BUG: 2D ndarray of dtype 'object' is always copied upon construction (pandas-dev#39263)

Author: irgolic

doc/source/whatsnew/v1.3.0.rst

@@ -234,6 +234,7 @@ Datetimelike
 - Bug in :meth:`Series.where` incorrectly casting ``datetime64`` values to ``int64`` (:issue:`37682`)
 - Bug in :class:`Categorical` incorrectly typecasting ``datetime`` object to ``Timestamp`` (:issue:`38878`)
 - Bug in :func:`date_range` incorrectly creating :class:`DatetimeIndex` containing ``NaT`` instead of raising ``OutOfBoundsDatetime`` in corner cases (:issue:`24124`)
+- Bug in :func:`DataFrame` constructor unnecessarily copying 2D object arrays (:issue:`39263`)
 
 Timedelta
 ^^^^^^^^^

pandas/core/internals/construction.py

@@ -27,7 +27,6 @@
     dict_compat,
     maybe_cast_to_datetime,
     maybe_convert_platform,
-    maybe_infer_to_datetimelike,
     maybe_upcast,
 )
 from pandas.core.dtypes.common import (
@@ -37,7 +36,6 @@
     is_integer_dtype,
     is_list_like,
     is_named_tuple,
-    is_object_dtype,
 )
 from pandas.core.dtypes.generic import (
     ABCDataFrame,
@@ -58,8 +56,8 @@
     union_indexes,
 )
 from pandas.core.internals.managers import (
+    create_block_manager_from_array,
     create_block_manager_from_arrays,
-    create_block_manager_from_blocks,
 )
 
 if TYPE_CHECKING:
@@ -232,34 +230,7 @@ def init_ndarray(values, index, columns, dtype: Optional[DtypeObj], copy: bool):
     )
     values = values.T
 
-    # if we don't have a dtype specified, then try to convert objects
-    # on the entire block; this is to convert if we have datetimelike's
-    # embedded in an object type
-    if dtype is None and is_object_dtype(values.dtype):
-
-        if values.ndim == 2 and values.shape[0] != 1:
-            # transpose and separate blocks
-
-            dvals_list = [maybe_infer_to_datetimelike(row) for row in values]
-            for n in range(len(dvals_list)):
-                if isinstance(dvals_list[n], np.ndarray):
-                    dvals_list[n] = dvals_list[n].reshape(1, -1)
-
-            from pandas.core.internals.blocks import make_block
-
-            # TODO: What about re-joining object columns?
-            block_values = [
-                make_block(dvals_list[n], placement=[n], ndim=2)
-                for n in range(len(dvals_list))
-            ]
-
-        else:
-            datelike_vals = maybe_infer_to_datetimelike(values)
-            block_values = [datelike_vals]
-    else:
-        block_values = [values]
-
-    return create_block_manager_from_blocks(block_values, [columns, index])
+    return create_block_manager_from_array(values, [columns, index], dtype)
 
 
 def init_dict(data: Dict, index, columns, dtype: Optional[DtypeObj] = None):

pandas/core/internals/managers.py

@@ -27,13 +27,15 @@
 from pandas.core.dtypes.cast import (
     find_common_type,
     infer_dtype_from_scalar,
+    maybe_infer_to_datetimelike,
     maybe_promote,
 )
 from pandas.core.dtypes.common import (
     DT64NS_DTYPE,
     is_dtype_equal,
     is_extension_array_dtype,
     is_list_like,
+    is_object_dtype,
 )
 from pandas.core.dtypes.concat import concat_compat
 from pandas.core.dtypes.dtypes import ExtensionDtype
@@ -1678,6 +1680,41 @@ def create_block_manager_from_arrays(
         raise construction_error(len(arrays), arrays[0].shape, axes, e)
 
 
+def create_block_manager_from_array(
+    array, axes: List[Index], dtype: Optional[Dtype] = None
+) -> BlockManager:
+    assert isinstance(axes, list)
+    assert all(isinstance(x, Index) for x in axes)
+
+    # ensure we dont have any PandasArrays when we call get_block_type
+    # Note: just calling extract_array breaks tests that patch PandasArray._typ.
+    array = array if not isinstance(array, ABCPandasArray) else array.to_numpy()
+
+    try:
+        # if we don't have a dtype specified, then try to convert objects
+        # on the entire block; this is to convert if we have datetimelike's
+        # embedded in an object type
+        if dtype is None and is_object_dtype(array.dtype):
+            maybe_datetime = [
+                maybe_infer_to_datetimelike(instance) for instance in array
+            ]
+            # don't convert (and copy) the objects if no type conversion occurs
+            if any(
+                not is_dtype_equal(instance.dtype, array.dtype)
+                for instance in maybe_datetime
+            ):
+                blocks = _form_blocks(maybe_datetime, axes[0], axes)
+            else:
+                blocks = [make_block(array, slice(0, len(axes[0])))]
+        else:
+            blocks = [make_block(array, slice(0, len(axes[0])), dtype=dtype)]
+        mgr = BlockManager(blocks, axes)
+        mgr._consolidate_inplace()
+        return mgr
+    except ValueError as e:
+        raise construction_error(array.shape[0], array.shape[1:], axes, e)
+
+
 def construction_error(tot_items, block_shape, axes, e=None):
     """ raise a helpful message about our construction """
     passed = tuple(map(int, [tot_items] + list(block_shape)))
@@ -1705,6 +1742,13 @@ def construction_error(tot_items, block_shape, axes, e=None):
 def _form_blocks(arrays, names: Index, axes) -> List[Block]:
     # put "leftover" items in float bucket, where else?
     # generalize?
+
+    if len(arrays) != len(names):
+        raise ValueError(
+            f"Number of arrays ({len(arrays)}) "
+            f"does not match index length ({len(names)})"
+        )
+
     items_dict: DefaultDict[str, List] = defaultdict(list)
     extra_locs = []
 

pandas/tests/frame/test_constructors.py

@@ -2267,6 +2267,14 @@ def test_nested_dict_construction(self):
         )
         tm.assert_frame_equal(result, expected)
 
+    def test_object_array_does_not_copy(self):
+        a = np.array(["a", "b"], dtype="object")
+        b = np.array([["a", "b"], ["c", "d"]], dtype="object")
+        df = DataFrame(a)
+        assert np.shares_memory(df.values, a)
+        df2 = DataFrame(b)
+        assert np.shares_memory(df2.values, b)
+
     def test_from_tzaware_object_array(self):
         # GH#26825 2D object array of tzaware timestamps should not raise
         dti = date_range("2016-04-05 04:30", periods=3, tz="UTC")