CLN: Enforce deprecation of not validating na argument to string methods (pandas-dev#62399)

Author: rhshadrach

doc/source/whatsnew/v3.0.0.rst

@@ -797,6 +797,7 @@ Other Removals
 - Enforce deprecation in :func:`testing.assert_series_equal` and :func:`testing.assert_frame_equal` with object dtype and mismatched null-like values, which are now considered not-equal (:issue:`18463`)
 - Enforce banning of upcasting in in-place setitem-like operations (:issue:`59007`) (see `PDEP6 <https://pandas.pydata.org/pdeps/0006-ban-upcasting.html>`_)
 - Enforced deprecation ``all`` and ``any`` reductions with ``datetime64``, :class:`DatetimeTZDtype`, and :class:`PeriodDtype` dtypes (:issue:`58029`)
+- Enforced deprecation allowing non-``bool`` and NA values for ``na`` in :meth:`.str.contains`, :meth:`.str.startswith`, and :meth:`.str.endswith` (:issue:`59615`)
 - Enforced deprecation disallowing ``float`` "periods" in :func:`date_range`, :func:`period_range`, :func:`timedelta_range`, :func:`interval_range`,  (:issue:`56036`)
 - Enforced deprecation disallowing parsing datetimes with mixed time zones unless user passes ``utc=True`` to :func:`to_datetime` (:issue:`57275`)
 - Enforced deprecation in :meth:`Series.value_counts` and :meth:`Index.value_counts` with object dtype performing dtype inference on the ``.index`` of the result (:issue:`56161`)

pandas/core/arrays/string_arrow.py

@@ -6,7 +6,6 @@
     TYPE_CHECKING,
     Self,
 )
-import warnings
 
 import numpy as np
 
@@ -19,7 +18,7 @@
     PYARROW_MIN_VERSION,
     pa_version_under16p0,
 )
-from pandas.util._exceptions import find_stack_level
+from pandas.util._validators import validate_na_arg
 
 from pandas.core.dtypes.common import (
     is_scalar,
@@ -244,17 +243,7 @@ def insert(self, loc: int, item) -> ArrowStringArray:
         return super().insert(loc, item)
 
     def _convert_bool_result(self, values, na=lib.no_default, method_name=None):
-        if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
-            # TODO: Enforce in 3.0 (#59615)
-            # GH#59561
-            warnings.warn(
-                f"Allowing a non-bool 'na' in obj.str.{method_name} is deprecated "
-                "and will raise in a future version.",
-                FutureWarning,  # pdlint: ignore[warning_class]
-                stacklevel=find_stack_level(),
-            )
-            na = bool(na)
-
+        validate_na_arg(na, name="na")
         if self.dtype.na_value is np.nan:
             if na is lib.no_default or isna(na):
                 # NaN propagates as False

pandas/core/strings/object_array.py

@@ -9,14 +9,13 @@
     cast,
 )
 import unicodedata
-import warnings
 
 import numpy as np
 
 from pandas._libs import lib
 import pandas._libs.missing as libmissing
 import pandas._libs.ops as libops
-from pandas.util._exceptions import find_stack_level
+from pandas.util._validators import validate_na_arg
 
 from pandas.core.dtypes.common import pandas_dtype
 from pandas.core.dtypes.missing import isna
@@ -145,6 +144,7 @@ def _str_contains(
         na=lib.no_default,
         regex: bool = True,
     ):
+        validate_na_arg(na, name="na")
         if regex:
             if not case:
                 flags |= re.IGNORECASE
@@ -158,41 +158,16 @@ def _str_contains(
             else:
                 upper_pat = pat.upper()
                 f = lambda x: upper_pat in x.upper()
-        if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
-            # TODO: Enforce in 3.0 (#59615)
-            # GH#59561
-            warnings.warn(
-                "Allowing a non-bool 'na' in obj.str.contains is deprecated "
-                "and will raise in a future version.",
-                FutureWarning,  # pdlint: ignore[warning_class]
-                stacklevel=find_stack_level(),
-            )
         return self._str_map(f, na, dtype=np.dtype("bool"))
 
     def _str_startswith(self, pat, na=lib.no_default):
+        validate_na_arg(na, name="na")
         f = lambda x: x.startswith(pat)
-        if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
-            # TODO: Enforce in 3.0 (#59615)
-            # GH#59561
-            warnings.warn(
-                "Allowing a non-bool 'na' in obj.str.startswith is deprecated "
-                "and will raise in a future version.",
-                FutureWarning,  # pdlint: ignore[warning_class]
-                stacklevel=find_stack_level(),
-            )
         return self._str_map(f, na_value=na, dtype=np.dtype(bool))
 
