Fix GH 14922

    having the int equivalent of NaT in an int64 column caused wrong
    sorting because this special value was considered as "missing
    value".

Author: uweschmitt

pandas/core/algorithms.py

@@ -343,7 +343,8 @@ def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
 
     table = hash_klass(size_hint or len(vals))
     uniques = vec_klass()
-    labels = table.get_labels(vals, uniques, 0, na_sentinel, True)
+    check_nulls = not is_integer_dtype(values)
+    labels = table.get_labels(vals, uniques, 0, na_sentinel, check_nulls)
 
     labels = _ensure_platform_int(labels)
 

pandas/tests/frame/test_sorting.py

@@ -6,7 +6,7 @@
 
 from pandas.compat import lrange
 from pandas import (DataFrame, Series, MultiIndex, Timestamp,
-                    date_range)
+                    date_range, NaT)
 
 from pandas.util.testing import (assert_series_equal,
                                  assert_frame_equal,
@@ -491,3 +491,18 @@ def test_frame_column_inplace_sort_exception(self):
 
         cp = s.copy()
         cp.sort_values()  # it works!
+
+    def test_sort_nat_values_in_int_column(self):
+
+        # GH 14922, sorting with large float and multiple columns incorrect
+        int_values = (2, int(NaT))
+        float_values = (2.0, -1.797693e308)
+
+        df = DataFrame(dict(int=int_values, float=float_values),
+                       columns=["int", "float"])
+
+        df_sorted = df.sort_values(["int", "float"])
+        df_expected = DataFrame(dict(int=int_values[::-1], float=float_values[::-1]),
+                                columns=["int", "float"], index=[1, 0])
+
+        assert_frame_equal(df_sorted, df_expected)