TST: specify dt64 units (#56217)

* TST: specify dt64 units

* specify dt64 unit

Author: jbrockmendel

pandas/tests/frame/test_reductions.py

@@ -798,7 +798,7 @@ def test_std_timedelta64_skipna_false(self):
         "values", [["2022-01-01", "2022-01-02", pd.NaT, "2022-01-03"], 4 * [pd.NaT]]
     )
     def test_std_datetime64_with_nat(
-        self, values, skipna, using_array_manager, request
+        self, values, skipna, using_array_manager, request, unit
     ):
         # GH#51335
         if using_array_manager and (
@@ -808,13 +808,14 @@ def test_std_datetime64_with_nat(
                 reason="GH#51446: Incorrect type inference on NaT in reduction result"
             )
             request.applymarker(mark)
-        df = DataFrame({"a": to_datetime(values)})
+        dti = to_datetime(values).as_unit(unit)
+        df = DataFrame({"a": dti})
         result = df.std(skipna=skipna)
         if not skipna or all(value is pd.NaT for value in values):
-            expected = Series({"a": pd.NaT}, dtype="timedelta64[ns]")
+            expected = Series({"a": pd.NaT}, dtype=f"timedelta64[{unit}]")
         else:
             # 86400000000000ns == 1 day
-            expected = Series({"a": 86400000000000}, dtype="timedelta64[ns]")
+            expected = Series({"a": 86400000000000}, dtype=f"timedelta64[{unit}]")
         tm.assert_series_equal(result, expected)
 
     def test_sum_corner(self):

pandas/tests/groupby/test_timegrouper.py

@@ -537,7 +537,9 @@ def test_groupby_groups_datetimeindex2(self):
         for date in dates:
             result = grouped.get_group(date)
             data = [[df.loc[date, "A"], df.loc[date, "B"]]]
-            expected_index = DatetimeIndex([date], name="date", freq="D")
+            expected_index = DatetimeIndex(
+                [date], name="date", freq="D", dtype=index.dtype
+            )
             expected = DataFrame(data, columns=list("AB"), index=expected_index)
             tm.assert_frame_equal(result, expected)
 

pandas/tests/indexes/datetimes/methods/test_round.py

@@ -40,9 +40,9 @@ def test_round_invalid(self, freq, error_msg):
         with pytest.raises(ValueError, match=error_msg):
             dti.round(freq)
 
-    def test_round(self, tz_naive_fixture):
+    def test_round(self, tz_naive_fixture, unit):
         tz = tz_naive_fixture
-        rng = date_range(start="2016-01-01", periods=5, freq="30Min", tz=tz)
+        rng = date_range(start="2016-01-01", periods=5, freq="30Min", tz=tz, unit=unit)
         elt = rng[1]
 
         expected_rng = DatetimeIndex(
@@ -53,10 +53,11 @@ def test_round(self, tz_naive_fixture):
                 Timestamp("2016-01-01 02:00:00", tz=tz),
                 Timestamp("2016-01-01 02:00:00", tz=tz),
             ]
-        )
+        ).as_unit(unit)
         expected_elt = expected_rng[1]
 
-        tm.assert_index_equal(rng.round(freq="h"), expected_rng)
+        result = rng.round(freq="h")
+        tm.assert_index_equal(result, expected_rng)
         assert elt.round(freq="h") == expected_elt
 
         msg = INVALID_FREQ_ERR_MSG
@@ -74,30 +75,31 @@ def test_round(self, tz_naive_fixture):
     def test_round2(self, tz_naive_fixture):
         tz = tz_naive_fixture
         # GH#14440 & GH#15578
-        index = DatetimeIndex(["2016-10-17 12:00:00.0015"], tz=tz)
+        index = DatetimeIndex(["2016-10-17 12:00:00.0015"], tz=tz).as_unit("ns")
         result = index.round("ms")
-        expected = DatetimeIndex(["2016-10-17 12:00:00.002000"], tz=tz)
+        expected = DatetimeIndex(["2016-10-17 12:00:00.002000"], tz=tz).as_unit("ns")
         tm.assert_index_equal(result, expected)
 
         for freq in ["us", "ns"]:
             tm.assert_index_equal(index, index.round(freq))
 
     def test_round3(self, tz_naive_fixture):
         tz = tz_naive_fixture
-        index = DatetimeIndex(["2016-10-17 12:00:00.00149"], tz=tz)
+        index = DatetimeIndex(["2016-10-17 12:00:00.00149"], tz=tz).as_unit("ns")
         result = index.round("ms")
-        expected = DatetimeIndex(["2016-10-17 12:00:00.001000"], tz=tz)
+        expected = DatetimeIndex(["2016-10-17 12:00:00.001000"], tz=tz).as_unit("ns")
         tm.assert_index_equal(result, expected)
 
     def test_round4(self, tz_naive_fixture):
-        index = DatetimeIndex(["2016-10-17 12:00:00.001501031"])
+        index = DatetimeIndex(["2016-10-17 12:00:00.001501031"], dtype="M8[ns]")
         result = index.round("10ns")
-        expected = DatetimeIndex(["2016-10-17 12:00:00.001501030"])
+        expected = DatetimeIndex(["2016-10-17 12:00:00.001501030"], dtype="M8[ns]")
         tm.assert_index_equal(result, expected)
 
