PERF: speed-up when scalar not found in Categorical's categories (pandas-dev#29750)

Author: topper-123

doc/source/whatsnew/v1.0.0.rst

@@ -357,6 +357,7 @@ Performance improvements
 - Performance improvement in :meth:`DataFrame.replace` when provided a list of values to replace (:issue:`28099`)
 - Performance improvement in :meth:`DataFrame.select_dtypes` by using vectorization instead of iterating over a loop (:issue:`28317`)
 - Performance improvement in :meth:`Categorical.searchsorted` and  :meth:`CategoricalIndex.searchsorted` (:issue:`28795`)
+- Performance improvement when searching for a scalar in a :meth:`Categorical` and the scalar is not found in the categories (:issue:`29750`)
 
 .. _whatsnew_1000.bug_fixes:
 

pandas/core/arrays/categorical.py

@@ -133,9 +133,9 @@ def func(self, other):
                 return ret
             else:
                 if opname == "__eq__":
-                    return np.repeat(False, len(self))
+                    return np.zeros(len(self), dtype=bool)
                 elif opname == "__ne__":
-                    return np.repeat(True, len(self))
+                    return np.ones(len(self), dtype=bool)
                 else:
                     raise TypeError(
                         f"Cannot compare a Categorical for op {opname} with a "

pandas/tests/arrays/categorical/test_operators.py

@@ -48,7 +48,7 @@ def test_comparisons(self):
         tm.assert_numpy_array_equal(result, expected)
 
         result = self.factor == "d"
-        expected = np.repeat(False, len(self.factor))
+        expected = np.zeros(len(self.factor), dtype=bool)
         tm.assert_numpy_array_equal(result, expected)
 
         # comparisons with categoricals

pandas/tests/indexes/interval/test_interval.py

@@ -105,11 +105,11 @@ def test_with_nans(self, closed):
         assert index.hasnans is False
 
         result = index.isna()
-        expected = np.repeat(False, len(index))
+        expected = np.zeros(len(index), dtype=bool)
         tm.assert_numpy_array_equal(result, expected)
 
         result = index.notna()
-        expected = np.repeat(True, len(index))
+        expected = np.ones(len(index), dtype=bool)
         tm.assert_numpy_array_equal(result, expected)
 
         index = self.create_index_with_nan(closed=closed)

pandas/tests/indexes/test_base.py

@@ -730,7 +730,7 @@ def test_nanosecond_index_access(self):
         assert first_value == x[Timestamp(expected_ts)]
 
     def test_booleanindex(self, index):
-        bool_index = np.repeat(True, len(index)).astype(bool)
+        bool_index = np.ones(len(index), dtype=bool)
         bool_index[5:30:2] = False
 
         sub_index = index[bool_index]