TST: check freq on series.index in assert_series_equal (pandas-dev#33815)

Author: jbrockmendel

pandas/_testing.py

@@ -1171,6 +1171,10 @@ def assert_series_equal(
         check_categorical=check_categorical,
         obj=f"{obj}.index",
     )
+    if isinstance(left.index, (pd.DatetimeIndex, pd.TimedeltaIndex)):
+        lidx = left.index
+        ridx = right.index
+        assert lidx.freq == ridx.freq, (lidx.freq, ridx.freq)
 
     if check_dtype:
         # We want to skip exact dtype checking when `check_categorical`

pandas/tests/arithmetic/test_numeric.py

@@ -919,6 +919,8 @@ def _check_op(series, other, op, pos_only=False):
 
             cython_or_numpy = op(left, right)
             python = left.combine(right, op)
+            if isinstance(other, Series) and not other.index.equals(series.index):
+                python.index = python.index._with_freq(None)
             tm.assert_series_equal(cython_or_numpy, python)
 
         def check(series, other):

pandas/tests/frame/methods/test_at_time.py

@@ -83,4 +83,8 @@ def test_at_time_axis(self, axis):
             expected = ts.loc[:, indices]
 
         result = ts.at_time("9:30", axis=axis)
+
+        # Without clearing freq, result has freq 1440T and expected 5T
+        result.index = result.index._with_freq(None)
+        expected.index = expected.index._with_freq(None)
         tm.assert_frame_equal(result, expected)

pandas/tests/frame/methods/test_shift.py

@@ -177,8 +177,12 @@ def test_tshift(self, datetime_frame):
             columns=datetime_frame.columns,
         )
         shifted = inferred_ts.tshift(1)
+
+        expected = datetime_frame.tshift(1)
+        expected.index = expected.index._with_freq(None)
+        tm.assert_frame_equal(shifted, expected)
+
         unshifted = shifted.tshift(-1)
-        tm.assert_frame_equal(shifted, datetime_frame.tshift(1))
         tm.assert_frame_equal(unshifted, inferred_ts)
 
         no_freq = datetime_frame.iloc[[0, 5, 7], :]

pandas/tests/groupby/test_timegrouper.py

@@ -747,6 +747,7 @@ def test_nunique_with_timegrouper_and_nat(self):
         grouper = pd.Grouper(key="time", freq="h")
         result = test.groupby(grouper)["data"].nunique()
         expected = test[test.time.notnull()].groupby(grouper)["data"].nunique()
+        expected.index = expected.index._with_freq(None)
         tm.assert_series_equal(result, expected)
 
     def test_scalar_call_versus_list_call(self):

pandas/tests/indexes/timedeltas/test_ops.py

@@ -18,10 +18,14 @@ def test_value_counts_unique(self):
         idx = TimedeltaIndex(np.repeat(idx.values, range(1, len(idx) + 1)))
 
         exp_idx = timedelta_range("1 days 18:00:00", freq="-1H", periods=10)
+        exp_idx = exp_idx._with_freq(None)
         expected = Series(range(10, 0, -1), index=exp_idx, dtype="int64")
 
-        for obj in [idx, Series(idx)]:
-            tm.assert_series_equal(obj.value_counts(), expected)
+        obj = idx
+        tm.assert_series_equal(obj.value_counts(), expected)
+
+        obj = Series(idx)
+        tm.assert_series_equal(obj.value_counts(), expected)
 
         expected = timedelta_range("1 days 09:00:00", freq="H", periods=10)
         tm.assert_index_equal(idx.unique(), expected)

pandas/tests/indexing/test_datetime.py

@@ -146,7 +146,7 @@ def test_indexing_with_datetimeindex_tz(self):
         for sel in (index, list(index)):
             # getitem
             result = ser[sel]
-            expected = ser
+            expected = ser.copy()
             if sel is not index:
                 expected.index = expected.index._with_freq(None)
             tm.assert_series_equal(result, expected)
@@ -159,7 +159,10 @@ def test_indexing_with_datetimeindex_tz(self):
 
             # .loc getitem
             result = ser.loc[sel]
-            tm.assert_series_equal(result, ser)
+            expected = ser.copy()
+            if sel is not index:
+                expected.index = expected.index._with_freq(None)
+            tm.assert_series_equal(result, expected)
 
             # .loc setitem
             result = ser.copy()

pandas/tests/resample/test_datetime_index.py

@@ -6,6 +6,7 @@
 import pytest
 import pytz
 
+from pandas._libs import lib
 from pandas.errors import UnsupportedFunctionCall
 
 import pandas as pd
@@ -62,6 +63,7 @@ def test_custom_grouper(index):
     arr = [1] + [5] * 2592
     idx = dti[0:-1:5]
     idx = idx.append(dti[-1:])
+    idx = pd.DatetimeIndex(idx, freq="5T")
     expect = Series(arr, index=idx)
 
