Masking and overflow checks for datetimeindex and timedeltaindex ops (pandas-dev#18020)

closes pandas-dev#17991

Author: jbrockmendel

doc/source/whatsnew/v0.21.1.txt

@@ -57,6 +57,8 @@ Documentation Changes
 Bug Fixes
 ~~~~~~~~~
 - Bug in ``DataFrame.resample(...).apply(...)`` when there is a callable that returns different columns (:issue:`15169`)
+- Bug in :class:`TimedeltaIndex` subtraction could incorrectly overflow when ``NaT`` is present (:issue:`17791`)
+- Bug in :class:`DatetimeIndex` subtracting datetimelike from DatetimeIndex could fail to overflow (:issue:`18020`)
 
 Conversion
 ^^^^^^^^^^

pandas/core/indexes/datetimelike.py

@@ -679,7 +679,7 @@ def __sub__(self, other):
                 return self._add_delta(-other)
             elif is_integer(other):
                 return self.shift(-other)
-            elif isinstance(other, datetime):
+            elif isinstance(other, (datetime, np.datetime64)):
                 return self._sub_datelike(other)
             elif isinstance(other, Period):
                 return self._sub_period(other)

pandas/core/indexes/datetimes.py

@@ -29,6 +29,7 @@
 import pandas.core.dtypes.concat as _concat
 from pandas.errors import PerformanceWarning
 from pandas.core.common import _values_from_object, _maybe_box
+from pandas.core.algorithms import checked_add_with_arr
 
 from pandas.core.indexes.base import Index, _index_shared_docs
 from pandas.core.indexes.numeric import Int64Index, Float64Index
@@ -767,7 +768,7 @@ def _sub_datelike(self, other):
                 raise TypeError("DatetimeIndex subtraction must have the same "
                                 "timezones or no timezones")
             result = self._sub_datelike_dti(other)
-        elif isinstance(other, datetime):
+        elif isinstance(other, (datetime, np.datetime64)):
             other = Timestamp(other)
             if other is libts.NaT:
                 result = self._nat_new(box=False)
@@ -777,7 +778,8 @@ def _sub_datelike(self, other):
                                 "timezones or no timezones")
             else:
                 i8 = self.asi8
-                result = i8 - other.value
+                result = checked_add_with_arr(i8, -other.value,
+                                              arr_mask=self._isnan)
                 result = self._maybe_mask_results(result,
                                                   fill_value=libts.iNaT)
         else:

pandas/core/indexes/timedeltas.py

@@ -361,7 +361,8 @@ def _add_datelike(self, other):
         else:
             other = Timestamp(other)
             i8 = self.asi8
-            result = checked_add_with_arr(i8, other.value)
+            result = checked_add_with_arr(i8, other.value,
+                                          arr_mask=self._isnan)
             result = self._maybe_mask_results(result, fill_value=iNaT)
         return DatetimeIndex(result, name=self.name, copy=False)
 

pandas/tests/indexes/datetimes/test_arithmetic.py

@@ -199,6 +199,40 @@ def test_ufunc_coercions(self):
             tm.assert_index_equal(result, exp)
             assert result.freq == 'D'
 
+    def test_datetimeindex_sub_timestamp_overflow(self):
+        dtimax = pd.to_datetime(['now', pd.Timestamp.max])
+        dtimin = pd.to_datetime(['now', pd.Timestamp.min])
+
+        tsneg = Timestamp('1950-01-01')
+        ts_neg_variants = [tsneg,
+                           tsneg.to_pydatetime(),
+                           tsneg.to_datetime64().astype('datetime64[ns]'),
+                           tsneg.to_datetime64().astype('datetime64[D]')]
+
+        tspos = Timestamp('1980-01-01')
+        ts_pos_variants = [tspos,
+                           tspos.to_pydatetime(),
+                           tspos.to_datetime64().astype('datetime64[ns]'),
+                           tspos.to_datetime64().astype('datetime64[D]')]
+
+        for variant in ts_neg_variants:
+            with pytest.raises(OverflowError):
+                dtimax - variant
+
+        expected = pd.Timestamp.max.value - tspos.value
+        for variant in ts_pos_variants:
+            res = dtimax - variant
+            assert res[1].value == expected
+
+        expected = pd.Timestamp.min.value - tsneg.value
+        for variant in ts_neg_variants:
+            res = dtimin - variant
+            assert res[1].value == expected
+
+        for variant in ts_pos_variants:
+            with pytest.raises(OverflowError):
+                dtimin - variant
+
 
 # GH 10699
 @pytest.mark.parametrize('klass,assert_func', zip([Series, DatetimeIndex],

pandas/tests/indexes/timedeltas/test_arithmetic.py

@@ -576,6 +576,26 @@ def test_add_overflow(self):
                   to_timedelta(['7 seconds', pd.NaT, '4 hours']))
         tm.assert_index_equal(result, exp)
 
+    def test_timedeltaindex_add_timestamp_nat_masking(self):
+        # GH17991 checking for overflow-masking with NaT
+        tdinat = pd.to_timedelta(['24658 days 11:15:00', 'NaT'])
+
+        tsneg = Timestamp('1950-01-01')
+        ts_neg_variants = [tsneg,
+                           tsneg.to_pydatetime(),
+                           tsneg.to_datetime64().astype('datetime64[ns]'),
+                           tsneg.to_datetime64().astype('datetime64[D]')]
+
+        tspos = Timestamp('1980-01-01')
+        ts_pos_variants = [tspos,
+                           tspos.to_pydatetime(),
+                           tspos.to_datetime64().astype('datetime64[ns]'),
+                           tspos.to_datetime64().astype('datetime64[D]')]
+
+        for variant in ts_neg_variants + ts_pos_variants:
+            res = tdinat + variant
+            assert res[1] is pd.NaT
+
     def test_tdi_ops_attributes(self):
         rng = timedelta_range('2 days', periods=5, freq='2D', name='x')