TST: Fix makeIntIndex, benchmark get loc

Author: Pietro Battiston <me@pietrobattiston.it> Closes pandas-dev#19483 from toobaz/test_get_loc and squashes the following commits: 51d6911 [Pietro Battiston] TST: benchmark get_loc in various cases d424f63 [Pietro Battiston] TST: produce unsorted integer index (consistently with other types)

Author: toobaz

asv_bench/benchmarks/index_object.py

@@ -147,6 +147,11 @@ def setup(self, dtype):
  self.idx = getattr(tm, 'make{}Index'.format(dtype))(N)
  self.array_mask = (np.arange(N) % 3) == 0
  self.series_mask = Series(self.array_mask)
+ self.sorted = self.idx.sort_values()
+ half = N // 2
+ self.non_unique = self.idx[:half].append(self.idx[:half])
+ self.non_unique_sorted = self.sorted[:half].append(self.sorted[:half])
+ self.key = self.sorted[N // 4]
 
  def time_boolean_array(self, dtype):
  self.idx[self.array_mask]
@@ -163,6 +168,18 @@ def time_slice(self, dtype):
  def time_slice_step(self, dtype):
  self.idx[::2]
 
+ def time_get_loc(self, dtype):
+ self.idx.get_loc(self.key)
+
+ def time_get_loc_sorted(self, dtype):
+ self.sorted.get_loc(self.key)
+
+ def time_get_loc_non_unique(self, dtype):
+ self.non_unique.get_loc(self.key)
+
+ def time_get_loc_non_unique_sorted(self, dtype):
+ self.non_unique_sorted.get_loc(self.key)
+
 
 class Float64IndexMethod(object):
  # GH 13166

pandas/tests/indexes/test_base.py

@@ -830,15 +830,16 @@ def test_map_with_tuples(self):
 
  # Test that returning a single tuple from an Index
  # returns an Index.
- boolean_index = tm.makeIntIndex(3).map(lambda x: (x,))
- expected = Index([(0,), (1,), (2,)])
- tm.assert_index_equal(boolean_index, expected)
+ idx = tm.makeIntIndex(3)
+ result = tm.makeIntIndex(3).map(lambda x: (x,))
+ expected = Index([(i,) for i in idx])
+ tm.assert_index_equal(result, expected)
 
  # Test that returning a tuple from a map of a single index
  # returns a MultiIndex object.
- boolean_index = tm.makeIntIndex(3).map(lambda x: (x, x == 1))
- expected = MultiIndex.from_tuples([(0, False), (1, True), (2, False)])
- tm.assert_index_equal(boolean_index, expected)
+ result = idx.map(lambda x: (x, x == 1))
+ expected = MultiIndex.from_tuples([(i, i == 1) for i in idx])
+ tm.assert_index_equal(result, expected)
 
  # Test that returning a single object from a MultiIndex
  # returns an Index.
@@ -870,7 +871,8 @@ def test_map_tseries_indices_return_index(self):
  def test_map_dictlike(self, mapper):
  # GH 12756
  expected = Index(['foo', 'bar', 'baz'])
- result = tm.makeIntIndex(3).map(mapper(expected.values, [0, 1, 2]))
+ idx = tm.makeIntIndex(3)
+ result = idx.map(mapper(expected.values, idx))
  tm.assert_index_equal(result, expected)
 
  for name in self.indices.keys():

pandas/tests/indexing/test_floats.py

@@ -4,7 +4,8 @@
 
 from warnings import catch_warnings
 import numpy as np
-from pandas import Series, DataFrame, Index, Float64Index
+from pandas import (Series, DataFrame, Index, Float64Index, Int64Index,
+ RangeIndex)
 from pandas.util.testing import assert_series_equal, assert_almost_equal
 import pandas.util.testing as tm
 
@@ -206,9 +207,8 @@ def test_scalar_integer(self):
  # test how scalar float indexers work on int indexes
 
  # integer index
- for index in [tm.makeIntIndex, tm.makeRangeIndex]:
+ for i in [Int64Index(range(5)), RangeIndex(5)]:
 
- i = index(5)
  for s in [Series(np.arange(len(i))),
  DataFrame(np.random.randn(len(i), len(i)),
  index=i, columns=i)]:
@@ -362,9 +362,9 @@ def test_slice_integer(self):
  # these coerce to a like integer
  # oob indicates if we are out of bounds
  # of positional indexing
- for index, oob in [(tm.makeIntIndex(5), False),
- (tm.makeRangeIndex(5), False),
- (tm.makeIntIndex(5) + 10, True)]:
+ for index, oob in [(Int64Index(range(5)), False),
+ (RangeIndex(5), False),
+ (Int64Index(range(5)) + 10, True)]:
 
  # s is an in-range index
  s = Series(range(5), index=index)
@@ -486,9 +486,8 @@ def f():
  def test_slice_integer_frame_getitem(self):
 
  # similar to above, but on the getitem dim (of a DataFrame)
- for index in [tm.makeIntIndex, tm.makeRangeIndex]:
+ for index in [Int64Index(range(5)), RangeIndex(5)]:
 
- index = index(5)
  s = DataFrame(np.random.randn(5, 2), index=index)
 
  def f(idxr):