     # GH2763 - return in put dtype if we can
@@ -502,15 +504,18 @@ def test_resample_how_method():
     )
     expected = Series(
         [11, np.NaN, np.NaN, np.NaN, np.NaN, np.NaN, 22],
-        index=[
-            Timestamp("2015-03-31 21:48:50"),
-            Timestamp("2015-03-31 21:49:00"),
-            Timestamp("2015-03-31 21:49:10"),
-            Timestamp("2015-03-31 21:49:20"),
-            Timestamp("2015-03-31 21:49:30"),
-            Timestamp("2015-03-31 21:49:40"),
-            Timestamp("2015-03-31 21:49:50"),
-        ],
+        index=pd.DatetimeIndex(
+            [
+                Timestamp("2015-03-31 21:48:50"),
+                Timestamp("2015-03-31 21:49:00"),
+                Timestamp("2015-03-31 21:49:10"),
+                Timestamp("2015-03-31 21:49:20"),
+                Timestamp("2015-03-31 21:49:30"),
+                Timestamp("2015-03-31 21:49:40"),
+                Timestamp("2015-03-31 21:49:50"),
+            ],
+            freq="10s",
+        ),
     )
     tm.assert_series_equal(s.resample("10S").mean(), expected)
 
@@ -778,7 +783,7 @@ def test_resample_single_group():
         [30.1, 31.6],
         index=[Timestamp("20070915 15:30:00"), Timestamp("20070915 15:40:00")],
     )
-    expected = Series([0.75], index=[Timestamp("20070915")])
+    expected = Series([0.75], index=pd.DatetimeIndex([Timestamp("20070915")], freq="D"))
     result = s.resample("D").apply(lambda x: np.std(x))
     tm.assert_series_equal(result, expected)
 
@@ -801,7 +806,9 @@ def test_resample_float_base():
 
     base = 17 + 43.51 / 60
     result = s.resample("3min", base=base).size()
-    expected = Series(3, index=pd.DatetimeIndex(["2018-11-26 16:17:43.51"]))
+    expected = Series(
+        3, index=pd.DatetimeIndex(["2018-11-26 16:17:43.51"], freq="3min")
+    )
     tm.assert_series_equal(result, expected)
 
 
@@ -938,13 +945,17 @@ def test_resample_anchored_intraday(simple_date_range_series):
     result = df.resample("M").mean()
     expected = df.resample("M", kind="period").mean().to_timestamp(how="end")
     expected.index += Timedelta(1, "ns") - Timedelta(1, "D")
+    expected.index = expected.index._with_freq("infer")
+    assert expected.index.freq == "M"
     tm.assert_frame_equal(result, expected)
 
     result = df.resample("M", closed="left").mean()
     exp = df.tshift(1, freq="D").resample("M", kind="period").mean()
     exp = exp.to_timestamp(how="end")
 
     exp.index = exp.index + Timedelta(1, "ns") - Timedelta(1, "D")
+    exp.index = exp.index._with_freq("infer")
+    assert exp.index.freq == "M"
     tm.assert_frame_equal(result, exp)
 
     rng = date_range("1/1/2012", "4/1/2012", freq="100min")
@@ -953,12 +964,16 @@ def test_resample_anchored_intraday(simple_date_range_series):
     result = df.resample("Q").mean()
     expected = df.resample("Q", kind="period").mean().to_timestamp(how="end")
     expected.index += Timedelta(1, "ns") - Timedelta(1, "D")
+    expected.index._data.freq = "Q"
+    expected.index._freq = lib.no_default
     tm.assert_frame_equal(result, expected)
 
     result = df.resample("Q", closed="left").mean()
     expected = df.tshift(1, freq="D").resample("Q", kind="period", closed="left").mean()
     expected = expected.to_timestamp(how="end")
     expected.index += Timedelta(1, "ns") - Timedelta(1, "D")
+    expected.index._data.freq = "Q"
+    expected.index._freq = lib.no_default
     tm.assert_frame_equal(result, expected)
 
     ts = simple_date_range_series("2012-04-29 23:00", "2012-04-30 5:00", freq="h")
@@ -1151,6 +1166,8 @@ def test_resample_timegrouper():
             name="A",
         )
         expected = DataFrame({"B": [1, 0, 2, 2, 1]}, index=exp_idx)
+        if df["A"].isna().any():
+            expected.index = expected.index._with_freq(None)
         tm.assert_frame_equal(result, expected)
 
