Backport PR #52426 on branch 2.0.x (API: Series/DataFrame from empty …

…dict should have RangeIndex) (#52578)

Backport PR #52426: API: Series/DataFrame from empty dict should have RangeIndex

Co-authored-by: Terji Petersen <terji78@gmail.com>

doc/source/whatsnew/v2.0.1.rst

@@ -32,7 +32,8 @@ Bug fixes
 
 Other
 ~~~~~
--
+- :class:`DataFrame` created from empty dicts had :attr:`~DataFrame.columns`  of dtype ``object``. It is now a :class:`RangeIndex` (:issue:`52404`)
+- :class:`Series` created from empty dicts had :attr:`~Series.index`  of dtype ``object``. It is now a :class:`RangeIndex` (:issue:`52404`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_201.contributors:

pandas/core/internals/construction.py

@@ -465,7 +465,7 @@ def dict_to_mgr(
 
     else:
         keys = list(data.keys())
-        columns = Index(keys)
+        columns = Index(keys) if keys else default_index(0)
         arrays = [com.maybe_iterable_to_list(data[k]) for k in keys]
         arrays = [arr if not isinstance(arr, Index) else arr._data for arr in arrays]
 

pandas/core/series.py

@@ -559,7 +559,7 @@ def _init_dict(
                 values = []
             keys = index
         else:
-            keys, values = (), []
+            keys, values = default_index(0), []
 
         # Input is now list-like, so rely on "standard" construction:
         s = Series(values, index=keys, dtype=dtype)

pandas/tests/frame/constructors/test_from_dict.py

@@ -7,6 +7,7 @@
     DataFrame,
     Index,
     MultiIndex,
+    RangeIndex,
     Series,
 )
 import pandas._testing as tm
@@ -152,21 +153,26 @@ def test_from_dict_columns_parameter(self):
             DataFrame.from_dict({"A": [1, 2], "B": [4, 5]}, columns=["one", "two"])
 
     @pytest.mark.parametrize(
-        "data_dict, keys, orient",
+        "data_dict, orient, expected",
         [
-            ({}, [], "index"),
-            ([{("a",): 1}, {("a",): 2}], [("a",)], "columns"),
-            ([OrderedDict([(("a",), 1), (("b",), 2)])], [("a",), ("b",)], "columns"),
-            ([{("a", "b"): 1}], [("a", "b")], "columns"),
+            ({}, "index", RangeIndex(0)),
+            (
+                [{("a",): 1}, {("a",): 2}],
+                "columns",
+                Index([("a",)], tupleize_cols=False),
+            ),
+            (
+                [OrderedDict([(("a",), 1), (("b",), 2)])],
+                "columns",
+                Index([("a",), ("b",)], tupleize_cols=False),
+            ),
+            ([{("a", "b"): 1}], "columns", Index([("a", "b")], tupleize_cols=False)),
         ],
     )
-    def test_constructor_from_dict_tuples(self, data_dict, keys, orient):
+    def test_constructor_from_dict_tuples(self, data_dict, orient, expected):
         # GH#16769
         df = DataFrame.from_dict(data_dict, orient)
-
         result = df.columns
-        expected = Index(keys, dtype="object", tupleize_cols=False)
-
         tm.assert_index_equal(result, expected)
 
     def test_frame_dict_constructor_empty_series(self):

pandas/tests/frame/test_constructors.py

@@ -224,7 +224,7 @@ def test_empty_constructor(self, constructor):
         ],
     )
     def test_empty_constructor_object_index(self, constructor):
-        expected = DataFrame(columns=Index([]))
+        expected = DataFrame(index=RangeIndex(0), columns=RangeIndex(0))
         result = constructor()
         assert len(result.index) == 0
         assert len(result.columns) == 0

pandas/tests/io/json/test_pandas.py

@@ -215,9 +215,7 @@ def test_roundtrip_empty(self, orient, convert_axes):
             idx = pd.Index([], dtype=(float if convert_axes else object))
             expected = DataFrame(index=idx, columns=idx)
         elif orient in ["index", "columns"]:
-            # TODO: this condition is probably a bug
-            idx = pd.Index([], dtype=(float if convert_axes else object))
-            expected = DataFrame(columns=idx)
+            expected = DataFrame()
         else:
             expected = empty_frame.copy()
 
@@ -651,11 +649,9 @@ def test_series_roundtrip_empty(self, orient):
