CoW: Remove Copy-on-Write fixtures from more tests (#57367)

Author: phofl

pandas/tests/apply/test_frame_apply.py

@@ -1487,7 +1487,7 @@ def test_apply_dtype(col):
     tm.assert_series_equal(result, expected)
 
 
-def test_apply_mutating(using_copy_on_write):
+def test_apply_mutating():
     # GH#35462 case where applied func pins a new BlockManager to a row
     df = DataFrame({"a": range(100), "b": range(100, 200)})
     df_orig = df.copy()
@@ -1504,11 +1504,7 @@ def func(row):
     result = df.apply(func, axis=1)
 
     tm.assert_frame_equal(result, expected)
-    if using_copy_on_write:
-        # INFO(CoW) With copy on write, mutating a viewing row doesn't mutate the parent
-        tm.assert_frame_equal(df, df_orig)
-    else:
-        tm.assert_frame_equal(df, result)
+    tm.assert_frame_equal(df, df_orig)
 
 
 def test_apply_empty_list_reduce():

pandas/tests/computation/test_eval.py

@@ -1964,7 +1964,7 @@ def test_eval_no_support_column_name(request, column):
     tm.assert_frame_equal(result, expected)
 
 
-def test_set_inplace(using_copy_on_write):
+def test_set_inplace():
     # https://github.com/pandas-dev/pandas/issues/47449
     # Ensure we don't only update the DataFrame inplace, but also the actual
     # column values, such that references to this column also get updated
@@ -1974,13 +1974,9 @@ def test_set_inplace(using_copy_on_write):
     df.eval("A = B + C", inplace=True)
     expected = DataFrame({"A": [11, 13, 15], "B": [4, 5, 6], "C": [7, 8, 9]})
     tm.assert_frame_equal(df, expected)
-    if not using_copy_on_write:
-        tm.assert_series_equal(ser, expected["A"])
-        tm.assert_series_equal(result_view["A"], expected["A"])
-    else:
-        expected = Series([1, 2, 3], name="A")
-        tm.assert_series_equal(ser, expected)
-        tm.assert_series_equal(result_view["A"], expected)
+    expected = Series([1, 2, 3], name="A")
+    tm.assert_series_equal(ser, expected)
+    tm.assert_series_equal(result_view["A"], expected)
 
 
 class TestValidate:

pandas/tests/extension/base/setitem.py

@@ -398,10 +398,6 @@ def test_setitem_series(self, data, full_indexer):
     def test_setitem_frame_2d_values(self, data):
         # GH#44514
         df = pd.DataFrame({"A": data})
-        using_copy_on_write = pd.options.mode.copy_on_write
-
-        blk_data = df._mgr.arrays[0]
-
         orig = df.copy()
 
         df.iloc[:] = df.copy()
@@ -412,9 +408,6 @@ def test_setitem_frame_2d_values(self, data):
 
         df.iloc[:] = df.values
         tm.assert_frame_equal(df, orig)
-        if not using_copy_on_write:
-            # GH#33457 Check that this setting occurred in-place
-            assert df._mgr.arrays[0] is blk_data
 
         df.iloc[:-1] = df.values[:-1]
         tm.assert_frame_equal(df, orig)

pandas/tests/extension/conftest.py

@@ -212,11 +212,3 @@ def invalid_scalar(data):
     If the array can hold any item (i.e. object dtype), then use pytest.skip.
     """
     return object.__new__(object)
-
-
-@pytest.fixture
-def using_copy_on_write() -> bool:
-    """
-    Fixture to check if Copy-on-Write is enabled.
-    """
-    return True

pandas/tests/extension/decimal/test_decimal.py

@@ -245,18 +245,6 @@ def test_fillna_series_method(self, data_missing, fillna_method):
         ):
             super().test_fillna_series_method(data_missing, fillna_method)
 
-    def test_fillna_copy_frame(self, data_missing, using_copy_on_write):
-        warn = DeprecationWarning if not using_copy_on_write else None
-        msg = "ExtensionArray.fillna added a 'copy' keyword"
-        with tm.assert_produces_warning(warn, match=msg, check_stacklevel=False):
-            super().test_fillna_copy_frame(data_missing)
-
-    def test_fillna_copy_series(self, data_missing, using_copy_on_write):
-        warn = DeprecationWarning if not using_copy_on_write else None
-        msg = "ExtensionArray.fillna added a 'copy' keyword"
-        with tm.assert_produces_warning(warn, match=msg, check_stacklevel=False):
-            super().test_fillna_copy_series(data_missing)
-
     @pytest.mark.parametrize("dropna", [True, False])
     def test_value_counts(self, all_data, dropna):
         all_data = all_data[:10]
@@ -554,12 +542,11 @@ def test_to_numpy_keyword():
     tm.assert_numpy_array_equal(result, expected)
 
