PERF: do not instantiate IndexEngine for standard lookup over RangeIndex

closes #16685

Author: toobaz

doc/source/whatsnew/v0.25.0.rst

@@ -628,6 +628,7 @@ Performance improvements
   int8/int16/int32 and the searched key is within the integer bounds for the dtype (:issue:`22034`)
 - Improved performance of :meth:`pandas.core.groupby.GroupBy.quantile` (:issue:`20405`)
 - Improved performance of slicing and other selected operation on a :class:`RangeIndex` (:issue:`26565`, :issue:`26617`, :issue:`26722`)
+- :class:`RangeIndex` now performs standard lookup without instantiating an actual hashtable, hence saving memory (:issue:`16685`)
 - Improved performance of :meth:`read_csv` by faster tokenizing and faster parsing of small float numbers (:issue:`25784`)
 - Improved performance of :meth:`read_csv` by faster parsing of N/A and boolean values (:issue:`25804`)
 - Improved performance of :attr:`IntervalIndex.is_monotonic`, :attr:`IntervalIndex.is_monotonic_increasing` and :attr:`IntervalIndex.is_monotonic_decreasing` by removing conversion to :class:`MultiIndex` (:issue:`24813`)

pandas/core/indexes/range.py

@@ -13,8 +13,8 @@
 
 from pandas.core.dtypes import concat as _concat
 from pandas.core.dtypes.common import (
-    ensure_python_int, is_int64_dtype, is_integer, is_scalar,
-    is_timedelta64_dtype)
+    ensure_python_int, is_int64_dtype, is_integer, is_scalar, is_integer_dtype,
+    is_timedelta64_dtype, is_list_like, ensure_platform_int)
 from pandas.core.dtypes.generic import (
     ABCDataFrame, ABCSeries, ABCTimedeltaIndex)
 
@@ -348,6 +348,36 @@ def get_loc(self, key, method=None, tolerance=None):
                 raise KeyError(key)
         return super().get_loc(key, method=method, tolerance=tolerance)
 
+    @Appender(_index_shared_docs['get_indexer'])
+    def get_indexer(self, target, method=None, limit=None, tolerance=None):
+        if not (method is None and tolerance is None and is_list_like(target)):
+            return super().get_indexer(target, method=method,
+                                       tolerance=tolerance)
+
+        if self.step > 0:
+            start, stop, step = self.start, self.stop, self.step
+        else:
+            # Work on reversed range for simplicity:
+            start, stop, step = (self.stop - self.step,
+                                 self.start + 1,
+                                 - self.step)
+
+        target_array = np.asarray(target)
+        if not (is_integer_dtype(target_array) and target_array.ndim == 1):
+            # checks/conversions/roundings are delegated to general method
+            return super().get_indexer(target, method=method,
+                                       tolerance=tolerance)
+
+        locs = target_array - start
+        valid = (locs % step == 0) & (locs >= 0) & (target_array < stop)
+        locs[~valid] = -1
+        locs[valid] = locs[valid] / step
+
+        if step != self.step:
+            # We reversed this range: transform to original locs
+            locs[valid] = len(self) - 1 - locs[valid]
+        return ensure_platform_int(locs)
+
     def tolist(self):
         return list(self._range)
 

pandas/tests/indexes/test_range.py

@@ -965,3 +965,23 @@ def test_append(self, appends):
             # Append single item rather than list
             result2 = indices[0].append(indices[1])
             tm.assert_index_equal(result2, expected, exact=True)
+
+    def test_engineless_lookup(self):
+        # GH 16685
+        # Standard lookup on RangeIndex should not require the engine to be
+        # created
+        idx = RangeIndex(2, 10, 3)
+
+        assert idx.get_loc(5) == 1
+        tm.assert_numpy_array_equal(idx.get_indexer([2, 8]),
+                                    np.array([0, 2]))
+        with pytest.raises(KeyError):
+            idx.get_loc(3)
+
+        assert '_engine' not in idx._cache
+
+        # The engine is still required for lookup of a different dtype scalar:
+        with pytest.raises(KeyError):
+            assert idx.get_loc('a') == -1
+
+        assert '_engine' in idx._cache