+        ts = "2016-10-17 12:00:00.001501031"
+        dti = DatetimeIndex([ts], dtype="M8[ns]")
         with tm.assert_produces_warning(False):
-            ts = "2016-10-17 12:00:00.001501031"
-            DatetimeIndex([ts]).round("1010ns")
+            dti.round("1010ns")
 
     def test_no_rounding_occurs(self, tz_naive_fixture):
         # GH 21262
@@ -112,9 +114,10 @@ def test_no_rounding_occurs(self, tz_naive_fixture):
                 Timestamp("2016-01-01 00:06:00", tz=tz),
                 Timestamp("2016-01-01 00:08:00", tz=tz),
             ]
-        )
+        ).as_unit("ns")
 
-        tm.assert_index_equal(rng.round(freq="2min"), expected_rng)
+        result = rng.round(freq="2min")
+        tm.assert_index_equal(result, expected_rng)
 
     @pytest.mark.parametrize(
         "test_input, rounder, freq, expected",

pandas/tests/indexes/datetimes/test_constructors.py

@@ -707,10 +707,14 @@ def test_constructor_dtype(self):
         idx = DatetimeIndex(
             ["2013-01-01", "2013-01-02"], dtype="datetime64[ns, US/Eastern]"
         )
-        expected = DatetimeIndex(["2013-01-01", "2013-01-02"]).tz_localize("US/Eastern")
+        expected = (
+            DatetimeIndex(["2013-01-01", "2013-01-02"])
+            .as_unit("ns")
+            .tz_localize("US/Eastern")
+        )
         tm.assert_index_equal(idx, expected)
 
-        idx = DatetimeIndex(["2013-01-01", "2013-01-02"], tz="US/Eastern")
+        idx = DatetimeIndex(["2013-01-01", "2013-01-02"], tz="US/Eastern").as_unit("ns")
         tm.assert_index_equal(idx, expected)
 
     def test_constructor_dtype_tz_mismatch_raises(self):
@@ -774,7 +778,7 @@ def test_constructor_start_end_with_tz(self, tz):
         result = date_range(freq="D", start=start, end=end, tz=tz)
         expected = DatetimeIndex(
             ["2013-01-01 06:00:00", "2013-01-02 06:00:00"],
-            tz="America/Los_Angeles",
+            dtype="M8[ns, America/Los_Angeles]",
             freq="D",
         )
         tm.assert_index_equal(result, expected)

pandas/tests/indexes/datetimes/test_indexing.py

@@ -226,58 +226,54 @@ def test_take_nan_first_datetime(self):
         expected = DatetimeIndex([index[-1], index[0], index[1]])
         tm.assert_index_equal(result, expected)
 
-    def test_take(self):
+    @pytest.mark.parametrize("tz", [None, "Asia/Tokyo"])
+    def test_take(self, tz):
         # GH#10295
-        idx1 = date_range("2011-01-01", "2011-01-31", freq="D", name="idx")
-        idx2 = date_range(
-            "2011-01-01", "2011-01-31", freq="D", tz="Asia/Tokyo", name="idx"
+        idx = date_range("2011-01-01", "2011-01-31", freq="D", name="idx", tz=tz)
+
+        result = idx.take([0])
+        assert result == Timestamp("2011-01-01", tz=idx.tz)
+
+        result = idx.take([0, 1, 2])
+        expected = date_range(
+            "2011-01-01", "2011-01-03", freq="D", tz=idx.tz, name="idx"
         )
+        tm.assert_index_equal(result, expected)
+        assert result.freq == expected.freq
 
-        for idx in [idx1, idx2]:
-            result = idx.take([0])
-            assert result == Timestamp("2011-01-01", tz=idx.tz)
+        result = idx.take([0, 2, 4])
+        expected = date_range(
+            "2011-01-01", "2011-01-05", freq="2D", tz=idx.tz, name="idx"
+        )
+        tm.assert_index_equal(result, expected)
+        assert result.freq == expected.freq
 
