Remove maskna API from ndarray, and all (and only) the code supporting it

The original masked-NA-NEP branch contained a large number of changes
in addition to the core NA support. For example:
 - ufunc.__call__ support for where= argument
 - nditer support for arbitrary masks (in support of where=)
 - ufunc.reduce support for simultaneous reduction over multiple axes
 - a new "array assignment API"
 - ndarray.diagonal() returning a view in all cases
 - bug-fixes in __array_priority__ handling
 - datetime test changes
etc. There's no consensus yet on what should be done with the
maskna-related part of this branch, but the rest is generally useful
and uncontroversial, so the goal of this branch is to identify exactly
which code changes are involved in maskna support.

The basic strategy used to create this patch was:
 - Remove the new masking-related fields from ndarray, so no arrays
   are masked
 - Go through and remove all the code that this makes
   dead/inaccessible/irrelevant, in a largely mechanical fashion. So
   for example, if I saw 'if (PyArray_HASMASK(a)) { ... }' then that
   whole block was obviously just dead code if no arrays have masks,
   and I removed it. Likewise for function arguments like skipna that
   are useless if there aren't any NAs to skip.

This changed the signature of a number of functions that were newly
exposed in the numpy public API. I've removed all such functions from
the public API, since releasing them with the NA-less signature in 1.7
would create pointless compatibility hassles later if and when we add
back the NA-related functionality. Most such functions are removed by
this commit; the exception is PyArray_ReduceWrapper, which requires
more extensive surgery, and will be handled in followup commits.

I also removed the new ndarray.setasflat method. Reason: a comment
noted that the only reason this was added was to allow easier testing
of one branch of PyArray_CopyAsFlat. That branch is now the main
branch, so that isn't an issue. Nonetheless this function is arguably
useful, so perhaps it should have remained, but I judged that since
numpy's API is already hairier than we would like, it's not a good
idea to add extra hair "just in case". (Also AFAICT the test for this
method in test_maskna was actually incorrect, as noted here:
   https://github.com/njsmith/numpyNEP/blob/master/numpyNEP.py
so I'm not confident that it ever worked in master, though I haven't
had a chance to follow-up on this.)

I also removed numpy.count_reduce_items, since without skipna it
became trivial.

I believe that these are the only exceptions to the "remove dead code"
strategy.

1 files changed, 40 insertions, 75 deletions

diff --git a/numpy/core/arrayprint.py b/numpy/core/arrayprint.py
index 35c82a21d..19be452e5 100644
--- a/numpy/core/arrayprint.py
+++ b/numpy/core/arrayprint.py
@@ -15,7 +15,7 @@ __docformat__ = 'restructuredtext'
 import sys
 import numerictypes as _nt
 from umath import maximum, minimum, absolute, not_equal, isnan, isinf
-from multiarray import format_longfloat, datetime_as_string, datetime_data, isna
+from multiarray import format_longfloat, datetime_as_string, datetime_data
 from fromnumeric import ravel
 
 
@@ -29,7 +29,6 @@ _float_output_suppress_small = False
 _line_width = 75
 _nan_str = 'nan'
 _inf_str = 'inf'
-_na_str = 'NA'
 _formatter = None  # formatting function for array elements
 
 if sys.version_info[0] >= 3:
@@ -37,7 +36,7 @@ if sys.version_info[0] >= 3:
 
 def set_printoptions(precision=None, threshold=None, edgeitems=None,
                      linewidth=None, suppress=None,
-                     nanstr=None, infstr=None, nastr=None,
+                     nanstr=None, infstr=None,
                      formatter=None):
     """
     Set printing options.
@@ -65,8 +64,6 @@ def set_printoptions(precision=None, threshold=None, edgeitems=None,
         String representation of floating point not-a-number (default nan).
     infstr : str, optional
         String representation of floating point infinity (default inf).
-    nastr : str, optional
-        String representation of NA missing value (default NA).
     formatter : dict of callables, optional
         If not None, the keys should indicate the type(s) that the respective
         formatting function applies to.  Callables should return a string.
@@ -144,7 +141,7 @@ def set_printoptions(precision=None, threshold=None, edgeitems=None,
 