         data = empty_series.to_json(orient=orient)
         result = read_json(data, typ="series", orient=orient)
 
-        expected = empty_series
-        if orient in ("values", "records"):
-            expected = expected.reset_index(drop=True)
-        else:
-            expected.index = expected.index.astype(float)
+        expected = empty_series.reset_index(drop=True)
+        if orient in ("split"):
+            expected.index = expected.index.astype(np.float64)
 
         tm.assert_series_equal(result, expected)
 

pandas/tests/io/test_parquet.py

@@ -1203,9 +1203,8 @@ def test_error_on_using_partition_cols_and_partition_on(
 
     def test_empty_dataframe(self, fp):
         # GH #27339
-        df = pd.DataFrame(index=[], columns=[])
+        df = pd.DataFrame()
         expected = df.copy()
-        expected.index.name = "index"
         check_round_trip(df, fp, expected=expected)
 
     def test_timezone_aware_index(self, fp, timezone_aware_date_list):
@@ -1260,8 +1259,5 @@ def test_invalid_dtype_backend(self, engine):
     def test_empty_columns(self, fp):
         # GH 52034
         df = pd.DataFrame(index=pd.Index(["a", "b", "c"], name="custom name"))
-        expected = pd.DataFrame(
-            columns=pd.Index([], dtype=object),
-            index=pd.Index(["a", "b", "c"], name="custom name"),
-        )
+        expected = pd.DataFrame(index=pd.Index(["a", "b", "c"], name="custom name"))
         check_round_trip(df, fp, expected=expected)

pandas/tests/series/test_constructors.py

@@ -93,35 +93,34 @@ def test_unparseable_strings_with_dt64_dtype(self):
             Series(np.array(vals, dtype=object), dtype="datetime64[ns]")
 
     @pytest.mark.parametrize(
-        "constructor,check_index_type",
+        "constructor",
         [
             # NOTE: some overlap with test_constructor_empty but that test does not
             # test for None or an empty generator.
             # test_constructor_pass_none tests None but only with the index also
             # passed.
-            (lambda idx: Series(index=idx), True),
-            (lambda idx: Series(None, index=idx), True),
-            (lambda idx: Series({}, index=idx), False),  # creates an Index[object]
-            (lambda idx: Series((), index=idx), True),
-            (lambda idx: Series([], index=idx), True),
-            (lambda idx: Series((_ for _ in []), index=idx), True),
-            (lambda idx: Series(data=None, index=idx), True),
-            (lambda idx: Series(data={}, index=idx), False),  # creates an Index[object]
-            (lambda idx: Series(data=(), index=idx), True),
-            (lambda idx: Series(data=[], index=idx), True),
-            (lambda idx: Series(data=(_ for _ in []), index=idx), True),
+            (lambda idx: Series(index=idx)),
+            (lambda idx: Series(None, index=idx)),
+            (lambda idx: Series({}, index=idx)),
+            (lambda idx: Series((), index=idx)),
+            (lambda idx: Series([], index=idx)),
+            (lambda idx: Series((_ for _ in []), index=idx)),
+            (lambda idx: Series(data=None, index=idx)),
+            (lambda idx: Series(data={}, index=idx)),
+            (lambda idx: Series(data=(), index=idx)),
+            (lambda idx: Series(data=[], index=idx)),
+            (lambda idx: Series(data=(_ for _ in []), index=idx)),
         ],
     )
     @pytest.mark.parametrize("empty_index", [None, []])
-    def test_empty_constructor(self, constructor, check_index_type, empty_index):
-        # TODO: share with frame test of the same name
+    def test_empty_constructor(self, constructor, empty_index):
         # GH 49573 (addition of empty_index parameter)
         expected = Series(index=empty_index)
         result = constructor(empty_index)
 
         assert result.dtype == object
         assert len(result.index) == 0
-        tm.assert_series_equal(result, expected, check_index_type=check_index_type)
+        tm.assert_series_equal(result, expected, check_index_type=True)
 
     def test_invalid_dtype(self):
         # GH15520