DEPR: non-bool na for obj.str.contains

Author: jbrockmendel

pandas/core/arrays/string_arrow.py

@@ -6,6 +6,7 @@
     TYPE_CHECKING,
     Union,
 )
+import warnings
 
 import numpy as np
 
@@ -19,6 +20,7 @@
     pa_version_under10p1,
     pa_version_under13p0,
 )
+from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
     is_scalar,
@@ -295,6 +297,14 @@ def _str_contains(
             result = pc.match_substring(self._pa_array, pat, ignore_case=not case)
         result = self._result_converter(result, na=na)
         if not isna(na):
+            if not isinstance(na, bool):
+                # GH#59561
+                warnings.warn(
+                    "Allowing a non-bool 'na' in obj.str.contains is deprecated "
+                    "and will raise in a future version.",
+                    FutureWarning,
+                    stacklevel=find_stack_level(),
+                )
             result[isna(result)] = bool(na)
         return result
 

pandas/core/strings/object_array.py

@@ -9,12 +9,14 @@
     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.core.dtypes.missing import isna
 
@@ -142,6 +144,14 @@ def _str_contains(
             else:
                 upper_pat = pat.upper()
                 f = lambda x: upper_pat in x.upper()
+        if not isna(na) and not isinstance(na, bool):
+            # GH#59561
+            warnings.warn(
+                "Allowing a non-bool 'na' in obj.str.contains is deprecated "
+                "and will raise in a future version.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
         return self._str_map(f, na, dtype=np.dtype("bool"))
 
     def _str_startswith(self, pat, na=None):

pandas/tests/strings/test_find_replace.py

@@ -166,7 +166,16 @@ def test_contains_na_kwarg_for_nullable_string_dtype(
     # https://github.com/pandas-dev/pandas/pull/41025#issuecomment-824062416
 
     values = Series(["a", "b", "c", "a", np.nan], dtype=nullable_string_dtype)
-    result = values.str.contains("a", na=na, regex=regex)
+
+    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):
+        result = values.str.contains("a", na=na, regex=regex)
     expected = Series([True, False, False, True, expected], dtype="boolean")
     tm.assert_series_equal(result, expected)
 
@@ -232,7 +241,12 @@ def test_contains_nan(any_string_dtype):
     expected = Series([True, True, True], dtype=expected_dtype)
     tm.assert_series_equal(result, expected)
 
-    result = s.str.contains("foo", na="foo")
+    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: