Backport PR #51312 on branch 2.0.x (CI/TST: Enable -W error:::pandas in pyproject.toml) (#51570)

Backport PR #51312: CI/TST: Enable -W error:::pandas in pyproject.toml

Co-authored-by: Matthew Roeschke <[email protected]>

Author: meeseeksmachine

.github/workflows/macos-windows.yml

@@ -18,8 +18,6 @@ env:
   PANDAS_CI: 1
   PYTEST_TARGET: pandas
   PATTERN: "not slow and not db and not network and not single_cpu"
-  ERROR_ON_WARNINGS: "1"
-
 
 permissions:
   contents: read

.github/workflows/ubuntu.yml

@@ -40,7 +40,6 @@ jobs:
           - name: "Minimum Versions"
             env_file: actions-38-minimum_versions.yaml
             pattern: "not slow and not network and not single_cpu"
-            error_on_warnings: "0"
           - name: "Locale: it_IT"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -65,12 +64,10 @@ jobs:
             env_file: actions-310.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "1"
-            error_on_warnings: "0"
           - name: "Data Manager"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_data_manager: "array"
-            error_on_warnings: "0"
           - name: "Pypy"
             env_file: actions-pypy-38.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -79,7 +76,6 @@ jobs:
             env_file: actions-310-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "-W error::DeprecationWarning -W error::FutureWarning"
-            error_on_warnings: "0"
         exclude:
           - env_file: actions-38.yaml
             pyarrow_version: "8"
@@ -99,7 +95,6 @@ jobs:
       ENV_FILE: ci/deps/${{ matrix.env_file }}
       PATTERN: ${{ matrix.pattern }}
       EXTRA_APT: ${{ matrix.extra_apt || '' }}
-      ERROR_ON_WARNINGS: ${{ matrix.error_on_warnings || '1' }}
       LANG: ${{ matrix.lang || '' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_DATA_MANAGER: ${{ matrix.pandas_data_manager || 'block' }}

ci/run_tests.sh

@@ -30,13 +30,6 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
-if [[ "$ERROR_ON_WARNINGS" == "1" ]]; then
-  for pth in $(find pandas -name '*.py' -not -path "pandas/tests/*" | sed -e 's/\.py//g' -e 's/\/__init__//g' -e 's/\//./g');
-    do
-        PYTEST_CMD="$PYTEST_CMD -W error:::$pth"
-    done
-fi
-
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"
 

pandas/_testing/_warnings.py

@@ -5,6 +5,7 @@
     nullcontext,
 )
 import re
+import sys
 from typing import (
     Generator,
     Literal,
@@ -163,6 +164,17 @@ def _assert_caught_no_extra_warnings(
 
     for actual_warning in caught_warnings:
         if _is_unexpected_warning(actual_warning, expected_warning):
+            # GH#38630 pytest.filterwarnings does not suppress these.
+            if actual_warning.category == ResourceWarning:
+                # GH 44732: Don't make the CI flaky by filtering SSL-related
+                # ResourceWarning from dependencies
+                if "unclosed <ssl.SSLSocket" in str(actual_warning.message):
+                    continue
+                # GH 44844: Matplotlib leaves font files open during the entire process
+                # upon import. Don't make CI flaky if ResourceWarning raised
+                # due to these open files.
+                if any("matplotlib" in mod for mod in sys.modules):
+                    continue
             extra_warnings.append(
                 (
                     actual_warning.category.__name__,

pandas/core/generic.py

@@ -4006,10 +4006,10 @@ class  animal  locomotion
 
         Get values at several indexes
 
-        >>> df.xs(('mammal', 'dog'))
-                    num_legs  num_wings
-        locomotion
-        walks              4          0
+        >>> df.xs(('mammal', 'dog', 'walks'))
+        num_legs     4
+        num_wings    0
+        Name: (mammal, dog, walks), dtype: int64
 
