PERF: GH2003 Series.isin for categorical dtypes

doc/source/whatsnew/v0.23.0.txt

@@ -345,6 +345,7 @@ Other Enhancements
   ``SQLAlchemy`` dialects supporting multivalue inserts include: ``mysql``, ``postgresql``, ``sqlite`` and any dialect with ``supports_multivalues_insert``. (:issue:`14315`, :issue:`8953`)
 - :func:`read_html` now accepts a ``displayed_only`` keyword argument to controls whether or not hidden elements are parsed (``True`` by default) (:issue:`20027`)
 - zip compression is supported via ``compression=zip`` in :func:`DataFrame.to_pickle`, :func:`Series.to_pickle`, :func:`DataFrame.to_csv`, :func:`Series.to_csv`, :func:`DataFrame.to_json`, :func:`Series.to_json`. (:issue:`17778`)
+- Performance enhancement for :func:`Series.isin` in the case of categorical dtypes (:issue:`20003`)
 
 .. _whatsnew_0230.api_breaking:
 

pandas/core/algorithms.py

@@ -403,8 +403,15 @@ def isin(comps, values):
     if not isinstance(values, (ABCIndex, ABCSeries, np.ndarray)):
         values = construct_1d_object_array_from_listlike(list(values))
 
-    comps, dtype, _ = _ensure_data(comps)
-    values, _, _ = _ensure_data(values, dtype=dtype)
+    if not is_categorical_dtype(comps):
+        comps, dtype, _ = _ensure_data(comps)
+        values, _, _ = _ensure_data(values, dtype=dtype)
+    else:
+        cats = comps.cat.categories
+        comps = comps.cat.codes.values
+        mask = isna(values)
+        values = cats.get_indexer(values)
+        values = values[mask | (values >= 0)]
 
     # faster for larger cases to use np.in1d
     f = lambda x, y: htable.ismember_object(x, values)

pandas/core/series.py

@@ -3507,7 +3507,11 @@ def isin(self, values):
         5    False
         Name: animal, dtype: bool
         """
-        result = algorithms.isin(com._values_from_object(self), values)
+        if is_categorical_dtype(self.dtype):
+            result = algorithms.isin(self, values)
+        else:
+            result = algorithms.isin(com._values_from_object(self), values)
+
         return self._constructor(result, index=self.index).__finalize__(self)
 
     def between(self, left, right, inclusive=True):

pandas/tests/series/test_analytics.py

@@ -1255,6 +1255,17 @@ def test_isin_empty(self, empty):
         result = s.isin(empty)
         tm.assert_series_equal(expected, result)
 
+    def test_isin_cats(self):
+        s = Series(["a", "b", np.nan]).astype("category")
+
+        result = s.isin(["a", np.nan])
+        expected = Series([True, False, True])
+        tm.assert_series_equal(expected, result)
+
+        result = s.isin(["a", "c"])
+        expected = Series([True, False, False])
+        tm.assert_series_equal(expected, result)
+
     def test_timedelta64_analytics(self):
         from pandas import date_range