wip

Author: MarcoGorelli

doc/source/user_guide/categorical.rst

@@ -793,7 +793,7 @@ Assigning a ``Categorical`` to parts of a column of other types will use the val
     :okwarning:
 
     df = pd.DataFrame({"a": [1, 1, 1, 1, 1], "b": ["a", "a", "a", "a", "a"]})
-    df.loc[1:2, "a"] = pd.Categorical(["b", "b"], categories=["a", "b"])
+    df.loc[1:2, "a"] = pd.Categorical([2, 2], categories=[2, 3])
     df.loc[2:3, "b"] = pd.Categorical(["b", "b"], categories=["a", "b"])
     df
     df.dtypes

pandas/core/indexing.py

@@ -25,7 +25,6 @@
 )
 from pandas.errors.cow import _chained_assignment_msg
 from pandas.util._decorators import doc
-from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.cast import (
     can_hold_element,
@@ -2124,7 +2123,7 @@ def _setitem_single_column(self, loc: int, value, plane_indexer) -> None:
                 self.obj._mgr.column_setitem(
                     loc, plane_indexer, value, inplace_only=True
                 )
-            except (ValueError, TypeError, LossySetitemError):
+            except (ValueError, TypeError, LossySetitemError) as exc:
                 # If we're setting an entire column and we can't do it inplace,
                 #  then we can use value's dtype (or inferred dtype)
                 #  instead of object
@@ -2140,14 +2139,9 @@ def _setitem_single_column(self, loc: int, value, plane_indexer) -> None:
                     # - Exclude `object`, as then no upcasting happens.
                     # - Exclude empty initial object with enlargement,
                     #   as then there's nothing to be inconsistent with.
-                    warnings.warn(
-                        f"Setting an item of incompatible dtype is deprecated "
-                        "and will raise in a future error of pandas. "
-                        f"Value '{value}' has dtype incompatible with {dtype}, "
-                        "please explicitly cast to a compatible dtype first.",
-                        FutureWarning,
-                        stacklevel=find_stack_level(),
-                    )
+                    raise TypeError(
+                        f"Invalid value '{value}' for dtype '{dtype}'"
+                    ) from exc
                 self.obj.isetitem(loc, value)
         else:
             # set value into the column (first attempting to operate inplace, then

pandas/core/internals/blocks.py

@@ -467,14 +467,7 @@ def coerce_to_target_dtype(self, other, warn_on_upcast: bool = False) -> Block:
             warn_on_upcast = False
 
         if warn_on_upcast:
-            warnings.warn(
-                f"Setting an item of incompatible dtype is deprecated "
-                "and will raise an error in a future version of pandas. "
-                f"Value '{other}' has dtype incompatible with {self.values.dtype}, "
-                "please explicitly cast to a compatible dtype first.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
+            raise TypeError(f"Invalid value '{other}' for dtype '{self.values.dtype}'")
         if self.values.dtype == new_dtype:
             raise AssertionError(
                 f"Did not expect new dtype {new_dtype} to equal self.dtype "

pandas/tests/copy_view/test_indexing.py

@@ -725,15 +725,13 @@ def test_column_as_series_set_with_upcast(backend):
         with pytest.raises(TypeError, match="Invalid value"):
             s[0] = "foo"
         expected = Series([1, 2, 3], name="a")
+        tm.assert_series_equal(s, expected)
+        tm.assert_frame_equal(df, df_orig)
+        # ensure cached series on getitem is not the changed series
+        tm.assert_series_equal(df["a"], df_orig["a"])
     else:
-        with tm.assert_produces_warning(FutureWarning, match="incompatible dtype"):
+        with pytest.raises(TypeError, match="Invalid value"):
             s[0] = "foo"
-        expected = Series(["foo", 2, 3], dtype=object, name="a")
-
-    tm.assert_series_equal(s, expected)
-    tm.assert_frame_equal(df, df_orig)
-    # ensure cached series on getitem is not the changed series
-    tm.assert_series_equal(df["a"], df_orig["a"])
 
 
 @pytest.mark.parametrize(
@@ -805,16 +803,14 @@ def test_set_value_copy_only_necessary_column(indexer_func, indexer, val, col):
     view = df[:]
 
     if val == "a":
-        with tm.assert_produces_warning(
-            FutureWarning, match="Setting an item of incompatible dtype is deprecated"
-        ):
+        with pytest.raises(TypeError, match="Invalid value"):
             indexer_func(df)[indexer] = val
+    else:
+        indexer_func(df)[indexer] = val
 
