API: dont infer freq in DTA/TDA arithmetic ops (#33487)

Author: jbrockmendel

pandas/core/arrays/datetimelike.py

@@ -1176,10 +1176,7 @@ def _add_timedeltalike_scalar(self, other):
             # adding a scalar preserves freq
             new_freq = self.freq
 
-        if new_freq is not None:
-            # fastpath that doesnt require inference
-            return type(self)(new_values, dtype=self.dtype, freq=new_freq)
-        return type(self)(new_values, dtype=self.dtype)._with_freq("infer")
+        return type(self)(new_values, dtype=self.dtype, freq=new_freq)
 
     def _add_timedelta_arraylike(self, other):
         """
@@ -1209,7 +1206,7 @@ def _add_timedelta_arraylike(self, other):
             mask = (self._isnan) | (other._isnan)
             new_values[mask] = iNaT
 
-        return type(self)(new_values, dtype=self.dtype)._with_freq("infer")
+        return type(self)(new_values, dtype=self.dtype)
 
     def _add_nat(self):
         """

pandas/core/arrays/datetimes.py

@@ -698,7 +698,7 @@ def _add_offset(self, offset):
                 # GH#30336 _from_sequence won't be able to infer self.tz
                 return type(self)._from_sequence(result).tz_localize(self.tz)
 
-        return type(self)._from_sequence(result)._with_freq("infer")
+        return type(self)._from_sequence(result)
 
     def _sub_datetimelike_scalar(self, other):
         # subtract a datetime from myself, yielding a ndarray[timedelta64[ns]]

pandas/core/indexes/datetimelike.py

@@ -625,6 +625,11 @@ def _set_freq(self, freq):
         # GH#29843
         self._data._with_freq(freq)
 
+    def _with_freq(self, freq):
+        index = self.copy(deep=False)
+        index._set_freq(freq)
+        return index
+
     def _shallow_copy(self, values=None, name: Label = lib.no_default):
         name = self.name if name is lib.no_default else name
         cache = self._cache.copy() if values is None else {}

pandas/core/indexes/timedeltas.py

@@ -48,7 +48,6 @@
         "std",
         "median",
         "_format_native_types",
-        "freq",
     ],
     TimedeltaArray,
 )

pandas/tests/arithmetic/test_datetime64.py

@@ -865,7 +865,7 @@ def test_dt64arr_add_sub_td64ndarray(self, tz_naive_fixture, box_with_array):
         tdi = pd.TimedeltaIndex(["-1 Day", "-1 Day", "-1 Day"])
         tdarr = tdi.values
 
-        expected = pd.date_range("2015-12-31", periods=3, tz=tz)
+        expected = pd.date_range("2015-12-31", "2016-01-02", periods=3, tz=tz)
 
         dtarr = tm.box_expected(dti, box_with_array)
         expected = tm.box_expected(expected, box_with_array)
@@ -875,7 +875,7 @@ def test_dt64arr_add_sub_td64ndarray(self, tz_naive_fixture, box_with_array):
         result = tdarr + dtarr
         tm.assert_equal(result, expected)
 
-        expected = pd.date_range("2016-01-02", periods=3, tz=tz)
+        expected = pd.date_range("2016-01-02", "2016-01-04", periods=3, tz=tz)
         expected = tm.box_expected(expected, box_with_array)
 
         result = dtarr - tdarr
@@ -1385,13 +1385,13 @@ def test_dt64arr_add_sub_DateOffset(self, box_with_array):
         s = tm.box_expected(s, box_with_array)
         result = s + pd.DateOffset(years=1)
         result2 = pd.DateOffset(years=1) + s
-        exp = date_range("2001-01-01", "2001-01-31", name="a")
+        exp = date_range("2001-01-01", "2001-01-31", name="a")._with_freq(None)
         exp = tm.box_expected(exp, box_with_array)
         tm.assert_equal(result, exp)
         tm.assert_equal(result2, exp)
 
         result = s - pd.DateOffset(years=1)
-        exp = date_range("1999-01-01", "1999-01-31", name="a")
+        exp = date_range("1999-01-01", "1999-01-31", name="a")._with_freq(None)
         exp = tm.box_expected(exp, box_with_array)
         tm.assert_equal(result, exp)
 
