String dtype: remove fallback Perfomance warnings for string methods (#59760)

Author: jorisvandenbossche

pandas/core/arrays/arrow/_arrow_utils.py

@@ -1,24 +1,8 @@
 from __future__ import annotations
 
-import warnings
-
 import numpy as np
 import pyarrow
 
-from pandas.errors import PerformanceWarning
-from pandas.util._exceptions import find_stack_level
-
-
-def fallback_performancewarning(version: str | None = None) -> None:
-    """
-    Raise a PerformanceWarning for falling back to ExtensionArray's
-    non-pyarrow method
-    """
-    msg = "Falling back on a non-pyarrow code path which may decrease performance."
-    if version is not None:
-        msg += f" Upgrade to pyarrow >={version} to possibly suppress this warning."
-    warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
-
 
 def pyarrow_array_to_numpy_and_mask(
     arr, dtype: np.dtype

pandas/core/arrays/string_arrow.py

@@ -42,8 +42,6 @@
     import pyarrow as pa
     import pyarrow.compute as pc
 
-    from pandas.core.arrays.arrow._arrow_utils import fallback_performancewarning
-
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
@@ -301,7 +299,6 @@ def _str_contains(
         self, pat, case: bool = True, flags: int = 0, na=np.nan, regex: bool = True
     ):
         if flags:
-            fallback_performancewarning()
             return super()._str_contains(pat, case, flags, na, regex)
 
         if not isna(na):
@@ -327,7 +324,6 @@ def _str_replace(
         regex: bool = True,
     ):
         if isinstance(pat, re.Pattern) or callable(repl) or not case or flags:
-            fallback_performancewarning()
             return super()._str_replace(pat, repl, n, case, flags, regex)
 
         return ArrowExtensionArray._str_replace(self, pat, repl, n, case, flags, regex)

pandas/tests/extension/test_string.py

@@ -212,7 +212,6 @@ def test_compare_scalar(self, data, comparison_op):
         ser = pd.Series(data)
         self._compare_other(ser, data, comparison_op, "abc")
 
-    @pytest.mark.filterwarnings("ignore:Falling back:pandas.errors.PerformanceWarning")
     def test_groupby_extension_apply(self, data_for_grouping, groupby_apply_op):
         super().test_groupby_extension_apply(data_for_grouping, groupby_apply_op)
 

pandas/tests/indexes/test_setops.py

@@ -240,9 +240,6 @@ def test_intersection_base(self, index):
             with pytest.raises(TypeError, match=msg):
                 first.intersection([1, 2, 3])
 
-    @pytest.mark.filterwarnings(
-        "ignore:Falling back on a non-pyarrow:pandas.errors.PerformanceWarning"
-    )
     @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
     def test_union_base(self, index):
         index = index.unique()
@@ -270,9 +267,6 @@ def test_union_base(self, index):
                 first.union([1, 2, 3])
 
     @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
-    @pytest.mark.filterwarnings(
-        "ignore:Falling back on a non-pyarrow:pandas.errors.PerformanceWarning"
-    )
     def test_difference_base(self, sort, index):
         first = index[2:]
         second = index[:4]
@@ -299,9 +293,6 @@ def test_difference_base(self, sort, index):
                 first.difference([1, 2, 3], sort)
 
     @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
-    @pytest.mark.filterwarnings(
-        "ignore:Falling back on a non-pyarrow:pandas.errors.PerformanceWarning"
-    )
     def test_symmetric_difference(self, index):
         if isinstance(index, CategoricalIndex):
             pytest.skip(f"Not relevant for {type(index).__name__}")
@@ -523,9 +514,6 @@ def test_intersection_difference_match_empty(self, index, sort):
 
 
 @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
-@pytest.mark.filterwarnings(
-    "ignore:Falling back on a non-pyarrow:pandas.errors.PerformanceWarning"
-)
 @pytest.mark.parametrize(
     "method", ["intersection", "union", "difference", "symmetric_difference"]
 )

pandas/tests/strings/test_find_replace.py

@@ -4,10 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
-from pandas.compat import HAS_PYARROW
-from pandas.errors import PerformanceWarning
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -25,10 +21,6 @@
 # --------------------------------------------------------------------------------------
 
