Merge branch 'main' into example-correction-groupby

Author: ApoorvApoorv

ci/code_checks.sh

@@ -70,7 +70,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.MultiIndex.append PR07,SA01" \
         -i "pandas.MultiIndex.copy PR07,RT03,SA01" \
         -i "pandas.MultiIndex.get_level_values SA01" \
         -i "pandas.MultiIndex.get_loc PR07" \

pandas/_testing/asserters.py

@@ -578,13 +578,19 @@ def raise_assert_detail(
 
     if isinstance(left, np.ndarray):
         left = pprint_thing(left)
-    elif isinstance(left, (CategoricalDtype, NumpyEADtype, StringDtype)):
+    elif isinstance(left, (CategoricalDtype, NumpyEADtype)):
         left = repr(left)
+    elif isinstance(left, StringDtype):
+        # TODO(infer_string) this special case could be avoided if we have
+        # a more informative repr https://github.com/pandas-dev/pandas/issues/59342
+        left = f"StringDtype(storage={left.storage}, na_value={left.na_value})"
 
     if isinstance(right, np.ndarray):
         right = pprint_thing(right)
-    elif isinstance(right, (CategoricalDtype, NumpyEADtype, StringDtype)):
+    elif isinstance(right, (CategoricalDtype, NumpyEADtype)):
         right = repr(right)
+    elif isinstance(right, StringDtype):
+        right = f"StringDtype(storage={right.storage}, na_value={right.na_value})"
 
     msg += f"""
 [left]:  {left}

pandas/core/indexes/multi.py

@@ -2223,15 +2223,28 @@ def append(self, other):
         """
         Append a collection of Index options together.
 
+        The `append` method is used to combine multiple `Index` objects into a single
+        `Index`. This is particularly useful when dealing with multi-level indexing
+        (MultiIndex) where you might need to concatenate different levels of indices.
+        The method handles the alignment of the levels and codes of the indices being
+        appended to ensure consistency in the resulting `MultiIndex`.
+
         Parameters
         ----------
         other : Index or list/tuple of indices
+            Index or list/tuple of Index objects to be appended.
 
         Returns
         -------
         Index
             The combined index.
 
+        See Also
+        --------
+        MultiIndex: A multi-level, or hierarchical, index object for pandas objects.
+        Index.append : Append a collection of Index options together.
+        concat : Concatenate pandas objects along a particular axis.
+
         Examples
         --------
         >>> mi = pd.MultiIndex.from_arrays([["a"], ["b"]])

pandas/tests/arrays/interval/test_interval_pyarrow.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 from pandas.core.arrays import IntervalArray
@@ -80,6 +82,7 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.filterwarnings(
     "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
 )

pandas/tests/arrays/masked/test_arrow_compat.py

@@ -1,12 +1,18 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 
-pytestmark = pytest.mark.filterwarnings(
-    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
-)
+pytestmark = [
+    pytest.mark.filterwarnings(
+        "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+    ),
+    pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
+]
+
 
 pa = pytest.importorskip("pyarrow")
 

pandas/tests/arrays/masked/test_function.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.core.dtypes.common import is_integer_dtype
 
 import pandas as pd
@@ -60,7 +58,6 @@ def test_tolist(data):
     tm.assert_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_to_numpy():
     # GH#56991
 

pandas/tests/arrays/period/test_arrow_compat.py

@@ -1,5 +1,7 @@
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat.pyarrow import pa_version_under10p1
 
 from pandas.core.dtypes.dtypes import PeriodDtype
@@ -77,6 +79,7 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_arrow_table_roundtrip():
     from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
 
@@ -96,6 +99,7 @@ def test_arrow_table_roundtrip():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_arrow_load_from_zero_chunks():
     # GH-41040
 

pandas/tests/arrays/string_/test_string.py

@@ -8,6 +8,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat.pyarrow import pa_version_under12p0
 
 from pandas.core.dtypes.common import is_dtype_equal
@@ -511,6 +513,7 @@ def test_arrow_array(dtype):
     assert arr.equals(expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
 def test_arrow_roundtrip(dtype, string_storage2, request, using_infer_string):
     # roundtrip possible from arrow 1.0.0
@@ -539,6 +542,7 @@ def test_arrow_roundtrip(dtype, string_storage2, request, using_infer_string):
     assert result.loc[2, "a"] is result["a"].dtype.na_value
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
 def test_arrow_load_from_zero_chunks(
     dtype, string_storage2, request, using_infer_string

pandas/tests/arrays/test_array.py

@@ -5,6 +5,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 from pandas.api.extensions import register_extension_dtype
@@ -285,6 +287,7 @@ def test_array_copy():
     assert tm.shares_memory(a, b)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "data, expected",
     [

pandas/tests/dtypes/test_common.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 from pandas.core.dtypes.astype import astype_array
@@ -128,6 +130,7 @@ def test_dtype_equal(name1, dtype1, name2, dtype2):
         assert not com.is_dtype_equal(dtype1, dtype2)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("name,dtype", list(dtypes.items()), ids=lambda x: str(x))
 def test_pyarrow_string_import_error(name, dtype):
     # GH-44276