DEPR: fix stacklevel for DataFrame(mgr) deprecation (#55591)

Author: jorisvandenbossche

doc/source/user_guide/10min.rst

@@ -763,14 +763,12 @@ Parquet
 Writing to a Parquet file:
 
 .. ipython:: python
-   :okwarning:
 
    df.to_parquet("foo.parquet")
 
 Reading from a Parquet file Store using :func:`read_parquet`:
 
 .. ipython:: python
-   :okwarning:
 
    pd.read_parquet("foo.parquet")
 

doc/source/user_guide/io.rst

@@ -2247,7 +2247,6 @@ For line-delimited json files, pandas can also return an iterator which reads in
 Line-limited json can also be read using the pyarrow reader by specifying ``engine="pyarrow"``.
 
 .. ipython:: python
-   :okwarning:
 
    from io import BytesIO
    df = pd.read_json(BytesIO(jsonl.encode()), lines=True, engine="pyarrow")
@@ -5372,15 +5371,13 @@ See the documentation for `pyarrow <https://arrow.apache.org/docs/python/>`__ an
 Write to a parquet file.
 
 .. ipython:: python
-   :okwarning:
 
    df.to_parquet("example_pa.parquet", engine="pyarrow")
    df.to_parquet("example_fp.parquet", engine="fastparquet")
 
 Read from a parquet file.
 
 .. ipython:: python
-   :okwarning:
 
    result = pd.read_parquet("example_fp.parquet", engine="fastparquet")
    result = pd.read_parquet("example_pa.parquet", engine="pyarrow")
@@ -5390,7 +5387,6 @@ Read from a parquet file.
 By setting the ``dtype_backend`` argument you can control the default dtypes used for the resulting DataFrame.
 
 .. ipython:: python
-   :okwarning:
 
    result = pd.read_parquet("example_pa.parquet", engine="pyarrow", dtype_backend="pyarrow")
 
@@ -5404,7 +5400,6 @@ By setting the ``dtype_backend`` argument you can control the default dtypes use
 Read only certain columns of a parquet file.
 
 .. ipython:: python
-   :okwarning:
 
    result = pd.read_parquet(
        "example_fp.parquet",
@@ -5433,7 +5428,6 @@ Serializing a ``DataFrame`` to parquet may include the implicit index as one or
 more columns in the output file. Thus, this code:
 
 .. ipython:: python
-   :okwarning:
 
     df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
     df.to_parquet("test.parquet", engine="pyarrow")
@@ -5450,7 +5444,6 @@ If you want to omit a dataframe's indexes when writing, pass ``index=False`` to
 :func:`~pandas.DataFrame.to_parquet`:
 
 .. ipython:: python
-   :okwarning:
 
     df.to_parquet("test.parquet", index=False)
 
@@ -5473,7 +5466,6 @@ Partitioning Parquet files
 Parquet supports partitioning of data based on the values of one or more columns.
 
 .. ipython:: python
-   :okwarning:
 
     df = pd.DataFrame({"a": [0, 0, 1, 1], "b": [0, 1, 0, 1]})
     df.to_parquet(path="test", engine="pyarrow", partition_cols=["a"], compression=None)
@@ -5539,14 +5531,12 @@ ORC format, :func:`~pandas.read_orc` and :func:`~pandas.DataFrame.to_orc`. This
 Write to an orc file.
 
 .. ipython:: python
-   :okwarning:
 
    df.to_orc("example_pa.orc", engine="pyarrow")
 
 Read from an orc file.
 
 .. ipython:: python
-   :okwarning:
 
    result = pd.read_orc("example_pa.orc")
 
@@ -5555,7 +5545,6 @@ Read from an orc file.
 Read only certain columns of an orc file.
 
 .. ipython:: python
-   :okwarning:
 
    result = pd.read_orc(
        "example_pa.orc",

doc/source/user_guide/pyarrow.rst

@@ -104,7 +104,6 @@ To convert a :external+pyarrow:py:class:`pyarrow.Table` to a :class:`DataFrame`,
 :external+pyarrow:py:meth:`pyarrow.Table.to_pandas` method with ``types_mapper=pd.ArrowDtype``.
 
