From 5c27c024c2191817aadc86cf86f897bbf5eb5002 Mon Sep 17 00:00:00 2001
From: Douglas McNeil <dmcneil@mackenzieinvestments.com>
Date: Tue, 16 Aug 2016 06:08:47 -0400
Subject: [PATCH] BUG: Avoid sentinel-infinity comparison problems (#13445)

The problem causing #13445 ultimately traces to the fact that our
Infinity/NegInfinity objects were greater than/less than themselves,
which violates an assumption numpy makes when sorting.  This was
separately reported as https://github.com/numpy/numpy/issues/7934, but
we can fix and test downstream as well.

closes #13445

Author: Douglas McNeil <dmcneil@mackenzieinvestments.com>

Closes #14006 from dsm054/fix_rank_segfault and squashes the following commits:

7d79370 [Douglas McNeil] BUG: Avoid sentinel-infinity comparison problems (#13445)
---
 doc/source/whatsnew/v0.19.0.txt |  1 +
 pandas/algos.pyx                | 31 +++++++++++++++----------------
 pandas/tests/test_algos.py      | 30 ++++++++++++++++++++++++++++++
 pandas/tests/test_stats.py      |  7 +++++++
 4 files changed, 53 insertions(+), 16 deletions(-)

diff --git a/doc/source/whatsnew/v0.19.0.txt b/doc/source/whatsnew/v0.19.0.txt
index 9cac79288ea89..0ee56f865f8c8 100644
--- a/doc/source/whatsnew/v0.19.0.txt
+++ b/doc/source/whatsnew/v0.19.0.txt
@@ -900,6 +900,7 @@ Bug Fixes
 - Bug in ``.rolling()`` that allowed a negative integer window in contruction of the ``Rolling()`` object, but would later fail on aggregation (:issue:`13383`)
 
 - Bug in printing ``pd.DataFrame`` where unusual elements with the ``object`` dtype were causing segfaults (:issue:`13717`)
+- Bug in ranking ``Series`` which could result in segfaults (:issue:`13445`)
 - Bug in various index types, which did not propagate the name of passed index (:issue:`12309`)
 - Bug in ``DatetimeIndex``, which did not honour the ``copy=True`` (:issue:`13205`)
 - Bug in ``DatetimeIndex.is_normalized`` returns incorrectly for normalized date_range in case of local timezones (:issue:`13459`)
diff --git a/pandas/algos.pyx b/pandas/algos.pyx
index 44288ab9621f1..d3e68ad2a5eee 100644
--- a/pandas/algos.pyx
+++ b/pandas/algos.pyx
@@ -567,28 +567,27 @@ cdef inline are_diff(object left, object right):
     except TypeError:
         return left != right
 
-_return_false = lambda self, other: False
-_return_true = lambda self, other: True
 
 class Infinity(object):
+    """ provide a positive Infinity comparision method for ranking """
 
-    __lt__ = _return_false
-    __le__ = _return_false
-    __eq__ = _return_false
-    __ne__ = _return_true
-    __gt__ = _return_true
-    __ge__ = _return_true
-    __cmp__ = _return_false
+    __lt__ = lambda self, other: False
+    __le__ = lambda self, other: self is other
+    __eq__ = lambda self, other: self is other
+    __ne__ = lambda self, other: self is not other
+    __gt__ = lambda self, other: self is not other
+    __ge__ = lambda self, other: True
 
 class NegInfinity(object):
+    """ provide a negative Infinity comparision method for ranking """
+
+    __lt__ = lambda self, other: self is not other
+    __le__ = lambda self, other: True
+    __eq__ = lambda self, other: self is other
+    __ne__ = lambda self, other: self is not other
+    __gt__ = lambda self, other: False
+    __ge__ = lambda self, other: self is other
 
-    __lt__ = _return_true
-    __le__ = _return_true
-    __eq__ = _return_false
-    __ne__ = _return_true
-    __gt__ = _return_false
-    __ge__ = _return_false
-    __cmp__ = _return_true
 
 def rank_2d_generic(object in_arr, axis=0, ties_method='average',
                     ascending=True, na_option='keep', pct=False):
diff --git a/pandas/tests/test_algos.py b/pandas/tests/test_algos.py
index 66fd1861f08f9..452355541a79b 100644
--- a/pandas/tests/test_algos.py
+++ b/pandas/tests/test_algos.py
@@ -5,6 +5,7 @@
 from numpy.random import RandomState
 from numpy import nan
 from datetime import datetime
+from itertools import permutations
 from pandas import Series, Categorical, CategoricalIndex, Index
 import pandas as pd
 
@@ -1270,6 +1271,35 @@ def test_groupsort_indexer():
     assert (np.array_equal(result, expected))
 
 
+def test_infinity_sort():
+    # GH 13445
+    # numpy's argsort can be unhappy if something is less than
+    # itself.  Instead, let's give our infinities a self-consistent
+    # ordering, but outside the float extended real line.
+
+    Inf = _algos.Infinity()
+    NegInf = _algos.NegInfinity()
+
+    ref_nums = [NegInf, float("-inf"), -1e100, 0, 1e100, float("inf"), Inf]
+
+    assert all(Inf >= x for x in ref_nums)
+    assert all(Inf > x or x is Inf for x in ref_nums)
+    assert Inf >= Inf and Inf == Inf
+    assert not Inf < Inf and not Inf > Inf
+
+    assert all(NegInf <= x for x in ref_nums)
+    assert all(NegInf < x or x is NegInf for x in ref_nums)
+    assert NegInf <= NegInf and NegInf == NegInf
+    assert not NegInf < NegInf and not NegInf > NegInf
+
+    for perm in permutations(ref_nums):
+        assert sorted(perm) == ref_nums
+
+    # smoke tests
+    np.array([_algos.Infinity()] * 32).argsort()
+    np.array([_algos.NegInfinity()] * 32).argsort()
+
+
 def test_ensure_platform_int():
     arr = np.arange(100)
 
diff --git a/pandas/tests/test_stats.py b/pandas/tests/test_stats.py
index 85ce1d5127512..41d25b9662b5b 100644
--- a/pandas/tests/test_stats.py
+++ b/pandas/tests/test_stats.py
@@ -179,6 +179,13 @@ def test_rank_int(self):
             expected.index = result.index
             assert_series_equal(result, expected)
 
+    def test_rank_object_bug(self):
+        # GH 13445
+
+        # smoke tests
+        Series([np.nan] * 32).astype(object).rank(ascending=True)
+        Series([np.nan] * 32).astype(object).rank(ascending=False)
+
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],