CLN: Remove 3rd party warning filters (#50674)

* CLN: Remove 3rd party warning filers

* Move 3rd party warnings to pyproject.toml, some comments

* Move 3rd party warnings to pyproject.toml, some comments

Author: mroeschke

pandas/io/parquet.py

@@ -285,9 +285,6 @@ def write(
         **kwargs,
     ) -> None:
         self.validate_dataframe(df)
-        # thriftpy/protocol/compact.py:339:
-        # DeprecationWarning: tostring() is deprecated.
-        # Use tobytes() instead.
 
         if "partition_on" in kwargs and partition_cols is not None:
             raise ValueError(

pandas/tests/frame/test_unary.py

@@ -114,7 +114,10 @@ def test_pos_object(self, df):
         [
             pytest.param(
                 pd.DataFrame({"a": ["a", "b"]}),
-                marks=[pytest.mark.filterwarnings("ignore")],
+                # filterwarnings removable once min numpy version is 1.25
+                marks=[
+                    pytest.mark.filterwarnings("ignore:Applying:DeprecationWarning")
+                ],
             ),
         ],
     )

pandas/tests/io/__init__.py

@@ -1,20 +0,0 @@
-import pytest
-
-pytestmark = [
-    # fastparquet
-    pytest.mark.filterwarnings(
-        "ignore:PY_SSIZE_T_CLEAN will be required.*:DeprecationWarning"
-    ),
-    pytest.mark.filterwarnings(
-        r"ignore:`np\.bool` is a deprecated alias:DeprecationWarning"
-    ),
-    # xlrd
-    pytest.mark.filterwarnings(
-        "ignore:This method will be removed in future versions:DeprecationWarning"
-    ),
-    pytest.mark.filterwarnings(
-        "ignore:This method will be removed in future versions.  "
-        r"Use 'tree.iter\(\)' or 'list\(tree.iter\(\)\)' instead."
-        ":PendingDeprecationWarning"
-    ),
-]

pandas/tests/io/excel/__init__.py

@@ -1,12 +0,0 @@
-import pytest
-
-pytestmark = [
-    pytest.mark.filterwarnings(
-        # Looks like tree.getiterator is deprecated in favor of tree.iter
-        "ignore:This method will be removed in future versions:"
-        "PendingDeprecationWarning"
-    ),
-    pytest.mark.filterwarnings(
-        "ignore:This method will be removed in future versions:DeprecationWarning"
-    ),
-]

pandas/tests/io/excel/test_readers.py

@@ -42,7 +42,6 @@
         "openpyxl",
         marks=[
             td.skip_if_no("openpyxl"),
-            pytest.mark.filterwarnings("ignore:.*html argument"),
         ],
     ),
     pytest.param(

pandas/tests/io/pytables/__init__.py

@@ -1,14 +0,0 @@
-import pytest
-
-pytestmark = [
-    # pytables https://github.com/PyTables/PyTables/issues/822
-    pytest.mark.filterwarnings(
-        "ignore:a closed node found in the registry:UserWarning"
-    ),
-    pytest.mark.filterwarnings(
-        r"ignore:`np\.object` is a deprecated alias.*:DeprecationWarning"
-    ),
-    pytest.mark.filterwarnings(
-        r"ignore:`np\.bool` is a deprecated alias.*:DeprecationWarning"
-    ),
-]

pandas/tests/io/pytables/test_categorical.py

@@ -16,10 +16,6 @@
 
 pytestmark = [
     pytest.mark.single_cpu,
-    # pytables https://github.com/PyTables/PyTables/issues/822
-    pytest.mark.filterwarnings(
-        "ignore:a closed node found in the registry:UserWarning"
-    ),
 ]
 
 

pandas/tests/io/pytables/test_subclass.py

@@ -13,9 +13,6 @@
 )
 
 pytest.importorskip("tables")
-pytestmark = pytest.mark.filterwarnings(
-    "ignore:`np.object` is a deprecated alias:DeprecationWarning"
-)
 
 
 class TestHDFStoreSubclass:

pandas/tests/io/sas/test_sas7bdat.py

@@ -38,7 +38,6 @@ def data_test_ix(request, dirpath):
 
 
 # https://github.com/cython/cython/issues/1720
-@pytest.mark.filterwarnings("ignore:can't resolve package:ImportWarning")
 class TestSAS7BDAT:
     @pytest.mark.slow
     def test_from_file(self, dirpath, data_test_ix):

pandas/tests/io/test_common.py

@@ -50,7 +50,6 @@ def __fspath__(self):
 
 
 # https://github.com/cython/cython/issues/1720
-@pytest.mark.filterwarnings("ignore:can't resolve package:ImportWarning")
 class TestCommonIOCapabilities:
     data1 = """index,A,B,C,D
 foo,2,3,4,5
@@ -317,9 +316,6 @@ def test_read_expands_user_home_dir(
             ),
         ],
     )
-    @pytest.mark.filterwarnings(  # pytables np.object_ usage
-        "ignore:`np.object` is a deprecated alias:DeprecationWarning"
-    )
     def test_read_fspath_all(self, reader, module, path, datapath):
         pytest.importorskip(module)
         path = datapath(*path)
@@ -372,9 +368,6 @@ def test_write_fspath_all(self, writer_name, writer_kwargs, module):
                     expected = f_path.read()
                     assert result == expected
 