-            result = idx.take([0, 1, 2])
-            expected = date_range(
-                "2011-01-01", "2011-01-03", freq="D", tz=idx.tz, name="idx"
-            )
-            tm.assert_index_equal(result, expected)
-            assert result.freq == expected.freq
+        result = idx.take([7, 4, 1])
+        expected = date_range(
+            "2011-01-08", "2011-01-02", freq="-3D", tz=idx.tz, name="idx"
+        )
+        tm.assert_index_equal(result, expected)
+        assert result.freq == expected.freq
 
-            result = idx.take([0, 2, 4])
-            expected = date_range(
-                "2011-01-01", "2011-01-05", freq="2D", tz=idx.tz, name="idx"
-            )
-            tm.assert_index_equal(result, expected)
-            assert result.freq == expected.freq
+        result = idx.take([3, 2, 5])
+        expected = DatetimeIndex(
+            ["2011-01-04", "2011-01-03", "2011-01-06"],
+            dtype=idx.dtype,
+            freq=None,
+            name="idx",
+        )
+        tm.assert_index_equal(result, expected)
+        assert result.freq is None
 
-            result = idx.take([7, 4, 1])
-            expected = date_range(
-                "2011-01-08", "2011-01-02", freq="-3D", tz=idx.tz, name="idx"
-            )
-            tm.assert_index_equal(result, expected)
-            assert result.freq == expected.freq
-
-            result = idx.take([3, 2, 5])
-            expected = DatetimeIndex(
-                ["2011-01-04", "2011-01-03", "2011-01-06"],
-                dtype=idx.dtype,
-                freq=None,
-                name="idx",
-            )
-            tm.assert_index_equal(result, expected)
-            assert result.freq is None
-
-            result = idx.take([-3, 2, 5])
-            expected = DatetimeIndex(
-                ["2011-01-29", "2011-01-03", "2011-01-06"],
-                dtype=idx.dtype,
-                freq=None,
-                tz=idx.tz,
-                name="idx",
-            )
-            tm.assert_index_equal(result, expected)
-            assert result.freq is None
+        result = idx.take([-3, 2, 5])
+        expected = DatetimeIndex(
+            ["2011-01-29", "2011-01-03", "2011-01-06"],
+            dtype=idx.dtype,
+            freq=None,
+            name="idx",
+        )
+        tm.assert_index_equal(result, expected)
+        assert result.freq is None
 
     def test_take_invalid_kwargs(self):
         idx = date_range("2011-01-01", "2011-01-31", freq="D", name="idx")

pandas/tests/indexing/test_coercion.py

@@ -256,13 +256,13 @@ def test_insert_float_index(
     def test_insert_index_datetimes(self, fill_val, exp_dtype, insert_value):
         obj = pd.DatetimeIndex(
             ["2011-01-01", "2011-01-02", "2011-01-03", "2011-01-04"], tz=fill_val.tz
-        )
+        ).as_unit("ns")
         assert obj.dtype == exp_dtype
 
         exp = pd.DatetimeIndex(
             ["2011-01-01", fill_val.date(), "2011-01-02", "2011-01-03", "2011-01-04"],
             tz=fill_val.tz,
-        )
+        ).as_unit("ns")
         self._assert_insert_conversion(obj, fill_val, exp, exp_dtype)
 
         if fill_val.tz:

pandas/tests/indexing/test_datetime.py

@@ -57,7 +57,10 @@ def test_indexing_fast_xs(self):
         df = DataFrame({"a": date_range("2014-01-01", periods=10, tz="UTC")})
         result = df.iloc[5]
         expected = Series(
-            [Timestamp("2014-01-06 00:00:00+0000", tz="UTC")], index=["a"], name=5
+            [Timestamp("2014-01-06 00:00:00+0000", tz="UTC")],
+            index=["a"],
+            name=5,
+            dtype="M8[ns, UTC]",
         )
         tm.assert_series_equal(result, expected)
 

pandas/tests/reshape/concat/test_datetimes.py

@@ -52,18 +52,14 @@ def test_concat_datetime_timezone(self):
         df2 = DataFrame({"b": [1, 2, 3]}, index=idx2)
         result = concat([df1, df2], axis=1)
 