         Get values at specified index and level
 

pandas/io/sql.py

@@ -632,36 +632,9 @@ def read_sql(
     >>> pd.read_sql('test_data', 'postgres:///db_name')  # doctest:+SKIP
 
     Apply date parsing to columns through the ``parse_dates`` argument
-
-    >>> pd.read_sql('SELECT int_column, date_column FROM test_data',
-    ...             conn,
-    ...             parse_dates=["date_column"])
-       int_column date_column
-    0           0  2012-10-11
-    1           1  2010-12-11
-
     The ``parse_dates`` argument calls ``pd.to_datetime`` on the provided columns.
     Custom argument values for applying ``pd.to_datetime`` on a column are specified
     via a dictionary format:
-    1. Ignore errors while parsing the values of "date_column"
-
-    >>> pd.read_sql('SELECT int_column, date_column FROM test_data',
-    ...             conn,
-    ...             parse_dates={"date_column": {"errors": "ignore"}})
-       int_column date_column
-    0           0  2012-10-11
-    1           1  2010-12-11
-
-    2. Apply a dayfirst date parsing order on the values of "date_column"
-
-    >>> pd.read_sql('SELECT int_column, date_column FROM test_data',
-    ...             conn,
-    ...             parse_dates={"date_column": {"dayfirst": True}})
-       int_column date_column
-    0           0  2012-11-10
-    1           1  2010-11-12
-
-    3. Apply custom formatting when date parsing the values of "date_column"
 
     >>> pd.read_sql('SELECT int_column, date_column FROM test_data',
     ...             conn,

pandas/tests/frame/test_query_eval.py

@@ -1332,7 +1332,9 @@ def test_query_ea_dtypes(self, dtype):
         # GH#50261
         df = DataFrame({"a": Series([1, 2], dtype=dtype)})
         ref = {2}  # noqa:F841
-        result = df.query("a in @ref")
+        warning = RuntimeWarning if dtype == "Int64" and NUMEXPR_INSTALLED else None
+        with tm.assert_produces_warning(warning):
+            result = df.query("a in @ref")
         expected = DataFrame({"a": Series([2], dtype=dtype, index=[1])})
         tm.assert_frame_equal(result, expected)
 

pandas/tests/groupby/test_groupby.py

@@ -2774,6 +2774,9 @@ def test_sum_of_booleans(n):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.filterwarnings(
+    "ignore:invalid value encountered in remainder:RuntimeWarning"
+)
 @pytest.mark.parametrize("method", ["head", "tail", "nth", "first", "last"])
 def test_groupby_method_drop_na(method):
     # GH 21755

pandas/tests/groupby/test_nth.py

@@ -789,6 +789,9 @@ def test_nth_slices_with_column_axis(
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.filterwarnings(
+    "ignore:invalid value encountered in remainder:RuntimeWarning"
+)
 def test_head_tail_dropna_true():
     # GH#45089
     df = DataFrame(

pandas/tests/io/pytables/test_retain_attributes.py

@@ -1,5 +1,3 @@
-from warnings import catch_warnings
-
 import pytest
 
 from pandas._libs.tslibs import Timestamp
@@ -9,6 +7,7 @@
     Series,
     _testing as tm,
     date_range,
+    errors,
     read_hdf,
 )
 from pandas.tests.io.pytables.common import (
@@ -39,7 +38,7 @@ def test_retain_index_attributes(setup_path):
                 )
 
         # try to append a table with a different frequency
-        with catch_warnings(record=True):
+        with tm.assert_produces_warning(errors.AttributeConflictWarning):
             df2 = DataFrame(
                 {
                     "A": Series(
@@ -75,7 +74,7 @@ def test_retain_index_attributes(setup_path):
 def test_retain_index_attributes2(tmp_path, setup_path):
     path = tmp_path / setup_path
 
