Merge branch 'main' into main

Author: jessica-oraegbu

doc/source/whatsnew/v3.0.0.rst

@@ -1049,6 +1049,7 @@ Interval
 - Bug in :class:`Index`, :class:`Series`, :class:`DataFrame` constructors when given a sequence of :class:`Interval` subclass objects casting them to :class:`Interval` (:issue:`46945`)
 - Bug in :func:`interval_range` where start and end numeric types were always cast to 64 bit (:issue:`57268`)
 - Bug in :meth:`IntervalIndex.get_indexer` and :meth:`IntervalIndex.drop` when one of the sides of the index is non-unique (:issue:`52245`)
+- Construction of :class:`IntervalArray` and :class:`IntervalIndex` from arrays with mismatched signed/unsigned integer dtypes (e.g., ``int64`` and ``uint64``) now raises a :exc:`TypeError` instead of proceeding silently. (:issue:`55715`)
 
 Indexing
 ^^^^^^^^
@@ -1236,6 +1237,7 @@ Other
 - Bug in :meth:`DataFrame.query` where using duplicate column names led to a ``TypeError``. (:issue:`59950`)
 - Bug in :meth:`DataFrame.query` which raised an exception or produced incorrect results when expressions contained backtick-quoted column names containing the hash character ``#``, backticks, or characters that fall outside the ASCII range (U+0001..U+007F). (:issue:`59285`) (:issue:`49633`)
 - Bug in :meth:`DataFrame.query` which raised an exception when querying integer column names using backticks. (:issue:`60494`)
+- Bug in :meth:`DataFrame.rename` and :meth:`Series.rename` when passed a ``mapper``, ``index``, or ``columns`` argument that is a :class:`Series` with non-unique ``ser.index`` producing a corrupted result instead of raising ``ValueError`` (:issue:`58621`)
 - Bug in :meth:`DataFrame.sample` with ``replace=False`` and ``(n * max(weights) / sum(weights)) > 1``, the method would return biased results. Now raises ``ValueError``. (:issue:`61516`)
 - Bug in :meth:`DataFrame.shift` where passing a ``freq`` on a DataFrame with no columns did not shift the index correctly. (:issue:`60102`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)

pandas/core/arrays/interval.py

@@ -420,6 +420,18 @@ def _ensure_simple_new_inputs(
 
         dtype = IntervalDtype(left.dtype, closed=closed)
 
+        # Check for mismatched signed/unsigned integer dtypes after casting
+        left_dtype = left.dtype
+        right_dtype = right.dtype
+        if (
+            left_dtype.kind in "iu"
+            and right_dtype.kind in "iu"
+            and left_dtype.kind != right_dtype.kind
+        ):
+            raise TypeError(
+                f"Left and right arrays must have matching signedness. "
+                f"Got {left_dtype} and {right_dtype}."
+            )
         return left, right, dtype
 
     @classmethod

pandas/core/generic.py

@@ -1054,6 +1054,10 @@ def _rename(
             if level is not None:
                 level = ax._get_level_number(level)
 
+            if isinstance(replacements, ABCSeries) and not replacements.index.is_unique:
+                # GH#58621
+                raise ValueError("Cannot rename with a Series with non-unique index.")
+
             # GH 13473
             if not callable(replacements):
                 if ax._is_multi and level is not None:

pandas/core/indexes/range.py

@@ -88,13 +88,13 @@ class RangeIndex(Index):
 
     Parameters
     ----------
-    start : int (default: 0), range, or other RangeIndex instance
+    start : int, range, or other RangeIndex instance, default None
         If int and "stop" is not given, interpreted as "stop" instead.
-    stop : int (default: 0)
+    stop : int, default None
         The end value of the range (exclusive).
-    step : int (default: 1)
+    step : int, default None
         The step size of the range.
-    dtype : np.int64
+    dtype : np.int64, default None
         Unused, accepted for homogeneity with other index types.
     copy : bool, default False
         Unused, accepted for homogeneity with other index types.

pandas/tests/arrays/sparse/test_constructors.py

@@ -77,7 +77,10 @@ def test_constructor_object_dtype_bool_fill(self):
         assert arr.dtype == SparseDtype(object, False)
         assert arr.fill_value is False
         arr_expected = np.array(data, dtype=object)
-        it = (type(x) == type(y) and x == y for x, y in zip(arr, arr_expected))
+        it = (
+            type(x) == type(y) and x == y
+            for x, y in zip(arr, arr_expected, strict=True)
+        )
         assert np.fromiter(it, dtype=np.bool_).all()
 