 .. ipython:: python
-   :okwarning:
 
    table = pa.table([pa.array([1, 2, 3], type=pa.int64())], names=["a"])
 
@@ -165,7 +164,6 @@ functions provide an ``engine`` keyword that can dispatch to PyArrow to accelera
 * :func:`read_feather`
 
 .. ipython:: python
-   :okwarning:
 
    import io
    data = io.StringIO("""a,b,c
@@ -180,7 +178,6 @@ PyArrow-backed data by specifying the parameter ``dtype_backend="pyarrow"``. A r
 ``engine="pyarrow"`` to necessarily return PyArrow-backed data.
 
 .. ipython:: python
-   :okwarning:
 
     import io
     data = io.StringIO("""a,b,c,d,e,f,g,h,i

doc/source/user_guide/scale.rst

@@ -51,7 +51,6 @@ To load the columns we want, we have two options.
 Option 1 loads in all the data and then filters to what we need.
 
 .. ipython:: python
-   :okwarning:
 
    columns = ["id_0", "name_0", "x_0", "y_0"]
 
@@ -60,7 +59,6 @@ Option 1 loads in all the data and then filters to what we need.
 Option 2 only loads the columns we request.
 
 .. ipython:: python
-   :okwarning:
 
    pd.read_parquet("timeseries_wide.parquet", columns=columns)
 
@@ -202,7 +200,6 @@ counts up to this point. As long as each individual file fits in memory, this wi
 work for arbitrary-sized datasets.
 
 .. ipython:: python
-   :okwarning:
 
    %%time
    files = pathlib.Path("data/timeseries/").glob("ts*.parquet")

doc/source/whatsnew/v2.0.0.rst

@@ -152,7 +152,6 @@ When this keyword is set to ``"pyarrow"``, then these functions will return pyar
 * :meth:`Series.convert_dtypes`
 
 .. ipython:: python
-    :okwarning:
 
     import io
     data = io.StringIO("""a,b,c,d,e,f,g,h,i

pandas/core/frame.py

@@ -697,7 +697,7 @@ def __init__(
                     "is deprecated and will raise in a future version. "
                     "Use public APIs instead.",
                     DeprecationWarning,
-                    stacklevel=find_stack_level(),
+                    stacklevel=1,  # bump to 2 once pyarrow 15.0 is released with fix
                 )
 
             if using_copy_on_write():

pandas/core/series.py

@@ -407,7 +407,7 @@ def __init__(
                     "is deprecated and will raise in a future version. "
                     "Use public APIs instead.",
                     DeprecationWarning,
-                    stacklevel=find_stack_level(),
+                    stacklevel=2,
                 )
             if using_copy_on_write():
                 data = data.copy(deep=False)
@@ -446,7 +446,7 @@ def __init__(
                     "is deprecated and will raise in a future version. "
                     "Use public APIs instead.",
                     DeprecationWarning,
-                    stacklevel=find_stack_level(),
+                    stacklevel=2,
                 )
 
             if copy:
@@ -465,7 +465,7 @@ def __init__(
                     "is deprecated and will raise in a future version. "
                     "Use public APIs instead.",
                     DeprecationWarning,
-                    stacklevel=find_stack_level(),
+                    stacklevel=2,
                 )
 
         name = ibase.maybe_extract_name(name, data, type(self))
@@ -539,7 +539,7 @@ def __init__(
                     "is deprecated and will raise in a future version. "
                     "Use public APIs instead.",
                     DeprecationWarning,
-                    stacklevel=find_stack_level(),
+                    stacklevel=2,
                 )
                 allow_mgr = True
 

pandas/tests/arrays/interval/test_interval.py

@@ -309,6 +309,9 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
+@pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
 @pytest.mark.parametrize(
     "breaks",
     [[0.0, 1.0, 2.0, 3.0], date_range("2017", periods=4, freq="D")],
@@ -325,29 +328,26 @@ def test_arrow_table_roundtrip(breaks):
 
     table = pa.table(df)
     assert isinstance(table.field("a").type, ArrowIntervalType)
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert isinstance(result["a"].dtype, pd.IntervalDtype)
     tm.assert_frame_equal(result, df)
 
     table2 = pa.concat_tables([table, table])
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table2.to_pandas()
+    result = table2.to_pandas()
     expected = pd.concat([df, df], ignore_index=True)
     tm.assert_frame_equal(result, expected)
 