 
-def test_array_copy_on_write(using_copy_on_write):
+def test_array_copy_on_write():
     df = pd.DataFrame({"a": [decimal.Decimal(2), decimal.Decimal(3)]}, dtype="object")
     df2 = df.astype(DecimalDtype())
     df.iloc[0, 0] = 0
-    if using_copy_on_write:
-        expected = pd.DataFrame(
-            {"a": [decimal.Decimal(2), decimal.Decimal(3)]}, dtype=DecimalDtype()
-        )
-        tm.assert_equal(df2.values, expected.values)
+    expected = pd.DataFrame(
+        {"a": [decimal.Decimal(2), decimal.Decimal(3)]}, dtype=DecimalDtype()
+    )
+    tm.assert_equal(df2.values, expected.values)

pandas/tests/extension/json/test_json.py

@@ -217,12 +217,8 @@ def test_equals(self, data, na_value, as_series):
     def test_fillna_copy_frame(self, data_missing):
         super().test_fillna_copy_frame(data_missing)
 
-    def test_equals_same_data_different_object(
-        self, data, using_copy_on_write, request
-    ):
-        if using_copy_on_write:
-            mark = pytest.mark.xfail(reason="Fails with CoW")
-            request.applymarker(mark)
+    @pytest.mark.xfail(reason="Fails with CoW")
+    def test_equals_same_data_different_object(self, data, request):
         super().test_equals_same_data_different_object(data)
 
     @pytest.mark.xfail(reason="failing on np.array(self, dtype=str)")

pandas/tests/extension/test_sparse.py

@@ -277,32 +277,25 @@ def test_fillna_frame(self, data_missing):
 
     _combine_le_expected_dtype = "Sparse[bool]"
 
-    def test_fillna_copy_frame(self, data_missing, using_copy_on_write):
+    def test_fillna_copy_frame(self, data_missing):
         arr = data_missing.take([1, 1])
         df = pd.DataFrame({"A": arr}, copy=False)
 
         filled_val = df.iloc[0, 0]
         result = df.fillna(filled_val)
 
         if hasattr(df._mgr, "blocks"):
-            if using_copy_on_write:
-                assert df.values.base is result.values.base
-            else:
-                assert df.values.base is not result.values.base
+            assert df.values.base is result.values.base
         assert df.A._values.to_dense() is arr.to_dense()
 
-    def test_fillna_copy_series(self, data_missing, using_copy_on_write):
+    def test_fillna_copy_series(self, data_missing):
         arr = data_missing.take([1, 1])
         ser = pd.Series(arr, copy=False)
 
         filled_val = ser[0]
         result = ser.fillna(filled_val)
 
-        if using_copy_on_write:
-            assert ser._values is result._values
-
-        else:
-            assert ser._values is not result._values
+        assert ser._values is result._values
         assert ser._values.to_dense() is arr.to_dense()
 
     @pytest.mark.xfail(reason="Not Applicable")

pandas/tests/groupby/test_raises.py

@@ -363,7 +363,7 @@ def test_groupby_raises_timedelta(func):
 
 @pytest.mark.parametrize("how", ["method", "agg", "transform"])
 def test_groupby_raises_category(
-    how, by, groupby_series, groupby_func, using_copy_on_write, df_with_cat_col
+    how, by, groupby_series, groupby_func, df_with_cat_col
 ):
     # GH#50749
     df = df_with_cat_col
@@ -416,13 +416,7 @@ def test_groupby_raises_category(
             r"unsupported operand type\(s\) for -: 'Categorical' and 'Categorical'",
         ),
         "ffill": (None, ""),
-        "fillna": (
-            TypeError,
-            r"Cannot setitem on a Categorical with a new category \(0\), "
-            "set the categories first",
-        )
-        if not using_copy_on_write
-        else (None, ""),  # no-op with CoW
+        "fillna": (None, ""),  # no-op with CoW
         "first": (None, ""),
         "idxmax": (None, ""),
         "idxmin": (None, ""),
@@ -555,7 +549,6 @@ def test_groupby_raises_category_on_category(
     groupby_series,
     groupby_func,
     observed,
-    using_copy_on_write,
     df_with_cat_col,
 ):
     # GH#50749
@@ -616,13 +609,7 @@ def test_groupby_raises_category_on_category(
         ),
         "diff": (TypeError, "unsupported operand type"),
         "ffill": (None, ""),
-        "fillna": (
-            TypeError,
-            r"Cannot setitem on a Categorical with a new category \(0\), "
-            "set the categories first",
-        )
-        if not using_copy_on_write
-        else (None, ""),  # no-op with CoW
+        "fillna": (None, ""),  # no-op with CoW
         "first": (None, ""),
         "idxmax": (ValueError, "empty group due to unobserved categories")
         if empty_groups

pandas/tests/reshape/concat/test_concat.py

@@ -43,24 +43,15 @@ def test_append_concat(self):
         assert isinstance(result.index, PeriodIndex)
         assert result.index[0] == s1.index[0]
 