     @pytest.mark.parametrize("dtype", [SparseDtype(int, 0), int])

pandas/tests/arrays/test_datetimes.py

@@ -144,7 +144,7 @@ def test_iter(self, dta):
     def test_astype_object(self, dta):
         result = dta.astype(object)
         assert all(x._creso == dta._creso for x in result)
-        assert all(x == y for x, y in zip(result, dta))
+        assert all(x == y for x, y in zip(result, dta, strict=True))
 
     def test_to_pydatetime(self, dta_dti):
         dta, dti = dta_dti

pandas/tests/extension/base/setitem.py

@@ -221,28 +221,28 @@ def test_setitem_integer_array_with_repeats(self, data, idx, box_in_series):
         tm.assert_equal(arr, expected)
 
     @pytest.mark.parametrize(
-        "idx, box_in_series",
+        "idx",
         [
-            ([0, 1, 2, pd.NA], False),
-            pytest.param(
-                [0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
-            ),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            # TODO: change False to True?
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),  # noqa: PT014
+            [0, 1, 2, pd.NA],
+            pd.array([0, 1, 2, pd.NA], dtype="Int64"),
         ],
-        ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
+        ids=["list", "integer-array"],
     )
+    @pytest.mark.parametrize("box_in_series", [True, False])
     def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
         arr = data.copy()
 
-        # TODO(xfail) this raises KeyError about labels not found (it tries label-based)
-        # for list of labels with Series
+        msg = "Cannot index with an integer indexer containing NA values"
+        err = ValueError
+
         if box_in_series:
+            # The integer labels are not present in the (string) index, so
+            #  we get KeyErrors
             arr = pd.Series(data, index=[chr(100 + i) for i in range(len(data))])
+            msg = "0"
+            err = KeyError
 
-        msg = "Cannot index with an integer indexer containing NA values"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(err, match=msg):
             arr[idx] = arr[0]
 
     @pytest.mark.parametrize("as_callable", [True, False])

pandas/tests/extension/json/test_json.py

@@ -356,18 +356,25 @@ def test_setitem_integer_array(self, data, idx, box_in_series, request):
             request.applymarker(mark)
         super().test_setitem_integer_array(data, idx, box_in_series)
 
-    @pytest.mark.xfail(reason="list indices must be integers or slices, not NAType")
     @pytest.mark.parametrize(
-        "idx, box_in_series",
+        "idx",
+        [
+            [0, 1, 2, pd.NA],
+            pd.array([0, 1, 2, pd.NA], dtype="Int64"),
+        ],
+        ids=["list", "integer-array"],
+    )
+    @pytest.mark.parametrize(
+        "box_in_series",
         [
-            ([0, 1, 2, pd.NA], False),
+            True,
             pytest.param(
-                [0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
+                False,
+                marks=pytest.mark.xfail(
+                    reason="list indices must be integers or slices, not NAType"
+                ),
             ),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), True),
         ],
-        ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
     )
     def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
         super().test_setitem_integer_with_missing_raises(data, idx, box_in_series)

pandas/tests/frame/methods/test_rename.py

@@ -8,6 +8,7 @@
     DataFrame,
     Index,
     MultiIndex,
+    Series,
     merge,
 )
 import pandas._testing as tm
@@ -409,3 +410,33 @@ def test_rename_boolean_index(self):
             index=["foo", "bar", "bah"],
         )
         tm.assert_frame_equal(res, exp)
+
+    def test_rename_non_unique_index_series(self):
+        # GH#58621
+        df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
+        orig = df.copy(deep=True)
+
+        rename_series = Series(["X", "Y", "Z", "W"], index=["A", "B", "B", "C"])
+
+        msg = "Cannot rename with a Series with non-unique index"
+        with pytest.raises(ValueError, match=msg):
+            df.rename(rename_series)
+        with pytest.raises(ValueError, match=msg):
+            df.rename(columns=rename_series)
+        with pytest.raises(ValueError, match=msg):
+            df.rename(columns=rename_series, inplace=True)
+
+        # check we didn't corrupt the original
+        tm.assert_frame_equal(df, orig)
+
+        # Check the Series method while we're here
+        ser = df.iloc[0]
+        with pytest.raises(ValueError, match=msg):
+            ser.rename(rename_series)
+        with pytest.raises(ValueError, match=msg):
+            ser.rename(index=rename_series)
+        with pytest.raises(ValueError, match=msg):
+            ser.rename(index=rename_series, inplace=True)
+
+        # check we didn't corrupt the original
+        tm.assert_series_equal(ser, orig.iloc[0])

pandas/tests/indexes/interval/test_interval.py

@@ -882,6 +882,14 @@ def test_is_all_dates(self):
         assert not year_2017_index._is_all_dates
 
 
+def test_from_arrays_mismatched_signedness_raises():
+    # GH 55715
+    left = np.array([0, 1, 2], dtype="int64")
+    right = np.array([1, 2, 3], dtype="uint64")
+    with pytest.raises(TypeError, match="matching signedness"):
+        IntervalIndex.from_arrays(left, right)
+
+
 def test_dir():
     # GH#27571 dir(interval_index) should not raise
     index = IntervalIndex.from_arrays([0, 1], [1, 2])