Fix rank, json tests

Author: jbrockmendel

pandas/core/arrays/arrow/array.py

@@ -558,8 +558,8 @@ def _box_pa_array(
                         value, copy=copy, dtype=pass_dtype
                     )
                 mask = dta.isna()
-                value_i8 = dta.view("i8")
-                if not np.asarray(value_i8).flags["WRITEABLE"]:
+                value_i8 = cast("npt.NDArray", dta.view("i8"))
+                if not value_i8.flags["WRITEABLE"]:
                     # e.g. test_setitem_frame_2d_values
                     value_i8 = value_i8.copy()
                     dta = DatetimeArray._from_sequence(value_i8, dtype=dta.dtype)

pandas/io/json/_json.py

@@ -994,6 +994,13 @@ def _read_ujson(self) -> DataFrame | Series:
         else:
             obj = self._get_object_parser(self.data)
         if self.dtype_backend is not lib.no_default:
+            if self.dtype_backend == "pyarrow":
+                # The construction above takes "null" to NaN, which we want to
+                #  convert to NA. But .convert_dtypes to pyarrow doesn't allow
+                #  that, so we do a 2-step conversion through numpy-nullable.
+                obj = obj.convert_dtypes(
+                    infer_objects=False, dtype_backend="numpy_nullable"
+                )
             return obj.convert_dtypes(
                 infer_objects=False, dtype_backend=self.dtype_backend
             )
@@ -1071,6 +1078,13 @@ def __next__(self) -> DataFrame | Series:
             raise ex
 
         if self.dtype_backend is not lib.no_default:
+            if self.dtype_backend == "pyarrow":
+                # The construction above takes "null" to NaN, which we want to
+                #  convert to NA. But .convert_dtypes to pyarrow doesn't allow
+                #  that, so we do a 2-step conversion through numpy-nullable.
+                obj = obj.convert_dtypes(
+                    infer_objects=False, dtype_backend="numpy_nullable"
+                )
             return obj.convert_dtypes(
                 infer_objects=False, dtype_backend=self.dtype_backend
             )

pandas/tests/extension/test_arrow.py

@@ -285,7 +285,10 @@ def test_map(self, data_missing, na_action):
             tm.assert_numpy_array_equal(result, expected)
         else:
             result = data_missing.map(lambda x: x, na_action=na_action)
-            if data_missing.dtype == "float32[pyarrow]":
+            if (
+                data_missing.dtype == "float32[pyarrow]"
+                and not using_pyarrow_strict_nans()
+            ):
                 # map roundtrips through objects, which converts to float64
                 expected = data_missing.to_numpy(dtype="float64", na_value=np.nan)
             else:

pandas/tests/series/methods/test_rank.py

@@ -271,7 +271,12 @@ def test_rank_signature(self):
 
     def test_rank_tie_methods(self, ser, results, dtype, using_infer_string):
         method, exp = results
-        if dtype == "int64" or (not using_infer_string and dtype == "str"):
+        if (
+            dtype == "int64"
+            or dtype == "int64[pyarrow]"
+            or dtype == "uint64[pyarrow]"
+            or (not using_infer_string and dtype == "str")
+        ):
             pytest.skip("int64/str does not support NaN")
 
         ser = ser if dtype is None else ser.astype(dtype)
@@ -283,7 +288,15 @@ def test_rank_tie_methods(self, ser, results, dtype, using_infer_string):
                 exp[np.isnan(ser)] = 9.5
             elif method == "dense":
                 exp[np.isnan(ser)] = 6
-        tm.assert_series_equal(result, Series(exp, dtype=expected_dtype(dtype, method)))
+            elif method == "max":
+                exp[np.isnan(ser)] = 10
+            elif method == "min":
+                exp[np.isnan(ser)] = 9
+            elif method == "first":
+                exp[np.isnan(ser)] = [9, 10]
+
+        expected = Series(exp, dtype=expected_dtype(dtype, method))
+        tm.assert_series_equal(result, expected)
 
     @pytest.mark.parametrize("na_option", ["top", "bottom", "keep"])
     @pytest.mark.parametrize(
@@ -395,8 +408,12 @@ def test_rank_dense_method(self, dtype, ser, exp):
 
     def test_rank_descending(self, ser, results, dtype, using_infer_string):
         method, _ = results
-        if dtype == "int64" or (not using_infer_string and dtype == "str"):
-            s = ser.dropna()
+        if (
+            dtype == "int64"
+            or dtype == "int64[pyarrow]"
+            or (not using_infer_string and dtype == "str")
+        ):
+            s = ser.dropna().astype(dtype)
         else:
             s = ser.astype(dtype)