-    with catch_warnings(record=True):
+    with tm.assert_produces_warning(errors.AttributeConflictWarning):
         df = DataFrame(
             {"A": Series(range(3), index=date_range("2000-1-1", periods=3, freq="H"))}
         )
@@ -93,7 +92,7 @@ def test_retain_index_attributes2(tmp_path, setup_path):
 
     assert read_hdf(path, "data").index.name == "foo"
 
-    with catch_warnings(record=True):
+    with tm.assert_produces_warning(errors.AttributeConflictWarning):
         idx2 = date_range("2001-1-1", periods=3, freq="H")
         idx2.name = "bar"
         df2 = DataFrame({"A": Series(range(3), index=idx2)})

pandas/tests/io/sas/test_byteswap.py

@@ -29,6 +29,7 @@ def test_int_byteswap(read_offset, number, int_type, should_byteswap):
     _test(number, int_type, read_offset, should_byteswap)
 
 
+@pytest.mark.filterwarnings("ignore:overflow encountered:RuntimeWarning")
 @given(read_offset=st.integers(0, 11), number=st.floats())
 @pytest.mark.parametrize("float_type", [np.float32, np.float64])
 @pytest.mark.parametrize("should_byteswap", [True, False])

pandas/tests/series/test_arithmetic.py

@@ -32,6 +32,7 @@
     ops,
 )
 from pandas.core.computation import expressions as expr
+from pandas.core.computation.check import NUMEXPR_INSTALLED
 
 
 @pytest.fixture(autouse=True, params=[0, 1000000], ids=["numexpr", "python"])
@@ -349,14 +350,21 @@ def test_add_list_to_masked_array(self, val, dtype):
         result = [1, None, val] + ser
         tm.assert_series_equal(result, expected)
 
-    def test_add_list_to_masked_array_boolean(self):
+    def test_add_list_to_masked_array_boolean(self, request):
         # GH#22962
+        warning = (
+            UserWarning
+            if request.node.callspec.id == "numexpr" and NUMEXPR_INSTALLED
+            else None
+        )
         ser = Series([True, None, False], dtype="boolean")
-        result = ser + [True, None, True]
+        with tm.assert_produces_warning(warning):
+            result = ser + [True, None, True]
         expected = Series([True, None, True], dtype="boolean")
         tm.assert_series_equal(result, expected)
 
-        result = [True, None, True] + ser
+        with tm.assert_produces_warning(warning):
+            result = [True, None, True] + ser
         tm.assert_series_equal(result, expected)
 
 

pandas/tests/test_expressions.py

@@ -199,6 +199,9 @@ def test_invalid(self):
         result = expr._can_use_numexpr(operator.add, "+", array, array2, "evaluate")
         assert result
 
+    @pytest.mark.filterwarnings(
+        "ignore:invalid value encountered in true_divide:RuntimeWarning"
+    )
     @pytest.mark.parametrize(
         "opname,op_str",
         [("add", "+"), ("sub", "-"), ("mul", "*"), ("truediv", "/"), ("pow", "**")],

pyproject.toml

@@ -395,11 +395,14 @@ doctest_optionflags = [
   "ELLIPSIS",
 ]
 filterwarnings = [
+  "error:::pandas",
   "error::ResourceWarning",
   "error::pytest.PytestUnraisableExceptionWarning",
   "ignore:.*ssl.SSLSocket:pytest.PytestUnraisableExceptionWarning",
-  "ignore:unclosed <ssl.SSLSocket:ResourceWarning",
+  "ignore:.*ssl.SSLSocket:ResourceWarning",
   "ignore::ResourceWarning:asyncio",
+  # From plotting doctests
+  "ignore:More than 20 figures have been opened:RuntimeWarning",
   # Will be fixed in numba 0.56: https://github.com/numba/numba/issues/7758
   "ignore:`np.MachAr` is deprecated:DeprecationWarning:numba",
   "ignore:.*urllib3:DeprecationWarning:botocore",