 
-def using_pyarrow(dtype):
-    return dtype == "string" and dtype.storage == "pyarrow"
-
-
 def test_contains(any_string_dtype):
     values = np.array(
         ["foo", np.nan, "fooommm__foo", "mmm_", "foommm[_]+bar"], dtype=np.object_
@@ -281,10 +273,13 @@ def test_contains_nan(any_string_dtype):
 # --------------------------------------------------------------------------------------
 
 
-@pytest.mark.xfail(
-    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)", strict=False
-)
-def test_startswith_endswith_validate_na(any_string_dtype):
+def test_startswith_endswith_validate_na(request, any_string_dtype):
+    if (
+        any_string_dtype == "string"
+        and any_string_dtype.na_value is np.nan
+        and any_string_dtype.storage == "python"
+    ):
+        request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
     # GH#59615
     ser = Series(
         ["om", np.nan, "foo_nom", "nom", "bar_foo", np.nan, "foo"],
@@ -462,8 +457,7 @@ def test_replace_mixed_object():
 def test_replace_unicode(any_string_dtype):
     ser = Series([b"abcd,\xc3\xa0".decode("utf-8")], dtype=any_string_dtype)
     expected = Series([b"abcd, \xc3\xa0".decode("utf-8")], dtype=any_string_dtype)
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace(r"(?<=\w),(?=\w)", ", ", flags=re.UNICODE, regex=True)
+    result = ser.str.replace(r"(?<=\w),(?=\w)", ", ", flags=re.UNICODE, regex=True)
     tm.assert_series_equal(result, expected)
 
 
@@ -483,8 +477,7 @@ def test_replace_callable(any_string_dtype):
 
     # test with callable
     repl = lambda m: m.group(0).swapcase()
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace("[a-z][A-Z]{2}", repl, n=2, regex=True)
+    result = ser.str.replace("[a-z][A-Z]{2}", repl, n=2, regex=True)
     expected = Series(["foObaD__baRbaD", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
@@ -502,19 +495,15 @@ def test_replace_callable_raises(any_string_dtype, repl):
         r"(?(3)required )positional arguments?"
     )
     with pytest.raises(TypeError, match=msg):
-        with tm.maybe_produces_warning(
-            PerformanceWarning, using_pyarrow(any_string_dtype)
-        ):
-            values.str.replace("a", repl, regex=True)
+        values.str.replace("a", repl, regex=True)
 
 
 def test_replace_callable_named_groups(any_string_dtype):
     # test regex named groups
     ser = Series(["Foo Bar Baz", np.nan], dtype=any_string_dtype)
     pat = r"(?P<first>\w+) (?P<middle>\w+) (?P<last>\w+)"
     repl = lambda m: m.group("middle").swapcase()
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace(pat, repl, regex=True)
+    result = ser.str.replace(pat, repl, regex=True)
     expected = Series(["bAR", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
@@ -525,13 +514,11 @@ def test_replace_compiled_regex(any_string_dtype):
 
     # test with compiled regex
     pat = re.compile(r"BAD_*")
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace(pat, "", regex=True)
+    result = ser.str.replace(pat, "", regex=True)
     expected = Series(["foobar", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace(pat, "", n=1, regex=True)
+    result = ser.str.replace(pat, "", n=1, regex=True)
     expected = Series(["foobarBAD", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
@@ -552,8 +539,7 @@ def test_replace_compiled_regex_unicode(any_string_dtype):
     ser = Series([b"abcd,\xc3\xa0".decode("utf-8")], dtype=any_string_dtype)
     expected = Series([b"abcd, \xc3\xa0".decode("utf-8")], dtype=any_string_dtype)
     pat = re.compile(r"(?<=\w),(?=\w)", flags=re.UNICODE)
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace(pat, ", ", regex=True)
+    result = ser.str.replace(pat, ", ", regex=True)
     tm.assert_series_equal(result, expected)
 
