Backport PR #57232 on branch 2.2.x (REGR: to_json converting nullable ints to floats)

doc/source/whatsnew/v2.2.1.rst

@@ -20,6 +20,7 @@ Fixed regressions
 - Fixed regression in :meth:`DataFrame.loc` raising ``IndexError`` for non-unique, masked dtype indexes where result has more than 10,000 rows (:issue:`57027`)
 - Fixed regression in :meth:`DataFrame.sort_index` not producing a stable sort for a index with duplicates (:issue:`57151`)
 - Fixed regression in :meth:`DataFrame.to_dict` with ``orient='list'`` and datetime or timedelta types returning integers (:issue:`54824`)
+- Fixed regression in :meth:`DataFrame.to_json` converting nullable integers to floats (:issue:`57224`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` ignoring the ``skipna`` argument (:issue:`57040`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` where values containing the minimum or maximum value for the dtype could produce incorrect results (:issue:`57040`)
 - Fixed regression in :meth:`Index.join` raising ``TypeError`` when joining an empty index to a non-empty index containing mixed dtype values (:issue:`57048`)

pandas/core/arrays/arrow/array.py

@@ -1348,6 +1348,11 @@ def _to_timedeltaarray(self) -> TimedeltaArray:
         np_array = np_array.astype(np_dtype)
         return TimedeltaArray._simple_new(np_array, dtype=np_dtype)
 
+    def _values_for_json(self) -> np.ndarray:
+        if is_numeric_dtype(self.dtype):
+            return np.asarray(self, dtype=object)
+        return super()._values_for_json()
+
     @doc(ExtensionArray.to_numpy)
     def to_numpy(
         self,

pandas/core/arrays/masked.py

@@ -430,6 +430,9 @@ def __abs__(self) -> Self:
 
     # ------------------------------------------------------------------
 
+    def _values_for_json(self) -> np.ndarray:
+        return np.asarray(self, dtype=object)
+
     def to_numpy(
         self,
         dtype: npt.DTypeLike | None = None,

pandas/tests/io/json/test_pandas.py

@@ -2172,3 +2172,19 @@ def test_json_pos_args_deprecation():
     with tm.assert_produces_warning(FutureWarning, match=msg):
         buf = BytesIO()
         df.to_json(buf, "split")
+
+
+@td.skip_if_no("pyarrow")
+def test_to_json_ea_null():
+    # GH#57224
+    df = DataFrame(
+        {
+            "a": Series([1, NA], dtype="int64[pyarrow]"),
+            "b": Series([2, NA], dtype="Int64"),
+        }
+    )
+    result = df.to_json(orient="records", lines=True)
+    expected = """{"a":1,"b":2}
+{"a":null,"b":null}
+"""
+    assert result == expected