     # GH-41040
     table = pa.table(
         [pa.chunked_array([], type=table.column(0).type)], schema=table.schema
     )
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     tm.assert_frame_equal(result, expected[0:0])
 
 
+@pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
 @pytest.mark.parametrize(
     "breaks",
     [[0.0, 1.0, 2.0, 3.0], date_range("2017", periods=4, freq="D")],
@@ -365,9 +365,7 @@ def test_arrow_table_roundtrip_without_metadata(breaks):
     table = table.replace_schema_metadata()
     assert table.schema.metadata is None
 
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert isinstance(result["a"].dtype, pd.IntervalDtype)
     tm.assert_frame_equal(result, df)
 

pandas/tests/arrays/masked/test_arrow_compat.py

@@ -4,6 +4,10 @@
 import pandas as pd
 import pandas._testing as tm
 
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+
 pa = pytest.importorskip("pyarrow")
 
 from pandas.core.arrays.arrow._arrow_utils import pyarrow_array_to_numpy_and_mask
@@ -36,9 +40,7 @@ def test_arrow_roundtrip(data):
     table = pa.table(df)
     assert table.field("a").type == str(data.dtype.numpy_dtype)
 
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert result["a"].dtype == data.dtype
     tm.assert_frame_equal(result, df)
 
@@ -56,9 +58,7 @@ def types_mapper(arrow_type):
     record_batch = pa.RecordBatch.from_arrays(
         [bools_array, ints_array, small_ints_array], ["bools", "ints", "small_ints"]
     )
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = record_batch.to_pandas(types_mapper=types_mapper)
+    result = record_batch.to_pandas(types_mapper=types_mapper)
     bools = pd.Series([True, None, False], dtype="boolean")
     ints = pd.Series([1, None, 2], dtype="Int64")
     small_ints = pd.Series([-1, 0, 7], dtype="Int64")
@@ -75,9 +75,7 @@ def test_arrow_load_from_zero_chunks(data):
     table = pa.table(
         [pa.chunked_array([], type=table.field("a").type)], schema=table.schema
     )
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert result["a"].dtype == data.dtype
     tm.assert_frame_equal(result, df)
 
@@ -98,18 +96,14 @@ def test_arrow_sliced(data):
 
     df = pd.DataFrame({"a": data})
     table = pa.table(df)
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.slice(2, None).to_pandas()
+    result = table.slice(2, None).to_pandas()
     expected = df.iloc[2:].reset_index(drop=True)
     tm.assert_frame_equal(result, expected)
 
     # no missing values
     df2 = df.fillna(data[0])
     table = pa.table(df2)
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.slice(2, None).to_pandas()
+    result = table.slice(2, None).to_pandas()
     expected = df2.iloc[2:].reset_index(drop=True)
     tm.assert_frame_equal(result, expected)
 

pandas/tests/arrays/period/test_arrow_compat.py

@@ -11,6 +11,11 @@
     period_array,
 )
 
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+
+
 pa = pytest.importorskip("pyarrow")
 
 
@@ -81,16 +86,12 @@ def test_arrow_table_roundtrip():
 
     table = pa.table(df)
     assert isinstance(table.field("a").type, ArrowPeriodType)
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert isinstance(result["a"].dtype, PeriodDtype)
     tm.assert_frame_equal(result, df)
 
     table2 = pa.concat_tables([table, table])
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table2.to_pandas()
+    result = table2.to_pandas()
     expected = pd.concat([df, df], ignore_index=True)
     tm.assert_frame_equal(result, expected)
 
@@ -109,9 +110,7 @@ def test_arrow_load_from_zero_chunks():
         [pa.chunked_array([], type=table.column(0).type)], schema=table.schema
     )
 
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert isinstance(result["a"].dtype, PeriodDtype)
     tm.assert_frame_equal(result, df)
 
@@ -126,8 +125,6 @@ def test_arrow_table_roundtrip_without_metadata():
     table = table.replace_schema_metadata()
     assert table.schema.metadata is None
 
-    msg = "Passing a BlockManager to DataFrame is deprecated"
-    with tm.assert_produces_warning(DeprecationWarning, match=msg):
-        result = table.to_pandas()
+    result = table.to_pandas()
     assert isinstance(result["a"].dtype, PeriodDtype)
     tm.assert_frame_equal(result, df)