-    def test_concat_copy(self, using_copy_on_write):
+    def test_concat_copy(self):
         df = DataFrame(np.random.default_rng(2).standard_normal((4, 3)))
         df2 = DataFrame(np.random.default_rng(2).integers(0, 10, size=4).reshape(4, 1))
         df3 = DataFrame({5: "foo"}, index=range(4))
 
         # These are actual copies.
         result = concat([df, df2, df3], axis=1, copy=True)
-
-        if not using_copy_on_write:
-            for arr in result._mgr.arrays:
-                assert not any(
-                    np.shares_memory(arr, y)
-                    for x in [df, df2, df3]
-                    for y in x._mgr.arrays
-                )
-        else:
-            for arr in result._mgr.arrays:
-                assert arr.base is not None
+        for arr in result._mgr.arrays:
+            assert arr.base is not None
 
         # These are the same.
         result = concat([df, df2, df3], axis=1, copy=False)
@@ -78,15 +69,11 @@ def test_concat_copy(self, using_copy_on_write):
         result = concat([df, df2, df3, df4], axis=1, copy=False)
         for arr in result._mgr.arrays:
             if arr.dtype.kind == "f":
-                if using_copy_on_write:
-                    # this is a view on some array in either df or df4
-                    assert any(
-                        np.shares_memory(arr, other)
-                        for other in df._mgr.arrays + df4._mgr.arrays
-                    )
-                else:
-                    # the block was consolidated, so we got a copy anyway
-                    assert arr.base is None
+                # this is a view on some array in either df or df4
+                assert any(
+                    np.shares_memory(arr, other)
+                    for other in df._mgr.arrays + df4._mgr.arrays
+                )
             elif arr.dtype.kind in ["i", "u"]:
                 assert arr.base is df2._mgr.arrays[0].base
             elif arr.dtype == object:

pandas/tests/reshape/concat/test_dataframe.py

@@ -192,19 +192,6 @@ def test_concat_duplicates_in_index_with_keys(self):
         tm.assert_frame_equal(result, expected)
         tm.assert_index_equal(result.index.levels[1], Index([1, 3], name="date"))
 
-    @pytest.mark.parametrize("ignore_index", [True, False])
-    @pytest.mark.parametrize("order", ["C", "F"])
-    def test_concat_copies(self, axis, order, ignore_index, using_copy_on_write):
-        # based on asv ConcatDataFrames
-        df = DataFrame(np.zeros((10, 5), dtype=np.float32, order=order))
-
-        res = concat([df] * 5, axis=axis, ignore_index=ignore_index, copy=True)
-
-        if not using_copy_on_write:
-            for arr in res._iter_column_arrays():
-                for arr2 in df._iter_column_arrays():
-                    assert not np.shares_memory(arr, arr2)
-
     def test_outer_sort_columns(self):
         # GH#47127
         df1 = DataFrame({"A": [0], "B": [1], 0: 1})

pandas/tests/reshape/concat/test_index.py

@@ -100,23 +100,20 @@ def test_concat_rename_index(self):
         tm.assert_frame_equal(result, exp)
         assert result.index.names == exp.index.names
 
-    def test_concat_copy_index_series(self, axis, using_copy_on_write):
+    def test_concat_copy_index_series(self, axis):
         # GH 29879
         ser = Series([1, 2])
         comb = concat([ser, ser], axis=axis, copy=True)
-        if not using_copy_on_write or axis in [0, "index"]:
+        if axis in [0, "index"]:
             assert comb.index is not ser.index
         else:
             assert comb.index is ser.index
 
-    def test_concat_copy_index_frame(self, axis, using_copy_on_write):
+    def test_concat_copy_index_frame(self, axis):
         # GH 29879
         df = DataFrame([[1, 2], [3, 4]], columns=["a", "b"])
         comb = concat([df, df], axis=axis, copy=True)
-        if not using_copy_on_write:
-            assert not comb.index.is_(df.index)
-            assert not comb.columns.is_(df.columns)
-        elif axis in [0, "index"]:
+        if axis in [0, "index"]:
             assert not comb.index.is_(df.index)
             assert comb.columns.is_(df.columns)
         elif axis in [1, "columns"]: