API / CoW: Copy NumPy arrays by default in DataFrame constructor

pandas/conftest.py

@@ -522,7 +522,10 @@ def multiindex_dataframe_random_data(
     """DataFrame with 2 level MultiIndex with random data"""
     index = lexsorted_two_level_string_multiindex
     return DataFrame(
-        np.random.randn(10, 3), index=index, columns=Index(["A", "B", "C"], name="exp")
+        np.random.randn(10, 3),
+        index=index,
+        columns=Index(["A", "B", "C"], name="exp"),
+        copy=False,
     )
 
 

pandas/core/construction.py

@@ -18,6 +18,8 @@
 import numpy as np
 from numpy import ma
 
+from pandas._config import using_copy_on_write
+
 from pandas._libs import lib
 from pandas._libs.tslibs.period import Period
 from pandas._typing import (
@@ -762,6 +764,9 @@ def _try_cast(
 
         subarr = maybe_cast_to_integer_array(arr, dtype)
     else:
-        subarr = np.array(arr, dtype=dtype, copy=copy)
+        if using_copy_on_write():
+            subarr = np.array(arr, dtype=dtype, copy=copy, order="F")
+        else:
+            subarr = np.array(arr, dtype=dtype, copy=copy)
 
     return subarr

pandas/core/dtypes/cast.py

@@ -19,6 +19,8 @@
 
 import numpy as np
 
+from pandas._config import using_copy_on_write
+
 from pandas._libs import lib
 from pandas._libs.missing import (
     NA,
@@ -1613,11 +1615,17 @@ def maybe_cast_to_integer_array(arr: list | np.ndarray, dtype: np.dtype) -> np.n
                     "NumPy will stop allowing conversion of out-of-bound Python int",
                     DeprecationWarning,
                 )
-                casted = np.array(arr, dtype=dtype, copy=False)
+                if using_copy_on_write():
+                    casted = np.array(arr, dtype=dtype, copy=False, order="F")
+                else:
+                    casted = np.array(arr, dtype=dtype, copy=False)
         else:
             with warnings.catch_warnings():
                 warnings.filterwarnings("ignore", category=RuntimeWarning)
-                casted = arr.astype(dtype, copy=False)
+                if using_copy_on_write():
+                    casted = arr.astype(dtype, copy=False, order="F")
+                else:
+                    casted = arr.astype(dtype, copy=False)
     except OverflowError as err:
         raise OverflowError(
             "The elements provided in the data cannot all be "

pandas/core/frame.py

@@ -685,6 +685,8 @@ def __init__(
                 # INFO(ArrayManager) by default copy the 2D input array to get
                 # contiguous 1D arrays
                 copy = True
+            elif using_copy_on_write() and isinstance(data, np.ndarray):
+                copy = True
             else:
                 copy = False
 

pandas/core/internals/construction.py

@@ -14,6 +14,8 @@
 import numpy as np
 from numpy import ma
 
+from pandas._config import using_copy_on_write
+
 from pandas._libs import lib
 from pandas._typing import (
     ArrayLike,
@@ -289,6 +291,15 @@ def ndarray_to_mgr(
         if values.ndim == 1:
             values = values.reshape(-1, 1)
 
+    elif (
+        using_copy_on_write()
+        and isinstance(values, np.ndarray)
+        and (dtype is None or is_dtype_equal(values.dtype, dtype))
+        and copy_on_sanitize
+    ):
+        values = np.array(values, order="F", copy=copy_on_sanitize)
+        values = _ensure_2d(values)
+
     elif isinstance(values, (np.ndarray, ExtensionArray, ABCSeries, Index)):
         # drop subclass info
         values = np.array(values, copy=copy_on_sanitize)

pandas/tests/frame/methods/test_fillna.py

@@ -57,7 +57,10 @@ def test_fillna_on_column_view(self, using_copy_on_write):
 
         # i.e. we didn't create a new 49-column block
         assert len(df._mgr.arrays) == 1
-        assert np.shares_memory(df.values, arr)
+        if using_copy_on_write:
+            assert not np.shares_memory(df.values, arr)
+        else:
+            assert np.shares_memory(df.values, arr)
 
     def test_fillna_datetime(self, datetime_frame):
         tf = datetime_frame

pandas/tests/frame/methods/test_to_numpy.py

@@ -23,11 +23,15 @@ def test_to_numpy_dtype(self):
         tm.assert_numpy_array_equal(result, expected)
 
     @td.skip_array_manager_invalid_test
-    def test_to_numpy_copy(self):
+    def test_to_numpy_copy(self, using_copy_on_write):
         arr = np.random.randn(4, 3)
         df = DataFrame(arr)
-        assert df.values.base is arr
-        assert df.to_numpy(copy=False).base is arr
+        if using_copy_on_write:
+            assert df.values.base is not arr
+            assert df.to_numpy(copy=False).base is not arr
+        else:
+            assert df.values.base is arr
+            assert df.to_numpy(copy=False).base is arr
         assert df.to_numpy(copy=True).base is not arr
 
     def test_to_numpy_mixed_dtype_to_str(self):

pandas/tests/frame/test_constructors.py

@@ -313,11 +313,14 @@ def test_1d_object_array_does_not_copy(self):
         assert np.shares_memory(df.values, arr)
 
     @td.skip_array_manager_invalid_test
-    def test_2d_object_array_does_not_copy(self):
+    def test_2d_object_array_does_not_copy(self, using_copy_on_write):
         # https://github.com/pandas-dev/pandas/issues/39272
         arr = np.array([["a", "b"], ["c", "d"]], dtype="object")
         df = DataFrame(arr)
-        assert np.shares_memory(df.values, arr)
+        if using_copy_on_write:
+            assert not np.shares_memory(df.values, arr)
+        else:
+            assert np.shares_memory(df.values, arr)
 
     def test_constructor_dtype_list_data(self):
         df = DataFrame([[1, "2"], [None, "a"]], dtype=object)
@@ -2107,13 +2110,18 @@ def test_constructor_frame_shallow_copy(self, float_frame):
         cop.index = np.arange(len(cop))
         tm.assert_frame_equal(float_frame, orig)
 
-    def test_constructor_ndarray_copy(self, float_frame, using_array_manager):
+    def test_constructor_ndarray_copy(
+        self, float_frame, using_array_manager, using_copy_on_write
+    ):
         if not using_array_manager:
             arr = float_frame.values.copy()
             df = DataFrame(arr)
 
             arr[5] = 5
-            assert (df.values[5] == 5).all()
+            if using_copy_on_write:
+                assert not (df.values[5] == 5).all()
+            else:
+                assert (df.values[5] == 5).all()
 
             df = DataFrame(arr, copy=True)
             arr[6] = 6

pandas/tests/indexing/multiindex/test_setitem.py

@@ -482,12 +482,17 @@ def test_setitem_new_column_all_na(self):
 
 @td.skip_array_manager_invalid_test  # df["foo"] select multiple columns -> .values
 # is not a view
-def test_frame_setitem_view_direct(multiindex_dataframe_random_data):
+def test_frame_setitem_view_direct(
+    multiindex_dataframe_random_data, using_copy_on_write
+):
     # this works because we are modifying the underlying array
     # really a no-no
     df = multiindex_dataframe_random_data.T
     df["foo"].values[:] = 0
-    assert (df["foo"].values == 0).all()
+    if using_copy_on_write:
+        assert not (df["foo"].values == 0).all()
+    else:
+        assert (df["foo"].values == 0).all()
 
 
 def test_frame_setitem_copy_raises(