BUG: isin incorrectly casting ints to datetimes

asv_bench/benchmarks/series_methods.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 
-from pandas import NaT, Series, date_range
+from pandas import Categorical, NaT, Series, date_range
 
 from .pandas_vb_common import tm
 
@@ -36,6 +36,28 @@ def time_isin(self, dtypes):
         self.s.isin(self.values)
 
 
+class IsInDatetime64:
+    def setup(self):
+        dti = date_range(
+            start=datetime(2015, 10, 26), end=datetime(2016, 1, 1), freq="50s"
+        )
+        self.ser = Series(dti)
+        self.subset = self.ser._values[::3]
+        self.cat_subset = Categorical(self.subset)
+
+    def time_isin(self):
+        self.ser.isin(self.subset)
+
+    def time_isin_cat_values(self):
+        self.ser.isin(self.cat_subset)
+
+    def time_isin_mismatched_dtype(self):
+        self.ser.isin([1, 2])
+
+    def time_isin_empty(self):
+        self.ser.isin([])
+
+
 class IsInFloat64:
     def setup(self):
         self.small = Series([1, 2], dtype=np.float64)

doc/source/whatsnew/v1.2.0.rst

@@ -538,6 +538,9 @@ Datetimelike
 - Bug in :meth:`DatetimeArray.shift` incorrectly allowing ``fill_value`` with a mismatched timezone (:issue:`37299`)
 - Bug in adding a :class:`BusinessDay` with nonzero ``offset`` to a non-scalar other (:issue:`37457`)
 - Bug in :func:`to_datetime` with a read-only array incorrectly raising (:issue:`34857`)
+- Bug in :meth:`Series.isin` with ``datetime64[ns]`` dtype and :meth:`DatetimeIndex.isin` incorrectly casting integers to datetimes (:issue:`36621`)
+- Bug in :meth:`Series.isin` with ``datetime64[ns]`` dtype and :meth:`DatetimeIndex.isin` failing to consider timezone-aware and timezone-naive datetimes as always different (:issue:`35728`)
+- Bug in :meth:`Series.isin` with ``PeriodDtype`` dtype and :meth:`PeriodIndex.isin` failing to consider arguments with different ``PeriodDtype`` as always different (:issue:`37528`)
 
 Timedelta
 ^^^^^^^^^

pandas/core/algorithms.py

@@ -430,6 +430,12 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
         # handle categoricals
         return cast("Categorical", comps).isin(values)
 
+    if needs_i8_conversion(comps):
+        # Dispatch to DatetimeLikeIndexMixin.isin
+        from pandas import Index
+
+        return Index(comps).isin(values)
+
     comps, dtype = _ensure_data(comps)
     values, _ = _ensure_data(values, dtype=dtype)
 

pandas/core/indexes/datetimelike.py

@@ -491,12 +491,40 @@ def isin(self, values, level=None):
         if level is not None:
             self._validate_index_level(level)
 
+        if not hasattr(values, "dtype"):
+            values = np.asarray(values)
+
+        if values.dtype.kind in ["f", "i", "u", "c"]:
+            # TODO: de-duplicate with equals, validate_comparison_value
+            return np.zeros(self.shape, dtype=bool)
+
         if not isinstance(values, type(self)):
+            inferrable = [
+                "timedelta",
+                "timedelta64",
+                "datetime",
+                "datetime64",
+                "date",
+                "period",
+            ]
+            if values.dtype == object:
+                inferred = lib.infer_dtype(values, skipna=False)
+                if inferred not in inferrable:
+                    if "mixed" in inferred:
+                        return self.astype(object).isin(values)
+                    return np.zeros(self.shape, dtype=bool)
+
             try:
                 values = type(self)(values)
             except ValueError:
                 return self.astype(object).isin(values)
 
+        try:
+            self._data._check_compatible_with(values)
+        except (TypeError, ValueError):
+            # Includes tzawareness mismatch and IncompatibleFrequencyError
+            return np.zeros(self.shape, dtype=bool)
+
         return algorithms.isin(self.asi8, values.asi8)
 
     @Appender(Index.where.__doc__)

pandas/tests/series/methods/test_isin.py

@@ -4,6 +4,7 @@
 import pandas as pd
 from pandas import Series, date_range
 import pandas._testing as tm
+from pandas.core.arrays import PeriodArray
 
 
 class TestSeriesIsIn:
@@ -90,6 +91,60 @@ def test_isin_read_only(self):
         expected = Series([True, True, True])
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.parametrize("dtype", [object, None])
+    def test_isin_dt64_values_vs_ints(self, dtype):
+        # GH#36621 dont cast integers to datetimes for isin
+        dti = date_range("2013-01-01", "2013-01-05")
+        ser = Series(dti)
+
+        comps = np.asarray([1356998400000000000], dtype=dtype)
+
+        res = dti.isin(comps)
+        expected = np.array([False] * len(dti), dtype=bool)
+        tm.assert_numpy_array_equal(res, expected)
+
+        res = ser.isin(comps)
+        tm.assert_series_equal(res, Series(expected))
+
+        res = pd.core.algorithms.isin(ser, comps)
+        tm.assert_numpy_array_equal(res, expected)
+
+    def test_isin_tzawareness_mismatch(self):
+        dti = date_range("2013-01-01", "2013-01-05")
+        ser = Series(dti)
+
+        other = dti.tz_localize("UTC")
+
+        res = dti.isin(other)
+        expected = np.array([False] * len(dti), dtype=bool)
+        tm.assert_numpy_array_equal(res, expected)
+
+        res = ser.isin(other)
+        tm.assert_series_equal(res, Series(expected))
+
+        res = pd.core.algorithms.isin(ser, other)
+        tm.assert_numpy_array_equal(res, expected)
+
+    def test_isin_period_freq_mismatch(self):
+        dti = date_range("2013-01-01", "2013-01-05")
+        pi = dti.to_period("M")
+        ser = Series(pi)
+
+        # We construct another PeriodIndex with the same i8 values
+        #  but different dtype
+        dtype = dti.to_period("Y").dtype
+        other = PeriodArray._simple_new(pi.asi8, dtype=dtype)
+
+        res = pi.isin(other)
+        expected = np.array([False] * len(pi), dtype=bool)
+        tm.assert_numpy_array_equal(res, expected)
+
+        res = ser.isin(other)
+        tm.assert_series_equal(res, Series(expected))
+
+        res = pd.core.algorithms.isin(ser, other)
+        tm.assert_numpy_array_equal(res, expected)
+
 
 @pytest.mark.slow
 def test_isin_large_series_mixed_dtypes_and_nan():