Backport PR #52872 on branch 2.0.x (BUG: convert_dtypes ingoring convert keywords for pyarrow backend) (#52959)

Backport PR #52872: BUG: convert_dtypes ingoring convert keywords for pyarrow backend

Co-authored-by: Patrick Hoefler <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v2.0.2.rst

@@ -22,6 +22,7 @@ Bug fixes
 ~~~~~~~~~
 - Bug in :func:`api.interchange.from_dataframe` was returning :class:`DataFrame`'s of incorrect sizes when called on slices (:issue:`52824`)
 - Bug in :func:`api.interchange.from_dataframe` was unnecessarily raising on bitmasks (:issue:`49888`)
+- Bug in :meth:`DataFrame.convert_dtypes` ignores ``convert_*`` keywords when set to False ``dtype_backend="pyarrow"`` (:issue:`52872`)
 - Bug in :meth:`pd.array` raising for ``NumPy`` array and ``pa.large_string`` or ``pa.large_binary`` (:issue:`52590`)
 -
 

pandas/core/dtypes/cast.py

@@ -1122,20 +1122,29 @@ def convert_dtypes(
         from pandas.core.arrays.arrow.dtype import ArrowDtype
         from pandas.core.arrays.string_ import StringDtype
 
-        if isinstance(inferred_dtype, PandasExtensionDtype):
-            base_dtype = inferred_dtype.base
-        elif isinstance(inferred_dtype, (BaseMaskedDtype, ArrowDtype)):
-            base_dtype = inferred_dtype.numpy_dtype
-        elif isinstance(inferred_dtype, StringDtype):
-            base_dtype = np.dtype(str)
-        else:
-            # error: Incompatible types in assignment (expression has type
-            # "Union[str, Any, dtype[Any], ExtensionDtype]",
-            # variable has type "Union[dtype[Any], ExtensionDtype, None]")
-            base_dtype = inferred_dtype  # type: ignore[assignment]
-        pa_type = to_pyarrow_type(base_dtype)
-        if pa_type is not None:
-            inferred_dtype = ArrowDtype(pa_type)
+        assert not isinstance(inferred_dtype, str)
+
+        if (
+            (convert_integer and inferred_dtype.kind in "iu")
+            or (convert_floating and inferred_dtype.kind in "fc")
+            or (convert_boolean and inferred_dtype.kind == "b")
+            or (convert_string and isinstance(inferred_dtype, StringDtype))
+            or (
+                inferred_dtype.kind not in "iufcb"
+                and not isinstance(inferred_dtype, StringDtype)
+            )
+        ):
+            if isinstance(inferred_dtype, PandasExtensionDtype):
+                base_dtype = inferred_dtype.base
+            elif isinstance(inferred_dtype, (BaseMaskedDtype, ArrowDtype)):
+                base_dtype = inferred_dtype.numpy_dtype
+            elif isinstance(inferred_dtype, StringDtype):
+                base_dtype = np.dtype(str)
+            else:
+                base_dtype = inferred_dtype
+            pa_type = to_pyarrow_type(base_dtype)
+            if pa_type is not None:
+                inferred_dtype = ArrowDtype(pa_type)
 
     # error: Incompatible return value type (got "Union[str, Union[dtype[Any],
     # ExtensionDtype]]", expected "Union[dtype[Any], ExtensionDtype]")

pandas/tests/frame/methods/test_convert_dtypes.py

@@ -134,3 +134,17 @@ def test_pyarrow_engine_lines_false(self):
         )
         with pytest.raises(ValueError, match=msg):
             df.convert_dtypes(dtype_backend="numpy")
+
+    def test_pyarrow_backend_no_convesion(self):
+        # GH#52872
+        pytest.importorskip("pyarrow")
+        df = pd.DataFrame({"a": [1, 2], "b": 1.5, "c": True, "d": "x"})
+        expected = df.copy()
+        result = df.convert_dtypes(
+            convert_floating=False,
+            convert_integer=False,
+            convert_boolean=False,
+            convert_string=False,
+            dtype_backend="pyarrow",
+        )
+        tm.assert_frame_equal(result, expected)