Merge branch 'main' into main

Author: sanjanam1998

doc/source/whatsnew/v3.0.0.rst

@@ -1014,6 +1014,7 @@ Strings
 ^^^^^^^
 - Bug in :meth:`Series.str.zfill` raising ``AttributeError`` for :class:`ArrowDtype` (:issue:`61485`)
 - Bug in :meth:`Series.value_counts` would not respect ``sort=False`` for series having ``string`` dtype (:issue:`55224`)
+- Bug in multiplication with a :class:`StringDtype` incorrectly allowing multiplying by bools; explicitly cast to integers instead (:issue:`62595`)
 
 Interval
 ^^^^^^^^

pandas/core/arrays/string_.py

@@ -1113,6 +1113,16 @@ def _cmp_method(self, other, op):
                 other = np.asarray(other)
             other = other[valid]
 
+        other_dtype = getattr(other, "dtype", None)
+        if op.__name__.strip("_") in ["mul", "rmul"] and (
+            lib.is_bool(other) or lib.is_np_dtype(other_dtype, "b")
+        ):
+            # GH#62595
+            raise TypeError(
+                "Cannot multiply StringArray by bools. "
+                "Explicitly cast to integers instead."
+            )
+
         if op.__name__ in ops.ARITHMETIC_BINOPS:
             result = np.empty_like(self._ndarray, dtype="object")
             result[mask] = self.dtype.na_value

pandas/io/formats/info.py

@@ -1096,7 +1096,7 @@ def headers(self) -> Sequence[str]:
 
     def _gen_rows_without_counts(self) -> Iterator[Sequence[str]]:
         """Iterator with string representation of body data without counts."""
-        yield from self._gen_dtypes()
+        yield from ([dtype] for dtype in self._gen_dtypes())
 
     def _gen_rows_with_counts(self) -> Iterator[Sequence[str]]:
         """Iterator with string representation of body data with counts."""

pandas/tests/arithmetic/test_string.py

@@ -112,3 +112,25 @@ def test_pyarrow_numpy_string_invalid():
 
     with pytest.raises(TypeError, match="Invalid comparison"):
         ser > ser4
+
+
+def test_mul_bool_invalid(any_string_dtype):
+    # GH#62595
+    dtype = any_string_dtype
+    ser = Series(["a", "b", "c"], dtype=dtype)
+
+    if dtype == object:
+        pytest.skip("This is not expect to raise")
+    elif dtype.storage == "python":
+        msg = "Cannot multiply StringArray by bools. Explicitly cast to integers"
+    else:
+        msg = "Can only string multiply by an integer"
+
+    with pytest.raises(TypeError, match=msg):
+        False * ser
+    with pytest.raises(TypeError, match=msg):
+        ser * True
+    with pytest.raises(TypeError, match=msg):
+        ser * np.array([True, False, True], dtype=bool)
+    with pytest.raises(TypeError, match=msg):
+        np.array([True, False, True], dtype=bool) * ser

pandas/tests/series/methods/test_info.py

@@ -190,3 +190,23 @@ def test_info_memory_usage_bug_on_multiindex():
     # high upper bound
     diff = unstacked.memory_usage(deep=True).sum() - s.memory_usage(deep=True)
     assert diff < 2000
+
+
+def test_info_show_counts_false():
+    s = Series([1])
+    buf = StringIO()
+    s.info(buf=buf, show_counts=False)
+    result = buf.getvalue()
+    memory_bytes = float(s.memory_usage())
+    expected = textwrap.dedent(
+        f"""\
+    <class 'pandas.Series'>
+    RangeIndex: 1 entries, 0 to 0
+    Series name: None
+    Dtype
+    -----
+    int64
+    dtypes: int64(1)
+    memory usage: {memory_bytes} bytes"""
+    )
+    assert result.strip() == expected.strip()

pandas/tests/util/test_assert_frame_equal.py

@@ -1,3 +1,4 @@
+import numpy as np
 import pytest
 
 from pandas.errors import Pandas4Warning
@@ -413,3 +414,12 @@ def test_datetimelike_compat_deprecated():
         tm.assert_series_equal(df["a"], df["a"], check_datetimelike_compat=True)
     with tm.assert_produces_warning(Pandas4Warning, match=msg):
         tm.assert_series_equal(df["a"], df["a"], check_datetimelike_compat=False)
+
+
+@pytest.mark.parametrize("na_value", [pd.NA, np.nan, None])
+def test_assert_frame_equal_nested_df_na(na_value):
+    # GH#43022
+    inner = DataFrame({"a": [1, na_value]})
+    df1 = DataFrame({"df": [inner]})
+    df2 = DataFrame({"df": [inner]})
+    tm.assert_frame_equal(df1, df2)