     global _summaryThreshold, _summaryEdgeItems, _float_output_precision, \
            _line_width, _float_output_suppress_small, _nan_str, _inf_str, \
-           _na_str, _formatter
+           _formatter
     if linewidth is not None:
         _line_width = linewidth
     if threshold is not None:
@@ -159,8 +156,6 @@ def set_printoptions(precision=None, threshold=None, edgeitems=None,
         _nan_str = nanstr
     if infstr is not None:
         _inf_str = infstr
-    if nastr is not None:
-        _na_str = nastr
     _formatter = formatter
 
 def get_printoptions():
@@ -195,7 +190,6 @@ def get_printoptions():
              suppress=_float_output_suppress_small,
              nanstr=_nan_str,
              infstr=_inf_str,
-             nastr=_na_str,
              formatter=_formatter)
     return d
 
@@ -219,19 +213,14 @@ def _leading_trailing(a):
     return b
 
 def _boolFormatter(x):
-    if isna(x):
-        return str(x).replace('NA', _na_str, 1)
-    elif x:
+    if x:
         return ' True'
     else:
         return 'False'
 
 
 def repr_format(x):
-    if isna(x):
-        return str(x).replace('NA', _na_str, 1)
-    else:
-        return repr(x)
+    return repr(x)
 
 def _array2string(a, max_line_width, precision, suppress_small, separator=' ',
                   prefix="", formatter=None):
@@ -437,20 +426,17 @@ def array2string(a, max_line_width=None, precision=None,
 
     if a.shape == ():
         x = a.item()
-        if isna(x):
-            lst = str(x).replace('NA', _na_str, 1)
-        else:
-            try:
-                lst = a._format(x)
-                msg = "The `_format` attribute is deprecated in Numpy " \
-                      "2.0 and will be removed in 2.1. Use the " \
-                      "`formatter` kw instead."
-                import warnings
-                warnings.warn(msg, DeprecationWarning)
-            except AttributeError:
-                if isinstance(x, tuple):
-                    x = _convert_arrays(x)
-                lst = style(x)
+        try:
+            lst = a._format(x)
+            msg = "The `_format` attribute is deprecated in Numpy " \
+                  "2.0 and will be removed in 2.1. Use the " \
+                  "`formatter` kw instead."
+            import warnings
+            warnings.warn(msg, DeprecationWarning)
+        except AttributeError:
+            if isinstance(x, tuple):
+                x = _convert_arrays(x)
+            lst = style(x)
     elif reduce(product, a.shape) == 0:
         # treat as a null array if any of shape elements == 0
         lst = "[]"
@@ -553,17 +539,15 @@ class FloatFormat(object):
         import numeric as _nc
         errstate = _nc.seterr(all='ignore')
         try:
-            special = isnan(data) | isinf(data) | isna(data)
-            special[isna(data)] = False
+            special = isnan(data) | isinf(data)
             valid = not_equal(data, 0) & ~special
-            valid[isna(data)] = False
             non_zero = absolute(data.compress(valid))
             if len(non_zero) == 0:
                 max_val = 0.
                 min_val = 0.
             else:
-                max_val = maximum.reduce(non_zero, skipna=True)
-                min_val = minimum.reduce(non_zero, skipna=True)
+                max_val = maximum.reduce(non_zero)
+                min_val = minimum.reduce(non_zero)
                 if max_val >= 1.e8:
                     self.exp_format = True
                 if not self.suppress_small and (min_val < 0.0001
@@ -594,8 +578,7 @@ class FloatFormat(object):
             if _nc.any(special):
                 self.max_str_len = max(self.max_str_len,
                                        len(_nan_str),
-                                       len(_inf_str)+1,
-                                       len(_na_str))
+                                       len(_inf_str)+1)
             if self.sign:
                 format = '%#+'
             else:
@@ -609,9 +592,7 @@ class FloatFormat(object):
         import numeric as _nc
         err = _nc.seterr(invalid='ignore')
         try:
-            if isna(x):
-                return self.special_fmt % (str(x).replace('NA', _na_str, 1),)
-            elif isnan(x):
+            if isnan(x):
                 if self.sign:
                     return self.special_fmt % ('+' + _nan_str,)
                 else:
@@ -654,8 +635,8 @@ _MININT = -sys.maxint-1
 class IntegerFormat(object):
     def __init__(self, data):
         try:
-            max_str_len = max(len(str(maximum.reduce(data, skipna=True))),
-                              len(str(minimum.reduce(data, skipna=True))))
+            max_str_len = max(len(str(maximum.reduce(data))),
+                              len(str(minimum.reduce(data))))
             self.format = '%' + str(max_str_len) + 'd'
         except (TypeError, NotImplementedError):
             # if reduce(data) fails, this instance will not be called, just
@@ -666,9 +647,7 @@ class IntegerFormat(object):
             pass
 
