BUG: fix loc setitem with list of tuples on object-dtype column (#65264)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: jbrockmendel

doc/source/whatsnew/v3.1.0.rst

@@ -266,6 +266,7 @@ Indexing
 - Bug in :meth:`DataFrame.at` raising ``TypeError`` when accessing a :class:`MultiIndex` with a partial date string on a :class:`DatetimeIndex` level (:issue:`43395`)
 - Bug in :meth:`DataFrame.duplicated` returning an empty :class:`Series` without the DataFrame's index when the DataFrame had no columns (:issue:`61191`)
 - Bug in :meth:`DataFrame.iloc` setitem raising ``AttributeError`` when assigning a :class:`Series` or :class:`Index` with a nullable EA dtype (e.g. ``Int64``, ``Float64``, ``boolean``) into a column with a NumPy dtype (:issue:`47776`)
+- Bug in :meth:`DataFrame.loc` raising ``ValueError`` when assigning a list of tuples to an object-dtype column with a boolean mask on a mixed-dtype DataFrame (:issue:`37629`)
 - Bug in :meth:`DataFrame.loc` with a :class:`MultiIndex` returning wrong results instead of raising ``KeyError`` when passing string keys for numeric index levels (:issue:`60104`)
 - Bug in :meth:`DataFrame.mask` with ``inplace=True`` where incorrect values were produced when ``other`` was a :class:`Series` with :class:`ExtensionArray` values (:issue:`64635`)
 - Bug in :meth:`DataFrame.where` and :meth:`DataFrame.mask` raising ``TypeError`` when ``cond`` is a :class:`Series` and ``axis=1`` (:issue:`58190`)

pandas/core/indexing.py

@@ -2579,7 +2579,11 @@ def _setitem_with_indexer_split_path(self, indexer, value, name: str):
             if isinstance(value, ABCDataFrame):
                 self._setitem_with_indexer_frame_value(indexer, value, name)
 
-            elif _is_2d_value(value):
+            elif _is_2d_value(value) and not (
+                isinstance(value, list)
+                and isinstance(value[0], tuple)
+                and len(value[0]) != len(ilocs)
+            ):
                 self._setitem_with_indexer_2d_value(indexer, value)
 
             elif len(ilocs) == 1 and lplane_indexer == len(value) and not is_scalar(pi):

pandas/core/internals/blocks.py

@@ -41,6 +41,7 @@
 from pandas.core.dtypes.cast import (
     LossySetitemError,
     can_hold_element,
+    construct_1d_object_array_from_listlike,
     convert_dtypes,
     find_result_type,
     np_can_hold_element,
@@ -1133,6 +1134,15 @@ def setitem(self, indexer, value) -> Block:
                     num_set = len(values[indexer])
                 casted = setitem_datetimelike_compat(values, num_set, casted)
 
+                if (
+                    isinstance(casted, list)
+                    and len(casted) > 0
+                    and isinstance(casted[0], (tuple, list, np.ndarray))
+                ):
+                    # Prevent numpy from unpacking nested containers
+                    # (e.g. tuples) during boolean-indexed assignment. GH#37629
+                    casted = construct_1d_object_array_from_listlike(casted)
+
             self = self._maybe_copy(inplace=True)
             values = cast("np.ndarray", self.values.T)
             if isinstance(casted, np.ndarray) and casted.ndim == 1 and len(casted) == 1:

pandas/tests/indexing/test_indexing.py

@@ -1142,6 +1142,27 @@ def test_scalar_setitem_series_with_nested_value_length1(value, indexer_sli):
         assert ser.loc[0] == value
 
 
+def test_loc_setitem_list_of_tuples_on_object_column():
+    # GH#37629 - assigning list of tuples to object-dtype column
+    # with a boolean mask on a mixed-dtype DataFrame
+    df = DataFrame({"a": [1, 1, 2, 1], "b": [(1, 1, 0)] * 4})
+
+    # list of tuples matching selected row count
+    df.loc[df["a"] == 1, "b"] = [(0, 0, 1), (0, 0, 1), (0, 0, 1)]
+    expected = DataFrame(
+        {"a": [1, 1, 2, 1], "b": [(0, 0, 1), (0, 0, 1), (1, 1, 0), (0, 0, 1)]}
+    )
+    tm.assert_frame_equal(df, expected)
+    # verify tuples are preserved as tuples
+    assert isinstance(df["b"].iloc[0], tuple)
+
+    # doubly-nested list: [[(tuple)]] treated as 2D with 1 row x 1 col,
+    # tuple value broadcast to all matching rows
+    df2 = DataFrame({"a": [1, 1, 2, 1], "b": [(1, 1, 0)] * 4})
+    df2.loc[df2["a"] == 1, "b"] = [[(0, 0, 1)]]
+    tm.assert_frame_equal(df2, expected)
+
+
 def test_object_dtype_series_set_series_element():
     # GH 48933
     s1 = Series(dtype="O", index=["a", "b"])