Merge pull request pandas-dev#6960 from jreback/warnings

COMPAT: fix numpy 1.9-dev deprecation warnings in test suite

Author: jreback

ci/script.sh

@@ -16,6 +16,13 @@ fi
 "$TRAVIS_BUILD_DIR"/ci/build_docs.sh 2>&1 > /tmp/doc.log &
 # doc build log will be shown after tests
 
+# export the testing mode
+if [ -n "$NUMPY_BUILD" ]; then
+
+    export PANDAS_TESTING_MODE="numpy_deprecate"
+
+fi
+
 echo nosetests --exe -w /tmp -A "$NOSE_ARGS" pandas --with-xunit --xunit-file=/tmp/nosetests.xml
 nosetests --exe -w /tmp -A "$NOSE_ARGS" pandas --with-xunit --xunit-file=/tmp/nosetests.xml
 

doc/source/release.rst

@@ -240,6 +240,9 @@ Prior Version Deprecations/Changes
 - Remove ``time_rule`` from several rolling-moment statistical functions, such
   as :func:`rolling_sum` (:issue:`1042`)
 
+- Removed neg (-) boolean operations on numpy arrays in favor of inv (~), as this is going to
+  be deprecated in numpy 1.9 (:issue:`6960`)
+
 Experimental Features
 ~~~~~~~~~~~~~~~~~~~~~
 

doc/source/v0.14.0.txt

@@ -368,6 +368,8 @@ There are prior version deprecations that are taking effect as of 0.14.0.
   ( `commit 3136390 <https://github.com/pydata/pandas/commit/3136390>`__ )
 - Remove ``time_rule`` from several rolling-moment statistical functions, such
   as :func:`rolling_sum` (:issue:`1042`)
+- Removed neg (-) boolean operations on numpy arrays in favor of inv (~), as this is going to
+  be deprecated in numpy 1.9 (:issue:`6960`)
 
 .. _whatsnew_0140.deprecations:
 

pandas/algos.pyx

@@ -510,7 +510,7 @@ def rank_1d_generic(object in_arr, bint retry=1, ties_method='average',
         if not retry:
             raise
 
-        valid_locs = (-mask).nonzero()[0]
+        valid_locs = (~mask).nonzero()[0]
         ranks.put(valid_locs, rank_1d_generic(values.take(valid_locs), 0,
                                               ties_method=ties_method,
                                               ascending=ascending))

pandas/computation/ops.py

@@ -42,9 +42,7 @@ class Term(StringMixin):
     def __new__(cls, name, env, side=None, encoding=None):
         klass = Constant if not isinstance(name, string_types) else cls
         supr_new = super(Term, klass).__new__
-        if PY3:
-            return supr_new(klass)
-        return supr_new(klass, name, env, side=side, encoding=encoding)
+        return supr_new(klass)
 
     def __init__(self, name, env, side=None, encoding=None):
         self._name = name

pandas/computation/pytables.py

@@ -33,9 +33,7 @@ class Term(ops.Term):
     def __new__(cls, name, env, side=None, encoding=None):
         klass = Constant if not isinstance(name, string_types) else cls
         supr_new = StringMixin.__new__
-        if PY3:
-            return supr_new(klass)
-        return supr_new(klass, name, env, side=side, encoding=encoding)
+        return supr_new(klass)
 
     def __init__(self, name, env, side=None, encoding=None):
         super(Term, self).__init__(name, env, side=side, encoding=encoding)

pandas/core/algorithms.py

@@ -329,7 +329,7 @@ def quantile(x, q, interpolation_method='fraction'):
     x = np.asarray(x)
     mask = com.isnull(x)
 
-    x = x[-mask]
+    x = x[~mask]
 
     values = np.sort(x)
 
@@ -339,7 +339,7 @@ def _get_score(at):
 
         idx = at * (len(values) - 1)
         if idx % 1 == 0:
-            score = values[idx]
+            score = values[int(idx)]
         else:
             if interpolation_method == 'fraction':
                 score = _interpolate(values[int(idx)], values[int(idx) + 1],

pandas/core/common.py

@@ -248,7 +248,7 @@ def _isnull_ndarraylike_old(obj):
         # this is the NaT pattern
         result = values.view('i8') == tslib.iNaT
     else:
-        result = -np.isfinite(values)
+        result = ~np.isfinite(values)
 
     # box