@@ -1553,7 +1553,7 @@ def test_dti_add_sub_nonzero_mth_offset(
         mth = getattr(date, op)
         result = mth(offset)
 
-        expected = pd.DatetimeIndex(exp, tz=tz, freq=exp_freq)
+        expected = pd.DatetimeIndex(exp, tz=tz)
         expected = tm.box_expected(expected, box_with_array, False)
         tm.assert_equal(result, expected)
 
@@ -2344,29 +2344,29 @@ def test_ufunc_coercions(self):
             assert result.freq == "2D"
 
         exp = date_range("2010-12-31", periods=3, freq="2D", name="x")
+
         for result in [idx - delta, np.subtract(idx, delta)]:
             assert isinstance(result, DatetimeIndex)
             tm.assert_index_equal(result, exp)
             assert result.freq == "2D"
 
+        # When adding/subtracting an ndarray (which has no .freq), the result
+        #  does not infer freq
+        idx = idx._with_freq(None)
         delta = np.array(
             [np.timedelta64(1, "D"), np.timedelta64(2, "D"), np.timedelta64(3, "D")]
         )
-        exp = DatetimeIndex(
-            ["2011-01-02", "2011-01-05", "2011-01-08"], freq="3D", name="x"
-        )
+        exp = DatetimeIndex(["2011-01-02", "2011-01-05", "2011-01-08"], name="x")
+
         for result in [idx + delta, np.add(idx, delta)]:
-            assert isinstance(result, DatetimeIndex)
             tm.assert_index_equal(result, exp)
-            assert result.freq == "3D"
+            assert result.freq == exp.freq
 
-        exp = DatetimeIndex(
-            ["2010-12-31", "2011-01-01", "2011-01-02"], freq="D", name="x"
-        )
+        exp = DatetimeIndex(["2010-12-31", "2011-01-01", "2011-01-02"], name="x")
         for result in [idx - delta, np.subtract(idx, delta)]:
             assert isinstance(result, DatetimeIndex)
             tm.assert_index_equal(result, exp)
-            assert result.freq == "D"
+            assert result.freq == exp.freq
 
     @pytest.mark.parametrize(
         "names", [("foo", None, None), ("baz", "bar", None), ("bar", "bar", "bar")]

pandas/tests/arithmetic/test_timedelta64.py

@@ -491,6 +491,7 @@ def test_timedelta(self, freq):
 
         shifted = index + timedelta(1)
         back = shifted + timedelta(-1)
+        back = back._with_freq("infer")
         tm.assert_index_equal(index, back)
 
         if freq == "D":

pandas/tests/indexes/timedeltas/test_shift.py

@@ -38,7 +38,8 @@ def test_tdi_shift_minutes(self):
 
     def test_tdi_shift_int(self):
         # GH#8083
-        trange = pd.to_timedelta(range(5), unit="d") + pd.offsets.Hour(1)
+        tdi = pd.to_timedelta(range(5), unit="d")
+        trange = tdi._with_freq("infer") + pd.offsets.Hour(1)
         result = trange.shift(1)
         expected = TimedeltaIndex(
             [
@@ -54,7 +55,8 @@ def test_tdi_shift_int(self):
 
     def test_tdi_shift_nonstandard_freq(self):
         # GH#8083
-        trange = pd.to_timedelta(range(5), unit="d") + pd.offsets.Hour(1)
+        tdi = pd.to_timedelta(range(5), unit="d")
+        trange = tdi._with_freq("infer") + pd.offsets.Hour(1)
         result = trange.shift(3, freq="2D 1s")
         expected = TimedeltaIndex(
             [

pandas/tests/indexes/timedeltas/test_timedelta.py

@@ -30,7 +30,9 @@ def indices(self):
         return tm.makeTimedeltaIndex(10)
 
     def create_index(self) -> TimedeltaIndex:
-        return pd.to_timedelta(range(5), unit="d") + pd.offsets.Hour(1)
+        index = pd.to_timedelta(range(5), unit="d")._with_freq("infer")
+        assert index.freq == "D"
+        return index + pd.offsets.Hour(1)
 
     def test_numeric_compat(self):
         # Dummy method to override super's version; this test is now done