-    @pytest.mark.filterwarnings(  # pytables np.object_ usage
-        "ignore:`np.object` is a deprecated alias:DeprecationWarning"
-    )
     def test_write_fspath_hdf5(self):
         # Same test as write_fspath_all, except HDF5 files aren't
         # necessarily byte-for-byte identical for a given dataframe, so we'll

pandas/tests/io/test_parquet.py

@@ -3,10 +3,7 @@
 from io import BytesIO
 import os
 import pathlib
-from warnings import (
-    catch_warnings,
-    filterwarnings,
-)
+from warnings import catch_warnings
 
 import numpy as np
 import pytest
@@ -40,13 +37,7 @@
     _HAVE_PYARROW = False
 
 try:
-    with catch_warnings():
-        # `np.bool` is a deprecated alias...
-        filterwarnings("ignore", "`np.bool`", category=DeprecationWarning)
-        # accessing pd.Int64Index in pd namespace
-        filterwarnings("ignore", ".*Int64Index.*", category=FutureWarning)
-
-        import fastparquet
+    import fastparquet
 
     _HAVE_FASTPARQUET = True
 except ImportError:

pandas/tests/io/test_pickle.py

@@ -24,10 +24,7 @@
 import shutil
 import tarfile
 import uuid
-from warnings import (
-    catch_warnings,
-    simplefilter,
-)
+from warnings import catch_warnings
 import zipfile
 
 import numpy as np
@@ -132,49 +129,46 @@ def test_pickles(legacy_pickle):
     if not is_platform_little_endian():
         pytest.skip("known failure on non-little endian")
 
-    with catch_warnings(record=True):
-        simplefilter("ignore")
-
-        data = pd.read_pickle(legacy_pickle)
-
-        for typ, dv in data.items():
-            for dt, result in dv.items():
-                expected = data[typ][dt]
-
-                if typ == "series" and dt == "ts":
-                    # GH 7748
-                    tm.assert_series_equal(result, expected)
-                    assert result.index.freq == expected.index.freq
-                    assert not result.index.freq.normalize
-                    tm.assert_series_equal(result > 0, expected > 0)
-
-                    # GH 9291
-                    freq = result.index.freq
-                    assert freq + Day(1) == Day(2)
-
-                    res = freq + pd.Timedelta(hours=1)
-                    assert isinstance(res, pd.Timedelta)
-                    assert res == pd.Timedelta(days=1, hours=1)
-
-                    res = freq + pd.Timedelta(nanoseconds=1)
-                    assert isinstance(res, pd.Timedelta)
-                    assert res == pd.Timedelta(days=1, nanoseconds=1)
-                elif typ == "index" and dt == "period":
-                    tm.assert_index_equal(result, expected)
-                    assert isinstance(result.freq, MonthEnd)
-                    assert result.freq == MonthEnd()
-                    assert result.freqstr == "M"
-                    tm.assert_index_equal(result.shift(2), expected.shift(2))
-                elif typ == "series" and dt in ("dt_tz", "cat"):
-                    tm.assert_series_equal(result, expected)
-                elif typ == "frame" and dt in (
-                    "dt_mixed_tzs",
-                    "cat_onecol",
-                    "cat_and_float",
-                ):
-                    tm.assert_frame_equal(result, expected)
-                else:
-                    compare_element(result, expected, typ)
+    data = pd.read_pickle(legacy_pickle)
+
+    for typ, dv in data.items():
+        for dt, result in dv.items():
+            expected = data[typ][dt]
+
+            if typ == "series" and dt == "ts":
+                # GH 7748
+                tm.assert_series_equal(result, expected)
+                assert result.index.freq == expected.index.freq
+                assert not result.index.freq.normalize
+                tm.assert_series_equal(result > 0, expected > 0)
+
+                # GH 9291
+                freq = result.index.freq
+                assert freq + Day(1) == Day(2)
+
+                res = freq + pd.Timedelta(hours=1)
+                assert isinstance(res, pd.Timedelta)
+                assert res == pd.Timedelta(days=1, hours=1)
+
+                res = freq + pd.Timedelta(nanoseconds=1)
+                assert isinstance(res, pd.Timedelta)
+                assert res == pd.Timedelta(days=1, nanoseconds=1)
+            elif typ == "index" and dt == "period":
+                tm.assert_index_equal(result, expected)
+                assert isinstance(result.freq, MonthEnd)
+                assert result.freq == MonthEnd()
+                assert result.freqstr == "M"
+                tm.assert_index_equal(result.shift(2), expected.shift(2))
+            elif typ == "series" and dt in ("dt_tz", "cat"):
+                tm.assert_series_equal(result, expected)
+            elif typ == "frame" and dt in (
+                "dt_mixed_tzs",
+                "cat_onecol",
+                "cat_and_float",
+            ):
+                tm.assert_frame_equal(result, expected)
+            else:
+                compare_element(result, expected, typ)
 
