_bounded(warning_class, message, "2.3.0"):
-        check(
-            assert_type(read_spss(path, convert_categoricals=True), DataFrame),
-            DataFrame,
-        )
-        check(
-            assert_type(read_spss(str(path), usecols=["VAR00002"]), DataFrame),
-            DataFrame,
-        )
+    check(
+        assert_type(read_spss(path, convert_categoricals=True), DataFrame),
+        DataFrame,
+    )
+    check(
+        assert_type(read_spss(str(path), usecols=["VAR00002"]), DataFrame),
+        DataFrame,
+    )
 
 
 def test_json():