-    indexer_func(df)[indexer] = val
-
-    assert np.shares_memory(get_array(df, "b"), get_array(view, "b"))
-    assert not np.shares_memory(get_array(df, "a"), get_array(view, "a"))
-    tm.assert_frame_equal(view, df_orig)
+        assert np.shares_memory(get_array(df, "b"), get_array(view, "b"))
+        assert not np.shares_memory(get_array(df, "a"), get_array(view, "a"))
+        tm.assert_frame_equal(view, df_orig)
 
 
 def test_series_midx_slice():

pandas/tests/copy_view/test_methods.py

@@ -1105,26 +1105,26 @@ def test_putmask_aligns_rhs_no_reference(dtype):
     assert np.shares_memory(arr_a, get_array(df, "a"))
 
 
-@pytest.mark.parametrize(
-    "val, exp, warn", [(5.5, True, FutureWarning), (5, False, None)]
-)
-def test_putmask_dont_copy_some_blocks(val, exp, warn):
+@pytest.mark.parametrize("val, exp, raises", [(5.5, True, True), (5, False, False)])
+def test_putmask_dont_copy_some_blocks(val, exp, raises: bool):
     df = DataFrame({"a": [1, 2], "b": 1, "c": 1.5})
     view = df[:]
     df_orig = df.copy()
     indexer = DataFrame(
         [[True, False, False], [True, False, False]], columns=list("abc")
     )
-    with tm.assert_produces_warning(warn, match="incompatible dtype"):
+    if raises:
+        with pytest.raises(TypeError, match="Invalid value"):
+            df[indexer] = val
+    else:
         df[indexer] = val
-
-    assert not np.shares_memory(get_array(view, "a"), get_array(df, "a"))
-    # TODO(CoW): Could split blocks to avoid copying the whole block
-    assert np.shares_memory(get_array(view, "b"), get_array(df, "b")) is exp
-    assert np.shares_memory(get_array(view, "c"), get_array(df, "c"))
-    assert df._mgr._has_no_reference(1) is not exp
-    assert not df._mgr._has_no_reference(2)
-    tm.assert_frame_equal(view, df_orig)
+        assert not np.shares_memory(get_array(view, "a"), get_array(df, "a"))
+        # TODO(CoW): Could split blocks to avoid copying the whole block
+        assert np.shares_memory(get_array(view, "b"), get_array(df, "b")) is exp
+        assert np.shares_memory(get_array(view, "c"), get_array(df, "c"))
+        assert df._mgr._has_no_reference(1) is not exp
+        assert not df._mgr._has_no_reference(2)
+        tm.assert_frame_equal(view, df_orig)
 
 
 @pytest.mark.parametrize("dtype", ["int64", "Int64"])

pandas/tests/frame/indexing/test_coercion.py

@@ -49,35 +49,19 @@ def test_loc_setitem_multiindex_columns(self, consolidate):
 def test_37477():
     # fixed by GH#45121
     orig = DataFrame({"A": [1, 2, 3], "B": [3, 4, 5]})
-    expected = DataFrame({"A": [1, 2, 3], "B": [3, 1.2, 5]})
 
     df = orig.copy()
-    with tm.assert_produces_warning(
-        FutureWarning, match="Setting an item of incompatible dtype"
-    ):
+    with pytest.raises(TypeError, match="Invalid value"):
         df.at[1, "B"] = 1.2
-    tm.assert_frame_equal(df, expected)
 
-    df = orig.copy()
-    with tm.assert_produces_warning(
-        FutureWarning, match="Setting an item of incompatible dtype"
-    ):
+    with pytest.raises(TypeError, match="Invalid value"):
         df.loc[1, "B"] = 1.2
-    tm.assert_frame_equal(df, expected)
 
-    df = orig.copy()
-    with tm.assert_produces_warning(
-        FutureWarning, match="Setting an item of incompatible dtype"
-    ):
+    with pytest.raises(TypeError, match="Invalid value"):
         df.iat[1, 1] = 1.2
-    tm.assert_frame_equal(df, expected)
 