 
 def python_pickler(obj, path):

pandas/tests/plotting/frame/test_frame_color.py

@@ -1,6 +1,5 @@
 """ Test cases for DataFrame.plot """
 import re
-import warnings
 
 import numpy as np
 import pytest
@@ -18,23 +17,13 @@
 
 @td.skip_if_no_mpl
 class TestDataFrameColor(TestPlotBase):
-    def test_mpl2_color_cycle_str(self):
+    @pytest.mark.parametrize(
+        "color", ["C0", "C1", "C2", "C3", "C4", "C5", "C6", "C7", "C8", "C9"]
+    )
+    def test_mpl2_color_cycle_str(self, color):
         # GH 15516
         df = DataFrame(np.random.randn(10, 3), columns=["a", "b", "c"])
-        colors = ["C0", "C1", "C2", "C3", "C4", "C5", "C6", "C7", "C8", "C9"]
-        with warnings.catch_warnings(record=True) as w:
-            warnings.simplefilter("always", "MatplotlibDeprecationWarning")
-
-            for color in colors:
-                _check_plot_works(df.plot, color=color)
-
-            # if warning is raised, check that it is the exact problematic one
-            # GH 36972
-            if w:
-                match = "Support for uppercase single-letter colors is deprecated"
-                warning_message = str(w[0].message)
-                msg = "MatplotlibDeprecationWarning related to CN colors was raised"
-                assert match not in warning_message, msg
+        _check_plot_works(df.plot, color=color)
 
     def test_color_single_series_list(self):
         # GH 3486

pandas/tests/test_downstream.py

@@ -18,11 +18,6 @@
 )
 import pandas._testing as tm
 
-# xarray, fsspec, fastparquet all produce these
-pytestmark = pytest.mark.filterwarnings(
-    "ignore:distutils Version classes are deprecated.*:DeprecationWarning"
-)
-
 
 def import_module(name):
     # we *only* want to skip if the module is truly not available
@@ -148,12 +143,6 @@ def test_oo_optimized_datetime_index_unpickle():
 
 @pytest.mark.network
 @tm.network
-# Cython import warning
-@pytest.mark.filterwarnings("ignore:can't:ImportWarning")
-@pytest.mark.filterwarnings(
-    # patsy needs to update their imports
-    "ignore:Using or importing the ABCs from 'collections:DeprecationWarning"
-)
 def test_statsmodels():
 
     statsmodels = import_module("statsmodels")  # noqa:F841
@@ -164,8 +153,6 @@ def test_statsmodels():
     smf.ols("Lottery ~ Literacy + np.log(Pop1831)", data=df).fit()
 
 
-# Cython import warning
-@pytest.mark.filterwarnings("ignore:can't:ImportWarning")
 def test_scikit_learn():
 
     sklearn = import_module("sklearn")  # noqa:F841
@@ -180,10 +167,8 @@ def test_scikit_learn():
     clf.predict(digits.data[-1:])
 
 
-# Cython import warning and traitlets
 @pytest.mark.network
 @tm.network
-@pytest.mark.filterwarnings("ignore")
 def test_seaborn():
 
     seaborn = import_module("seaborn")
@@ -210,8 +195,6 @@ def test_pandas_datareader():
     pandas_datareader.DataReader("F", "quandl", "2017-01-01", "2017-02-01")
 
 
-# Cython import warning
-@pytest.mark.filterwarnings("ignore:can't resolve:ImportWarning")
 def test_pyarrow(df):
 
     pyarrow = import_module("pyarrow")

pandas/tests/util/test_show_versions.py

@@ -2,8 +2,6 @@
 import os
 import re
 
-import pytest
-
 from pandas.util._print_versions import (
     _get_dependency_info,
     _get_sys_info,
@@ -12,19 +10,6 @@
 import pandas as pd
 
 
-@pytest.mark.filterwarnings(
-    # openpyxl
-    "ignore:defusedxml.lxml is no longer supported:DeprecationWarning"
-)
-@pytest.mark.filterwarnings(
-    # html5lib
-    "ignore:Using or importing the ABCs from:DeprecationWarning"
-)
-@pytest.mark.filterwarnings(
-    # https://github.com/pandas-dev/pandas/issues/35252
-    "ignore:Distutils:UserWarning"
-)
-@pytest.mark.filterwarnings("ignore:Setuptools is replacing distutils:UserWarning")
 def test_show_versions(tmpdir):
     # GH39701
     as_json = os.path.join(tmpdir, "test_output.json")

pandas/tests/window/__init__.py

@@ -1,8 +0,0 @@
-import pytest
-
-pytestmark = [
-    # 2021-02-01 needed until numba updates their usage
-    pytest.mark.filterwarnings(
-        r"ignore:`np\.int` is a deprecated alias:DeprecationWarning"
-    ),
-]