     def _str_endswith(self, pat, na=lib.no_default):
+        validate_na_arg(na, name="na")
         f = lambda x: x.endswith(pat)
-        if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
-            # TODO: Enforce in 3.0 (#59615)
-            # GH#59561
-            warnings.warn(
-                "Allowing a non-bool 'na' in obj.str.endswith is deprecated "
-                "and will raise in a future version.",
-                FutureWarning,  # pdlint: ignore[warning_class]
-                stacklevel=find_stack_level(),
-            )
         return self._str_map(f, na_value=na, dtype=np.dtype(bool))
 
     def _str_replace(

pandas/tests/strings/test_find_replace.py

@@ -175,17 +175,14 @@ def test_contains_na_kwarg_for_nullable_string_dtype(
 
     values = Series(["a", "b", "c", "a", np.nan], dtype=nullable_string_dtype)
 
-    msg = (
-        "Allowing a non-bool 'na' in obj.str.contains is deprecated and "
-        "will raise in a future version"
-    )
-    warn = None
-    if not pd.isna(na) and not isinstance(na, bool):
-        warn = FutureWarning
-    with tm.assert_produces_warning(warn, match=msg):
+    if na in [0, 3] and na is not False:
+        msg = f"na must be None, pd.NA, np.nan, True, or False; got {na}"
+        with pytest.raises(ValueError, match=msg):
+            values.str.contains("a", na=na, regex=regex)
+    else:
         result = values.str.contains("a", na=na, regex=regex)
-    expected = Series([True, False, False, True, expected], dtype="boolean")
-    tm.assert_series_equal(result, expected)
+        expected = Series([True, False, False, True, expected], dtype="boolean")
+        tm.assert_series_equal(result, expected)
 
 
 def test_contains_moar(any_string_dtype):
@@ -255,19 +252,9 @@ def test_contains_nan(any_string_dtype):
     expected = Series([True, True, True], dtype=expected_dtype)
     tm.assert_series_equal(result, expected)
 
-    msg = (
-        "Allowing a non-bool 'na' in obj.str.contains is deprecated and "
-        "will raise in a future version"
-    )
-    with tm.assert_produces_warning(FutureWarning, match=msg):
-        result = s.str.contains("foo", na="foo")
-    if any_string_dtype == "object":
-        expected = Series(["foo", "foo", "foo"], dtype=np.object_)
-    elif any_string_dtype.na_value is np.nan:
-        expected = Series([True, True, True], dtype=np.bool_)
-    else:
-        expected = Series([True, True, True], dtype="boolean")
-    tm.assert_series_equal(result, expected)
+    msg = "na must be None, pd.NA, np.nan, True, or False; got foo"
+    with pytest.raises(ValueError, match=msg):
+        s.str.contains("foo", na="foo")
 
     result = s.str.contains("foo")
     if any_string_dtype == "str":
@@ -352,12 +339,10 @@ def test_startswith_endswith_validate_na(any_string_dtype):
         ["om", np.nan, "foo_nom", "nom", "bar_foo", np.nan, "foo"],
         dtype=any_string_dtype,
     )
-
-    msg = "Allowing a non-bool 'na' in obj.str.startswith is deprecated"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    msg = "na must be None, pd.NA, np.nan, True, or False; got baz"
+    with pytest.raises(ValueError, match=msg):
         ser.str.startswith("kapow", na="baz")
-    msg = "Allowing a non-bool 'na' in obj.str.endswith is deprecated"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with pytest.raises(ValueError, match=msg):
         ser.str.endswith("bar", na="baz")
 
 

pandas/util/_validators.py

@@ -17,6 +17,7 @@
 import numpy as np
 
 from pandas._libs import lib
+from pandas._libs.missing import NA
 
 from pandas.core.dtypes.common import (
     is_bool,
@@ -269,6 +270,33 @@ def validate_bool_kwarg(
     return value
 
 
+def validate_na_arg(value, name: str):
+    """
+    Validate na arguments.
+
+    Parameters
+    ----------
+    value : object
+        Value to validate.
+    name : str
+        Name of the argument, used to raise an informative error message.
+
+    Raises
+    ______
+    ValueError
+        When ``value`` is determined to be invalid.
+    """
+    if (
+        value is lib.no_default
+        or isinstance(value, bool)
+        or value is None
+        or value is NA
+        or (lib.is_float(value) and np.isnan(value))
+    ):
+        return
+    raise ValueError(f"{name} must be None, pd.NA, np.nan, True, or False; got {value}")
+
+
 def validate_fillna_kwargs(value, method, validate_scalar_dict_value: bool = True):
     """
     Validate the keyword arguments to 'fillna'.