-    df = orig.copy()
-    with tm.assert_produces_warning(
-        FutureWarning, match="Setting an item of incompatible dtype"
-    ):
+    with pytest.raises(TypeError, match="Invalid value"):
         df.iloc[1, 1] = 1.2
-    tm.assert_frame_equal(df, expected)
 
 
 def test_6942(indexer_al):
@@ -107,19 +91,11 @@ def test_26395(indexer_al):
     expected = DataFrame({"D": [0, 0, 2]}, index=["A", "B", "C"], dtype=np.int64)
     tm.assert_frame_equal(df, expected)
 
-    with tm.assert_produces_warning(
-        FutureWarning, match="Setting an item of incompatible dtype"
-    ):
+    with pytest.raises(TypeError, match="Invalid value"):
         indexer_al(df)["C", "D"] = 44.5
-    expected = DataFrame({"D": [0, 0, 44.5]}, index=["A", "B", "C"], dtype=np.float64)
-    tm.assert_frame_equal(df, expected)
 
-    with tm.assert_produces_warning(
-        FutureWarning, match="Setting an item of incompatible dtype"
-    ):
+    with pytest.raises(TypeError, match="Invalid value"):
         indexer_al(df)["C", "D"] = "hello"
-    expected = DataFrame({"D": [0, 0, "hello"]}, index=["A", "B", "C"], dtype=object)
-    tm.assert_frame_equal(df, expected)
 
 
 @pytest.mark.xfail(reason="unwanted upcast")

pandas/tests/frame/indexing/test_indexing.py

@@ -25,7 +25,6 @@
     Timestamp,
     date_range,
     isna,
-    notna,
     to_datetime,
 )
 import pandas._testing as tm
@@ -833,13 +832,8 @@ def test_setitem_single_column_mixed_datetime(self):
         tm.assert_series_equal(result, expected)
 
         # GH#16674 iNaT is treated as an integer when given by the user
-        with tm.assert_produces_warning(
-            FutureWarning, match="Setting an item of incompatible dtype"
-        ):
+        with pytest.raises(TypeError, match="Invalid value"):
             df.loc["b", "timestamp"] = iNaT
-        assert not isna(df.loc["b", "timestamp"])
-        assert df["timestamp"].dtype == np.object_
-        assert df.loc["b", "timestamp"] == iNaT
 
         # allow this syntax (as of GH#3216)
         df.loc["c", "timestamp"] = np.nan
@@ -851,35 +845,11 @@ def test_setitem_single_column_mixed_datetime(self):
 
     def test_setitem_mixed_datetime(self):
         # GH 9336
-        expected = DataFrame(
-            {
-                "a": [0, 0, 0, 0, 13, 14],
-                "b": [
-                    datetime(2012, 1, 1),
-                    1,
-                    "x",
-                    "y",
-                    datetime(2013, 1, 1),
-                    datetime(2014, 1, 1),
-                ],
-            }
-        )
         df = DataFrame(0, columns=list("ab"), index=range(6))
         df["b"] = pd.NaT
         df.loc[0, "b"] = datetime(2012, 1, 1)
-        with tm.assert_produces_warning(
-            FutureWarning, match="Setting an item of incompatible dtype"
-        ):
+        with pytest.raises(TypeError, match="Invalid value"):
             df.loc[1, "b"] = 1
-        df.loc[[2, 3], "b"] = "x", "y"
-        A = np.array(
-            [
-                [13, np.datetime64("2013-01-01T00:00:00")],
-                [14, np.datetime64("2014-01-01T00:00:00")],
-            ]
-        )
-        df.loc[[4, 5], ["a", "b"]] = A
-        tm.assert_frame_equal(df, expected)
 
     def test_setitem_frame_float(self, float_frame):
         piece = float_frame.loc[float_frame.index[:2], ["A", "B"]]
@@ -936,12 +906,8 @@ def test_setitem_frame_upcast(self):
         # needs upcasting
         df = DataFrame([[1, 2, "foo"], [3, 4, "bar"]], columns=["A", "B", "C"])
         df2 = df.copy()
-        with tm.assert_produces_warning(FutureWarning, match="incompatible dtype"):
+        with pytest.raises(TypeError, match="Invalid value"):
             df2.loc[:, ["A", "B"]] = df.loc[:, ["A", "B"]] + 0.5
-        expected = df.reindex(columns=["A", "B"])
-        expected += 0.5
-        expected["C"] = df["C"]
-        tm.assert_frame_equal(df2, expected)
 
     def test_setitem_frame_align(self, float_frame):
         piece = float_frame.loc[float_frame.index[:2], ["A", "B"]]
@@ -1366,12 +1332,8 @@ def test_loc_setitem_rhs_frame(self, idxr, val):
         # GH#47578
         df = DataFrame({"a": [1, 2]})
 
