cleared up bug with is_monotonic resetting unique

Author: jreback

pandas/core/algorithms.py

@@ -131,7 +131,7 @@ def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
     (hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
 
     table = hash_klass(size_hint or len(vals))
-    uniques = vec_klass(len(vals))
+    uniques = vec_klass()
     labels = table.get_labels(vals, uniques, 0, na_sentinel)
 
     labels = com._ensure_platform_int(labels)

pandas/core/index.py

@@ -1364,6 +1364,7 @@ def union(self, other):
         -------
         union : Index
         """
+
         if not hasattr(other, '__iter__'):
             raise TypeError('Input must be iterable.')
 

pandas/hashtable.pyx

@@ -35,10 +35,7 @@ cdef extern from "Python.h":
 
 cdef size_t _INIT_VEC_CAP = 32
 
-cdef class Vector:
-    pass
-
-cdef class ObjectVector(Vector):
+cdef class ObjectVector:
 
     cdef:
         PyObject **data
@@ -130,7 +127,7 @@ cdef void Float64VectorData_append(Float64VectorData *data, float64_t x) nogil:
     data.data[data.n] = x
     data.n += 1
 
-cdef class Float64Vector(Vector):
+cdef class Float64Vector:
 
     cdef:
         Float64VectorData *data

pandas/index.pyx

@@ -233,14 +233,13 @@ cdef class IndexEngine:
     cdef inline _do_monotonic_check(self):
         try:
             values = self._get_index_values()
-            self.monotonic_inc, self.monotonic_dec, self.unique = \
+            self.monotonic_inc, self.monotonic_dec = \
                 self._call_monotonic(values)
         except TypeError:
             self.monotonic_inc = 0
             self.monotonic_dec = 0
 
         self.monotonic_check = 1
-        self.unique_check = 1
 
     cdef _get_index_values(self):
         return self.vgetter()
@@ -269,7 +268,8 @@ cdef class IndexEngine:
 
         if len(self.mapping) == len(values):
             self.unique = 1
-        self.unique_check = 1
+            self.unique_check = 1
+
         self.initialized = 1
 
     def clear_mapping(self):

pandas/src/generate_code.py

@@ -586,12 +586,11 @@ def is_monotonic_%(name)s(ndarray[%(c_type)s] arr, bint timelike):
     '''
     Returns
     -------
-    is_monotonic_inc, is_monotonic_dec, is_unique
+    is_monotonic_inc, is_monotonic_dec
     '''
     cdef:
         Py_ssize_t i, n
         %(c_type)s prev, cur
-        bint is_unique = 1
         bint is_monotonic_inc = 1
         bint is_monotonic_dec = 1
 
@@ -600,21 +599,20 @@ def is_monotonic_%(name)s(ndarray[%(c_type)s] arr, bint timelike):
     if n == 1:
         if arr[0] != arr[0] or (timelike and arr[0] == iNaT):
             # single value is NaN
-            return False, False, True
+            return False, False
         else:
-            return True, True, True
+            return True, True
     elif n < 2:
-        return True, True, True
+        return True, True
 
     if timelike and arr[0] == iNaT:
-        return False, False, None
+        return False, False
 
     %(nogil)s
     %(tab)sprev = arr[0]
     %(tab)sfor i in range(1, n):
     %(tab)s    cur = arr[i]
     %(tab)s    if timelike and cur == iNaT:
-    %(tab)s        is_unique = 0
     %(tab)s        is_monotonic_inc = 0
     %(tab)s        is_monotonic_dec = 0
     %(tab)s        break
@@ -623,20 +621,18 @@ def is_monotonic_%(name)s(ndarray[%(c_type)s] arr, bint timelike):
     %(tab)s    elif cur > prev:
     %(tab)s        is_monotonic_dec = 0
     %(tab)s    elif cur == prev:
-    %(tab)s        is_unique = 0
+    %(tab)s        pass # is_unique = 0
     %(tab)s    else:
     %(tab)s        # cur or prev is NaN
-    %(tab)s        is_unique = 0
     %(tab)s        is_monotonic_inc = 0
     %(tab)s        is_monotonic_dec = 0
     %(tab)s        break
     %(tab)s    if not is_monotonic_inc and not is_monotonic_dec:
-    %(tab)s        is_unique = 0
     %(tab)s        is_monotonic_inc = 0
     %(tab)s        is_monotonic_dec = 0
     %(tab)s        break
     %(tab)s    prev = cur
-    return is_monotonic_inc, is_monotonic_dec, is_unique
+    return is_monotonic_inc, is_monotonic_dec
 """
 
 map_indices_template = """@cython.wraparound(False)