         result = df.groupby(pd.Grouper(freq="M", key="A")).count()
@@ -1163,6 +1180,8 @@ def test_resample_timegrouper():
             index=exp_idx,
             columns=["B", "C"],
         )
+        if df["A"].isna().any():
+            expected.index = expected.index._with_freq(None)
         tm.assert_frame_equal(result, expected)
 
         result = df.groupby(pd.Grouper(freq="M", key="A")).count()
@@ -1291,7 +1310,8 @@ def test_resample_across_dst():
     dti2 = DatetimeIndex(
         pd.to_datetime(df2.ts, unit="s")
         .dt.tz_localize("UTC")
-        .dt.tz_convert("Europe/Madrid")
+        .dt.tz_convert("Europe/Madrid"),
+        freq="H",
     )
     df = DataFrame([5, 5], index=dti1)
 
@@ -1322,13 +1342,17 @@ def test_resample_dst_anchor():
     # 5172
     dti = DatetimeIndex([datetime(2012, 11, 4, 23)], tz="US/Eastern")
     df = DataFrame([5], index=dti)
-    tm.assert_frame_equal(
-        df.resample(rule="D").sum(), DataFrame([5], index=df.index.normalize())
-    )
+
+    dti = DatetimeIndex(df.index.normalize(), freq="D")
+    expected = DataFrame([5], index=dti)
+    tm.assert_frame_equal(df.resample(rule="D").sum(), expected)
     df.resample(rule="MS").sum()
     tm.assert_frame_equal(
         df.resample(rule="MS").sum(),
-        DataFrame([5], index=DatetimeIndex([datetime(2012, 11, 1)], tz="US/Eastern")),
+        DataFrame(
+            [5],
+            index=DatetimeIndex([datetime(2012, 11, 1)], tz="US/Eastern", freq="MS"),
+        ),
     )
 
     dti = date_range("2013-09-30", "2013-11-02", freq="30Min", tz="Europe/Paris")
@@ -1424,7 +1448,9 @@ def test_downsample_across_dst_weekly():
     result = df.resample("1W").sum()
     expected = DataFrame(
         [23, 42],
-        index=pd.DatetimeIndex(["2017-03-26", "2017-04-02"], tz="Europe/Amsterdam"),
+        index=pd.DatetimeIndex(
+            ["2017-03-26", "2017-04-02"], tz="Europe/Amsterdam", freq="W"
+        ),
     )
     tm.assert_frame_equal(result, expected)
 
@@ -1447,12 +1473,12 @@ def test_downsample_dst_at_midnight():
     data = list(range(len(index)))
     dataframe = pd.DataFrame(data, index=index)
     result = dataframe.groupby(pd.Grouper(freq="1D")).mean()
-    expected = DataFrame(
-        [7.5, 28.0, 44.5],
-        index=date_range("2018-11-03", periods=3).tz_localize(
-            "America/Havana", ambiguous=True
-        ),
+
+    dti = date_range("2018-11-03", periods=3).tz_localize(
+        "America/Havana", ambiguous=True
     )
+    dti = pd.DatetimeIndex(dti, freq="D")
+    expected = DataFrame([7.5, 28.0, 44.5], index=dti,)
     tm.assert_frame_equal(result, expected)
 
 

pandas/tests/resample/test_period_index.py

@@ -270,7 +270,10 @@ def test_resample_with_pytz(self):
         )
         result = s.resample("D").mean()
         expected = Series(
-            2, index=pd.DatetimeIndex(["2017-01-01", "2017-01-02"], tz="US/Eastern")
+            2,
+            index=pd.DatetimeIndex(
+                ["2017-01-01", "2017-01-02"], tz="US/Eastern", freq="D"
+            ),
         )
         tm.assert_series_equal(result, expected)
         # Especially assert that the timezone is LMT for pytz
@@ -308,6 +311,7 @@ def test_resample_nonexistent_time_bin_edge(self):
         index = date_range("2017-03-12", "2017-03-12 1:45:00", freq="15T")
         s = Series(np.zeros(len(index)), index=index)
         expected = s.tz_localize("US/Pacific")
+        expected.index = pd.DatetimeIndex(expected.index, freq="900S")
         result = expected.resample("900S").mean()
         tm.assert_series_equal(result, expected)
 
@@ -471,6 +475,7 @@ def test_resample_tz_localized(self):
         ]
 
         exp = ts_local_naive.resample("W").mean().tz_localize("America/Los_Angeles")
+        exp.index = pd.DatetimeIndex(exp.index, freq="W")
 
         tm.assert_series_equal(result, exp)
 
