Merge branch 'main' into cooolheater-issue59965

cooolheater · web-flow · commit ce38be279a95 · 2024-10-29T22:37:08.000+09:00
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,9 +2,9 @@ minimum_pre_commit_version: 2.15.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
-    commit,
-    merge-commit,
-    push,
+    pre-commit,
+    pre-merge-commit,
+    pre-push,
     prepare-commit-msg,
     commit-msg,
     post-checkout,
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -97,7 +97,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
@@ -106,7 +105,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
@@ -115,7 +113,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
-        -i "pandas.core.resample.Resampler.__iter__ RT03,SA01" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \
         -i "pandas.core.resample.Resampler.groups SA01" \
         -i "pandas.core.resample.Resampler.indices SA01" \
@@ -143,7 +140,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
         -i "pandas.errors.PossibleDataLossError SA01" \
-        -i "pandas.errors.PossiblePrecisionLoss SA01" \
         -i "pandas.errors.UndefinedVariableError PR01,SA01" \
         -i "pandas.errors.UnsortedIndexError SA01" \
         -i "pandas.errors.UnsupportedFunctionCall SA01" \
diff --git a/ci/deps/actions-310.yaml b/ci/deps/actions-310.yaml
@@ -52,7 +52,7 @@ dependencies:
   - scipy>=1.10.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0
+  - xarray>=2022.12.0, <=2024.9.0
   - xlrd>=2.0.1
   - xlsxwriter>=3.0.5
   - zstandard>=0.19.0
diff --git a/ci/deps/actions-311-downstream_compat.yaml b/ci/deps/actions-311-downstream_compat.yaml
@@ -53,7 +53,7 @@ dependencies:
   - scipy>=1.10.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0
+  - xarray>=2022.12.0, <=2024.9.0
   - xlrd>=2.0.1
   - xlsxwriter>=3.0.5
   - zstandard>=0.19.0
diff --git a/ci/deps/actions-311.yaml b/ci/deps/actions-311.yaml
@@ -52,7 +52,7 @@ dependencies:
   - scipy>=1.10.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0
+  - xarray>=2022.12.0, <=2024.9.0
   - xlrd>=2.0.1
   - xlsxwriter>=3.0.5
   - zstandard>=0.19.0
diff --git a/ci/deps/actions-312.yaml b/ci/deps/actions-312.yaml
@@ -52,7 +52,7 @@ dependencies:
   - scipy>=1.10.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0
+  - xarray>=2022.12.0, <=2024.9.0
   - xlrd>=2.0.1
   - xlsxwriter>=3.0.5
   - zstandard>=0.19.0
diff --git a/ci/deps/circle-311-arm64.yaml b/ci/deps/circle-311-arm64.yaml
@@ -52,7 +52,7 @@ dependencies:
   - scipy>=1.10.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0
+  - xarray>=2022.12.0, <2024.10.0
   - xlrd>=2.0.1
   - xlsxwriter>=3.0.5
   - zstandard>=0.19.0
diff --git a/environment.yml b/environment.yml
@@ -55,7 +55,7 @@ dependencies:
   - scipy>=1.10.0
   - sqlalchemy>=2.0.0
   - tabulate>=0.9.0
-  - xarray>=2022.12.0
+  - xarray>=2022.12.0, <=2024.9.0
   - xlrd>=2.0.1
   - xlsxwriter>=3.0.5
   - zstandard>=0.19.0
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
@@ -767,10 +767,24 @@ def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
         """
         Groupby iterator.
 
+        This method provides an iterator over the groups created by the ``resample``
+        or ``groupby`` operation on the object. The method yields tuples where
+        the first element is the label (group key) corresponding to each group or
+        resampled bin, and the second element is the subset of the data that falls
+        within that group or bin.
+
         Returns
         -------
-        Generator yielding sequence of (name, subsetted object)
-        for each group
+        Iterator
+            Generator yielding a sequence of (name, subsetted object)
+            for each group.
+
+        See Also
+        --------
+        Series.groupby : Group data by a specific key or column.
+        DataFrame.groupby : Group DataFrame using mapper or by columns.
+        DataFrame.resample : Resample a DataFrame.
+        Series.resample : Resample a Series.
 
         Examples
         --------
diff --git a/pandas/core/strings/accessor.py b/pandas/core/strings/accessor.py
@@ -255,7 +255,9 @@ def _validate(data):
         inferred_dtype = lib.infer_dtype(values, skipna=True)
 
         if inferred_dtype not in allowed_types:
-            raise AttributeError("Can only use .str accessor with string values!")
+            raise AttributeError(
+                f"Can only use .str accessor with string values, not {inferred_dtype}"
+            )
         return inferred_dtype
 
     def __getitem__(self, key):
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
@@ -691,6 +691,10 @@ class PossiblePrecisionLoss(Warning):
     When the column value is outside or equal to the int64 value the column is
     converted to a float64 dtype.
 
+    See Also
+    --------
+    DataFrame.to_stata : Export DataFrame object to Stata dta format.
+
     Examples
     --------
     >>> df = pd.DataFrame({"s": pd.Series([1, 2**53], dtype=np.int64)})
diff --git a/pandas/tests/io/test_spss.py b/pandas/tests/io/test_spss.py
@@ -177,4 +177,6 @@ def test_spss_metadata(datapath):
                 "modification_time": datetime.datetime(2015, 2, 6, 14, 33, 36),
             }
         )
-    assert df.attrs == metadata
+    if Version(pyreadstat.__version__) >= Version("1.2.8"):
+        metadata["mr_sets"] = {}
+    tm.assert_dict_equal(df.attrs, metadata)
diff --git a/pandas/tests/series/accessors/test_str_accessor.py b/pandas/tests/series/accessors/test_str_accessor.py
@@ -15,7 +15,8 @@ def test_str_attribute(self):
 
         # str accessor only valid with string values
         ser = Series(range(5))
-        with pytest.raises(AttributeError, match="only use .str accessor"):
+        msg = "Can only use .str accessor with string values, not integer"
+        with pytest.raises(AttributeError, match=msg):
             ser.str.repeat(2)
 
     def test_str_accessor_updates_on_inplace(self):
diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -44,7 +44,7 @@ s3fs>=2022.11.0
 scipy>=1.10.0
 SQLAlchemy>=2.0.0
 tabulate>=0.9.0
-xarray>=2022.12.0
+xarray>=2022.12.0, <=2024.9.0
 xlrd>=2.0.1
 xlsxwriter>=3.0.5
 zstandard>=0.19.0