     def __call__(self, x):
-        if isna(x):
-            return str(x).replace('NA', _na_str, 1)
-        elif _MININT < x < _MAXINT:
+        if _MININT < x < _MAXINT:
             return self.format % x
         else:
             return "%s" % x
@@ -681,9 +660,7 @@ class LongFloatFormat(object):
         self.sign = sign
 
     def __call__(self, x):
-        if isna(x):
-            return str(x).replace('NA', _na_str, 1)
-        elif isnan(x):
+        if isnan(x):
             if self.sign:
                 return '+' + _nan_str
             else:
@@ -711,12 +688,9 @@ class LongComplexFormat(object):
         self.imag_format = LongFloatFormat(precision, sign=True)
 
     def __call__(self, x):
-        if isna(x):
-            return str(x).replace('NA', _na_str, 1)
-        else:
-            r = self.real_format(x.real)
-            i = self.imag_format(x.imag)
-            return r + i + 'j'
+        r = self.real_format(x.real)
+        i = self.imag_format(x.imag)
+        return r + i + 'j'
 
 
 class ComplexFormat(object):
@@ -726,17 +700,14 @@ class ComplexFormat(object):
                                        sign=True)
 
     def __call__(self, x):
-        if isna(x):
-            return str(x).replace('NA', _na_str, 1)
+        r = self.real_format(x.real, strip_zeros=False)
+        i = self.imag_format(x.imag, strip_zeros=False)
+        if not self.imag_format.exp_format:
+            z = i.rstrip('0')
+            i = z + 'j' + ' '*(len(i)-len(z))
         else:
-            r = self.real_format(x.real, strip_zeros=False)
-            i = self.imag_format(x.imag, strip_zeros=False)
-            if not self.imag_format.exp_format:
-                z = i.rstrip('0')
-                i = z + 'j' + ' '*(len(i)-len(z))
-            else:
-                i = i + 'j'
-            return r + i
+            i = i + 'j'
+        return r + i
 
 class DatetimeFormat(object):
     def __init__(self, x, unit=None,
@@ -761,13 +732,10 @@ class DatetimeFormat(object):
         self.casting = casting
 
     def __call__(self, x):
-        if isna(x):
-            return str(x).replace('NA', _na_str, 1)
-        else:
-            return "'%s'" % datetime_as_string(x,
-                                        unit=self.unit,
-                                        timezone=self.timezone,
-                                        casting=self.casting)
+        return "'%s'" % datetime_as_string(x,
+                                    unit=self.unit,
+                                    timezone=self.timezone,
+                                    casting=self.casting)
 
 class TimedeltaFormat(object):
     def __init__(self, data):
@@ -778,8 +746,5 @@ class TimedeltaFormat(object):
             self.format = '%' + str(max_str_len) + 'd'
 
     def __call__(self, x):
-        if isna(x):
-            return str(x).replace('NA', _na_str, 1)
-        else:
-            return self.format % x.astype('i8')
+        return self.format % x.astype('i8')