@@ -582,6 +587,7 @@ def test_resample_with_dst_time_change(self):
         index = pd.to_datetime(expected_index_values, utc=True).tz_convert(
             "America/Chicago"
         )
+        index = pd.DatetimeIndex(index, freq="12h")
         expected = pd.DataFrame(
             [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 2.0],
             index=index,
@@ -650,7 +656,9 @@ def test_evenly_divisible_with_no_extra_bins(self):
         df = DataFrame(np.random.randn(9, 3), index=date_range("2000-1-1", periods=9))
         result = df.resample("5D").mean()
         expected = pd.concat([df.iloc[0:5].mean(), df.iloc[5:].mean()], axis=1).T
-        expected.index = [Timestamp("2000-1-1"), Timestamp("2000-1-6")]
+        expected.index = pd.DatetimeIndex(
+            [Timestamp("2000-1-1"), Timestamp("2000-1-6")], freq="5D"
+        )
         tm.assert_frame_equal(result, expected)
 
         index = date_range(start="2001-5-4", periods=28)
@@ -836,6 +844,9 @@ def test_resample_with_non_zero_base(self, start, end, start_freq, end_freq, bas
         # to_timestamp casts 24H -> D
         result = result.asfreq(end_freq) if end_freq == "24H" else result
         expected = s.to_timestamp().resample(end_freq, base=base).mean()
+        if end_freq == "M":
+            # TODO: is non-tick the relevant characteristic?
+            expected.index = expected.index._with_freq(None)
         tm.assert_series_equal(result, expected)
 
     @pytest.mark.parametrize(

pandas/tests/resample/test_time_grouper.py

@@ -170,7 +170,7 @@ def test_resample_entirly_nat_window(method, method_args, unit):
     s = pd.Series([0] * 2 + [np.nan] * 2, index=pd.date_range("2017", periods=4))
     result = methodcaller(method, **method_args)(s.resample("2d"))
     expected = pd.Series(
-        [0.0, unit], index=pd.to_datetime(["2017-01-01", "2017-01-03"])
+        [0.0, unit], index=pd.DatetimeIndex(["2017-01-01", "2017-01-03"], freq="2D")
     )
     tm.assert_series_equal(result, expected)
 
@@ -207,7 +207,8 @@ def test_aggregate_with_nat(func, fill_value):
     pad = DataFrame([[fill_value] * 4], index=[3], columns=["A", "B", "C", "D"])
     expected = normal_result.append(pad)
     expected = expected.sort_index()
-    expected.index = date_range(start="2013-01-01", freq="D", periods=5, name="key")
+    dti = date_range(start="2013-01-01", freq="D", periods=5, name="key")
+    expected.index = dti._with_freq(None)  # TODO: is this desired?
     tm.assert_frame_equal(expected, dt_result)
     assert dt_result.index.name == "key"
 
@@ -237,7 +238,9 @@ def test_aggregate_with_nat_size():
     pad = Series([0], index=[3])
     expected = normal_result.append(pad)
     expected = expected.sort_index()
-    expected.index = date_range(start="2013-01-01", freq="D", periods=5, name="key")
+    expected.index = date_range(
+        start="2013-01-01", freq="D", periods=5, name="key"
+    )._with_freq(None)
     tm.assert_series_equal(expected, dt_result)
     assert dt_result.index.name == "key"
 
@@ -269,8 +272,9 @@ def test_repr():
 def test_upsample_sum(method, method_args, expected_values):
     s = pd.Series(1, index=pd.date_range("2017", periods=2, freq="H"))
     resampled = s.resample("30T")
-    index = pd.to_datetime(
-        ["2017-01-01T00:00:00", "2017-01-01T00:30:00", "2017-01-01T01:00:00"]
+    index = pd.DatetimeIndex(
+        ["2017-01-01T00:00:00", "2017-01-01T00:30:00", "2017-01-01T01:00:00"],
+        freq="30T",
     )
     result = methodcaller(method, **method_args)(resampled)
     expected = pd.Series(expected_values, index=index)

pandas/tests/resample/test_timedelta.py

@@ -102,7 +102,7 @@ def test_resample_categorical_data_with_timedeltaindex():
     result = df.resample("10s").agg(lambda x: (x.value_counts().index[0]))
     expected = DataFrame(
         {"Group_obj": ["A", "A"], "Group": ["A", "A"]},
-        index=pd.to_timedelta([0, 10], unit="s"),
+        index=pd.TimedeltaIndex([0, 10], unit="s", freq="10s"),
     )
     expected = expected.reindex(["Group_obj", "Group"], axis=1)
     expected["Group"] = expected["Group_obj"]