-        with tm.assert_produces_warning(
-            FutureWarning, match="Setting an item of incompatible dtype"
-        ):
+        with pytest.raises(TypeError, match="Invalid value"):
             df.loc[:, idxr] = DataFrame({"a": [val, 11]}, index=[1, 2])
-        expected = DataFrame({"a": [np.nan, val]})
-        tm.assert_frame_equal(df, expected)
 
     def test_iloc_setitem_enlarge_no_warning(self):
         # GH#47381
@@ -1579,18 +1541,9 @@ def test_setitem(self):
         # With NaN: because uint64 has no NaN element,
         # the column should be cast to object.
         df2 = df.copy()
-        with tm.assert_produces_warning(FutureWarning, match="incompatible dtype"):
+        with pytest.raises(TypeError, match="Invalid value"):
             df2.iloc[1, 1] = pd.NaT
             df2.iloc[1, 2] = pd.NaT
-        result = df2["B"]
-        tm.assert_series_equal(notna(result), Series([True, False, True], name="B"))
-        tm.assert_series_equal(
-            df2.dtypes,
-            Series(
-                [np.dtype("uint64"), np.dtype("O"), np.dtype("O")],
-                index=["A", "B", "C"],
-            ),
-        )
 
 
 def test_object_casting_indexing_wraps_datetimelike():
@@ -1926,22 +1879,30 @@ def test_add_new_column_infer_string():
 class TestSetitemValidation:
     # This is adapted from pandas/tests/arrays/masked/test_indexing.py
     # but checks for warnings instead of errors.
-    def _check_setitem_invalid(self, df, invalid, indexer, warn):
-        msg = "Setting an item of incompatible dtype is deprecated"
-        msg = re.escape(msg)
-
+    def _check_setitem_invalid(self, df, invalid, indexer):
         orig_df = df.copy()
 
         # iloc
-        with tm.assert_produces_warning(warn, match=msg):
+        with pytest.raises(TypeError, match="Invalid value"):
             df.iloc[indexer, 0] = invalid
             df = orig_df.copy()
 
         # loc
-        with tm.assert_produces_warning(warn, match=msg):
+        with pytest.raises(TypeError, match="Invalid value"):
             df.loc[indexer, "a"] = invalid
             df = orig_df.copy()
 
+    def _check_setitem_valid(self, df, invalid, indexer):
+        orig_df = df.copy()
+
+        # iloc
+        df.iloc[indexer, 0] = invalid
+        df = orig_df.copy()
+
+        # loc
+        df.loc[indexer, "a"] = invalid
+        df = orig_df.copy()
+
     _invalid_scalars = [
         1 + 2j,
         "True",
@@ -1959,20 +1920,19 @@ def _check_setitem_invalid(self, df, invalid, indexer, warn):
     @pytest.mark.parametrize("indexer", _indexers)
     def test_setitem_validation_scalar_bool(self, invalid, indexer):
         df = DataFrame({"a": [True, False, False]}, dtype="bool")
-        self._check_setitem_invalid(df, invalid, indexer, FutureWarning)
+        self._check_setitem_invalid(df, invalid, indexer)
 
     @pytest.mark.parametrize("invalid", _invalid_scalars + [True, 1.5, np.float64(1.5)])
     @pytest.mark.parametrize("indexer", _indexers)
     def test_setitem_validation_scalar_int(self, invalid, any_int_numpy_dtype, indexer):
         df = DataFrame({"a": [1, 2, 3]}, dtype=any_int_numpy_dtype)
         if isna(invalid) and invalid is not pd.NaT and not np.isnat(invalid):
-            warn = None
+            self._check_setitem_valid(df, invalid, indexer)
         else:
-            warn = FutureWarning
-        self._check_setitem_invalid(df, invalid, indexer, warn)
+            self._check_setitem_invalid(df, invalid, indexer)
 
     @pytest.mark.parametrize("invalid", _invalid_scalars + [True])
     @pytest.mark.parametrize("indexer", _indexers)
     def test_setitem_validation_scalar_float(self, invalid, float_numpy_dtype, indexer):
         df = DataFrame({"a": [1, 2, None]}, dtype=float_numpy_dtype)
-        self._check_setitem_invalid(df, invalid, indexer, FutureWarning)
+        self._check_setitem_invalid(df, invalid, indexer)