-        exp_idx = (
-            DatetimeIndex(
-                [
-                    "2011-01-01 00:00:00+01:00",
-                    "2011-01-01 01:00:00+01:00",
-                    "2011-01-01 02:00:00+01:00",
-                ],
-                freq="h",
-            )
-            .tz_convert("UTC")
-            .tz_convert("Europe/Paris")
-            .as_unit("ns")
+        exp_idx = DatetimeIndex(
+            [
+                "2011-01-01 00:00:00+01:00",
+                "2011-01-01 01:00:00+01:00",
+                "2011-01-01 02:00:00+01:00",
+            ],
+            dtype="M8[ns, Europe/Paris]",
+            freq="h",
         )
 
         expected = DataFrame(
@@ -431,21 +427,25 @@ def test_concat_multiindex_with_tz(self):
         # GH 6606
         df = DataFrame(
             {
-                "dt": [
-                    datetime(2014, 1, 1),
-                    datetime(2014, 1, 2),
-                    datetime(2014, 1, 3),
-                ],
+                "dt": DatetimeIndex(
+                    [
+                        datetime(2014, 1, 1),
+                        datetime(2014, 1, 2),
+                        datetime(2014, 1, 3),
+                    ],
+                    dtype="M8[ns, US/Pacific]",
+                ),
                 "b": ["A", "B", "C"],
                 "c": [1, 2, 3],
                 "d": [4, 5, 6],
             }
         )
-        df["dt"] = df["dt"].apply(lambda d: Timestamp(d, tz="US/Pacific"))
         df = df.set_index(["dt", "b"])
 
         exp_idx1 = DatetimeIndex(
-            ["2014-01-01", "2014-01-02", "2014-01-03"] * 2, tz="US/Pacific", name="dt"
+            ["2014-01-01", "2014-01-02", "2014-01-03"] * 2,
+            dtype="M8[ns, US/Pacific]",
+            name="dt",
         )
         exp_idx2 = Index(["A", "B", "C"] * 2, name="b")
         exp_idx = MultiIndex.from_arrays([exp_idx1, exp_idx2])

pandas/tests/series/indexing/test_setitem.py

@@ -126,7 +126,8 @@ def test_setitem_with_tz_dst(self, indexer_sli):
                 Timestamp("2016-11-06 00:00-04:00", tz=tz),
                 Timestamp("2011-01-01 00:00-05:00", tz=tz),
                 Timestamp("2016-11-06 01:00-05:00", tz=tz),
-            ]
+            ],
+            dtype=orig.dtype,
         )
 
         # scalar
@@ -138,6 +139,7 @@ def test_setitem_with_tz_dst(self, indexer_sli):
         vals = Series(
             [Timestamp("2011-01-01", tz=tz), Timestamp("2012-01-01", tz=tz)],
             index=[1, 2],
+            dtype=orig.dtype,
         )
         assert vals.dtype == f"datetime64[ns, {tz}]"
 
@@ -146,7 +148,8 @@ def test_setitem_with_tz_dst(self, indexer_sli):
                 Timestamp("2016-11-06 00:00", tz=tz),
                 Timestamp("2011-01-01 00:00", tz=tz),
                 Timestamp("2012-01-01 00:00", tz=tz),
-            ]
+            ],
+            dtype=orig.dtype,
         )
 
         ser = orig.copy()

pandas/tests/series/test_constructors.py

@@ -1154,24 +1154,24 @@ def test_constructor_with_datetime_tz5(self):
 
     def test_constructor_with_datetime_tz4(self):
         # inference
-        s = Series(
+        ser = Series(
             [
                 Timestamp("2013-01-01 13:00:00-0800", tz="US/Pacific"),
                 Timestamp("2013-01-02 14:00:00-0800", tz="US/Pacific"),
             ]
         )
-        assert s.dtype == "datetime64[ns, US/Pacific]"
-        assert lib.infer_dtype(s, skipna=True) == "datetime64"
+        assert ser.dtype == "datetime64[ns, US/Pacific]"
+        assert lib.infer_dtype(ser, skipna=True) == "datetime64"
 
     def test_constructor_with_datetime_tz3(self):
-        s = Series(
+        ser = Series(
             [
                 Timestamp("2013-01-01 13:00:00-0800", tz="US/Pacific"),
                 Timestamp("2013-01-02 14:00:00-0800", tz="US/Eastern"),
             ]
         )
-        assert s.dtype == "object"
-        assert lib.infer_dtype(s, skipna=True) == "datetime"
+        assert ser.dtype == "object"
+        assert lib.infer_dtype(ser, skipna=True) == "datetime"
 
     def test_constructor_with_datetime_tz2(self):
         # with all NaT
@@ -1587,7 +1587,7 @@ def test_NaT_scalar(self):
     def test_NaT_cast(self):
         # GH10747
         result = Series([np.nan]).astype("M8[ns]")
-        expected = Series([NaT])
+        expected = Series([NaT], dtype="M8[ns]")
         tm.assert_series_equal(result, expected)
 
     def test_constructor_name_hashable(self):