BUG: Parse missing values using read_json with dtype=False to NaN instead of None (GH28501) (#37834)

Author: avinashpancham

doc/source/whatsnew/v1.2.0.rst

@@ -653,6 +653,7 @@ I/O
 - Bug in :func:`read_html` was raising a ``TypeError`` when supplying a ``pathlib.Path`` argument to the ``io`` parameter (:issue:`37705`)
 - :meth:`to_excel` and :meth:`to_markdown` support writing to fsspec URLs such as S3 and Google Cloud Storage (:issue:`33987`)
 - Bug in :meth:`read_fw` was not skipping blank lines (even with ``skip_blank_lines=True``) (:issue:`37758`)
+- Parse missing values using :func:`read_json` with ``dtype=False`` to ``NaN`` instead of ``None`` (:issue:`28501`)
 - :meth:`read_fwf` was inferring compression with ``compression=None`` which was not consistent with the other :meth:``read_*`` functions (:issue:`37909`)
 
 Period

pandas/io/json/_json.py

@@ -20,7 +20,7 @@
 
 from pandas.core.dtypes.common import ensure_str, is_period_dtype
 
-from pandas import DataFrame, MultiIndex, Series, isna, to_datetime
+from pandas import DataFrame, MultiIndex, Series, isna, notna, to_datetime
 from pandas.core import generic
 from pandas.core.construction import create_series_with_explicit_dtype
 from pandas.core.generic import NDFrame
@@ -858,7 +858,10 @@ def _try_convert_data(self, name, data, use_dtypes=True, convert_dates=True):
         # don't try to coerce, unless a force conversion
         if use_dtypes:
             if not self.dtype:
-                return data, False
+                if all(notna(data)):
+                    return data, False
+                return data.fillna(np.nan), True
+
             elif self.dtype is True:
                 pass
             else:

pandas/tests/io/json/test_pandas.py

@@ -345,10 +345,16 @@ def test_frame_from_json_missing_data(self, orient, convert_axes, numpy, dtype):
             convert_axes=convert_axes,
             dtype=dtype,
         )
-        if not dtype:  # TODO: Special case for object data; maybe a bug?
-            assert result.iloc[0, 2] is None
-        else:
-            assert np.isnan(result.iloc[0, 2])
+        assert np.isnan(result.iloc[0, 2])
+
+    @pytest.mark.parametrize("dtype", [True, False])
+    def test_frame_read_json_dtype_missing_value(self, orient, dtype):
+        # GH28501 Parse missing values using read_json with dtype=False
+        # to NaN instead of None
+        result = read_json("[null]", dtype=dtype)
+        expected = DataFrame([np.nan])
+
+        tm.assert_frame_equal(result, expected)
 
     @pytest.mark.parametrize("inf", [np.inf, np.NINF])
     @pytest.mark.parametrize("dtype", [True, False])