Merge pull request #8570 from jreback/equals

PERF: improve perf of array_equivalent_object (GH8512)

Author: jreback

pandas/core/common.py

@@ -411,12 +411,13 @@ def array_equivalent(left, right, strict_nan=False):
  if left.shape != right.shape: return False
 
  # Object arrays can contain None, NaN and NaT.
- if issubclass(left.dtype.type, np.object_):
+ if issubclass(left.dtype.type, np.object_) or issubclass(right.dtype.type, np.object_):
 
  if not strict_nan:
  # pd.isnull considers NaN and None to be equivalent.
- return lib.array_equivalent_object(left.ravel(), right.ravel())
- 
+ return lib.array_equivalent_object(_ensure_object(left.ravel()),
+ _ensure_object(right.ravel()))
+
  for left_value, right_value in zip(left, right):
  if left_value is tslib.NaT and right_value is not tslib.NaT:
  return False

pandas/lib.pyx

@@ -330,26 +330,6 @@ def list_to_object_array(list obj):
  return arr
 
 
-@cython.wraparound(False)
-@cython.boundscheck(False)
-def array_equivalent_object(ndarray left, ndarray right):
- cdef Py_ssize_t i, n
- cdef object lobj, robj
-
- n = len(left)
- for i from 0 <= i < n:
- lobj = left[i]
- robj = right[i]
-
- # we are either not equal or both nan
- # I think None == None will be true here
- if lobj != robj:
- if checknull(lobj) and checknull(robj):
- continue
- return False
- return True
-
-
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def fast_unique(ndarray[object] values):
@@ -692,6 +672,31 @@ def scalar_compare(ndarray[object] values, object val, object op):
 
  return result.view(bool)
 
+@cython.wraparound(False)
+@cython.boundscheck(False)
+def array_equivalent_object(ndarray[object] left, ndarray[object] right):
+ """ perform an element by element comparion on 1-d object arrays
+ taking into account nan positions """
+ cdef Py_ssize_t i, n
+ cdef object x, y
+
+ n = len(left)
+ for i from 0 <= i < n:
+ x = left[i]
+ y = right[i]
+
+ # we are either not equal or both nan
+ # I think None == None will be true here
+ if cpython.PyObject_RichCompareBool(x, y, cpython.Py_EQ):
+ continue
+ elif _checknull(x) and _checknull(y):
+ continue
+ else:
+ return False
+
+ return True
+
+
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def vec_compare(ndarray[object] left, ndarray[object] right, object op):