 
@@ -580,8 +566,7 @@ def test_replace_compiled_regex_callable(any_string_dtype):
     ser = Series(["fooBAD__barBAD", np.nan], dtype=any_string_dtype)
     repl = lambda m: m.group(0).swapcase()
     pat = re.compile("[a-z][A-Z]{2}")
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace(pat, repl, n=2, regex=True)
+    result = ser.str.replace(pat, repl, n=2, regex=True)
     expected = Series(["foObaD__baRbaD", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
@@ -629,8 +614,7 @@ def test_replace_moar(any_string_dtype):
     )
     tm.assert_series_equal(result, expected)
 
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace("A", "YYY", case=False)
+    result = ser.str.replace("A", "YYY", case=False)
     expected = Series(
         [
             "YYY",
@@ -648,8 +632,7 @@ def test_replace_moar(any_string_dtype):
     )
     tm.assert_series_equal(result, expected)
 
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace("^.a|dog", "XX-XX ", case=False, regex=True)
+    result = ser.str.replace("^.a|dog", "XX-XX ", case=False, regex=True)
     expected = Series(
         [
             "A",
@@ -672,13 +655,11 @@ def test_replace_not_case_sensitive_not_regex(any_string_dtype):
     # https://github.com/pandas-dev/pandas/issues/41602
     ser = Series(["A.", "a.", "Ab", "ab", np.nan], dtype=any_string_dtype)
 
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace("a", "c", case=False, regex=False)
+    result = ser.str.replace("a", "c", case=False, regex=False)
     expected = Series(["c.", "c.", "cb", "cb", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.replace("a.", "c.", case=False, regex=False)
+    result = ser.str.replace("a.", "c.", case=False, regex=False)
     expected = Series(["c.", "c.", "Ab", "ab", np.nan], dtype=any_string_dtype)
     tm.assert_series_equal(result, expected)
 
@@ -850,8 +831,7 @@ def test_fullmatch_case_kwarg(any_string_dtype):
     result = ser.str.fullmatch("ab", case=False)
     tm.assert_series_equal(result, expected)
 
-    with tm.maybe_produces_warning(PerformanceWarning, using_pyarrow(any_string_dtype)):
-        result = ser.str.fullmatch("ab", flags=re.IGNORECASE)
+    result = ser.str.fullmatch("ab", flags=re.IGNORECASE)
     tm.assert_series_equal(result, expected)
 
 
@@ -1036,17 +1016,13 @@ def test_flags_kwarg(any_string_dtype):
 
     pat = r"([A-Z0-9._%+-]+)@([A-Z0-9.-]+)\.([A-Z]{2,4})"
 
-    use_pyarrow = using_pyarrow(any_string_dtype)
-
     result = data.str.extract(pat, flags=re.IGNORECASE, expand=True)
     assert result.iloc[0].tolist() == ["dave", "google", "com"]
 
-    with tm.maybe_produces_warning(PerformanceWarning, use_pyarrow):
-        result = data.str.match(pat, flags=re.IGNORECASE)
+    result = data.str.match(pat, flags=re.IGNORECASE)
     assert result.iloc[0]
 
-    with tm.maybe_produces_warning(PerformanceWarning, use_pyarrow):
-        result = data.str.fullmatch(pat, flags=re.IGNORECASE)
+    result = data.str.fullmatch(pat, flags=re.IGNORECASE)
     assert result.iloc[0]
 
     result = data.str.findall(pat, flags=re.IGNORECASE)
@@ -1056,8 +1032,6 @@ def test_flags_kwarg(any_string_dtype):
     assert result.iloc[0] == 1
 
     msg = "has match groups"
-    with tm.assert_produces_warning(
-        UserWarning, match=msg, raise_on_extra_warnings=not use_pyarrow
-    ):
+    with tm.assert_produces_warning(UserWarning, match=msg):
         result = data.str.contains(pat, flags=re.IGNORECASE)
     assert result.iloc[0]

pandas/tests/strings/test_string_array.py

@@ -12,7 +12,6 @@
 )
 
 
-@pytest.mark.filterwarnings("ignore:Falling back")
 def test_string_array(nullable_string_dtype, any_string_method):
     method_name, args, kwargs = any_string_method