     if isinstance(obj, ABCSeries):
@@ -280,12 +280,22 @@ def notnull(obj):
     res = isnull(obj)
     if np.isscalar(res):
         return not res
-    return -res
+    return ~res
 
 def _is_null_datelike_scalar(other):
     """ test whether the object is a null datelike, e.g. Nat
     but guard against passing a non-scalar """
-    return (np.isscalar(other) and (isnull(other) or other == tslib.iNaT)) or other is pd.NaT or other is None
+    if other is pd.NaT or other is None:
+        return True
+    elif np.isscalar(other):
+
+        # a timedelta
+        if hasattr(other,'dtype'):
+            return other.view('i8') == tslib.iNaT
+        elif is_integer(other) and other == tslib.iNaT:
+            return True
+        return isnull(other)
+    return False
 
 def array_equivalent(left, right):
     """
@@ -363,7 +373,7 @@ def mask_missing(arr, values_to_mask):
         values_to_mask = np.array(values_to_mask, dtype=object)
 
     na_mask = isnull(values_to_mask)
-    nonna = values_to_mask[-na_mask]
+    nonna = values_to_mask[~na_mask]
 
     mask = None
     for x in nonna:

pandas/core/format.py

@@ -1861,7 +1861,7 @@ def _get_format_timedelta64(values):
     def impl(x):
         if x is None or lib.checknull(x):
             return 'NaT'
-        elif format_short and x == 0:
+        elif format_short and com.is_integer(x) and x.view('int64') == 0:
             return "0 days" if even_days else "00:00:00"
         else:
             return lib.repr_timedelta64(x, format=format)

pandas/core/frame.py

@@ -3041,7 +3041,7 @@ def update(self, other, join='left', overwrite=True, filter_func=None,
             this = self[col].values
             that = other[col].values
             if filter_func is not None:
-                mask = -filter_func(this) | isnull(that)
+                mask = ~filter_func(this) | isnull(that)
             else:
                 if raise_conflict:
                     mask_this = notnull(that)

pandas/core/generic.py

@@ -606,7 +606,11 @@ def _indexed_same(self, other):
                     for a in self._AXIS_ORDERS])
 
     def __neg__(self):
-        arr = operator.neg(_values_from_object(self))
+        values = _values_from_object(self)
+        if values.dtype == np.bool_:
+            arr = operator.inv(values)
+        else:
+            arr = operator.neg(values)
         return self._wrap_array(arr, self.axes, copy=False)
 
     def __invert__(self):
@@ -1459,10 +1463,10 @@ def drop(self, labels, axis=0, level=None, inplace=False, **kwargs):
             if level is not None:
                 if not isinstance(axis, MultiIndex):
                     raise AssertionError('axis must be a MultiIndex')
-                indexer = -lib.ismember(axis.get_level_values(level),
+                indexer = ~lib.ismember(axis.get_level_values(level),
                                         set(labels))
             else:
-                indexer = -axis.isin(labels)
+                indexer = ~axis.isin(labels)
 
             slicer = [slice(None)] * self.ndim
             slicer[self._get_axis_number(axis_name)] = indexer

pandas/core/groupby.py

@@ -1698,7 +1698,7 @@ def __init__(self, index, grouper=None, obj=None, name=None, level=None,
 
                     labels = np.empty(len(inds), dtype=inds.dtype)
                     labels[mask] = ok_labels
-                    labels[-mask] = -1
+                    labels[~mask] = -1
 
                 if len(uniques) < len(level_index):
                     level_index = level_index.take(uniques)

pandas/core/index.py

@@ -480,10 +480,10 @@ def to_int():
             if is_integer(key):
                 return key
             elif is_float(key):
-                if not self.is_floating():
-                    warnings.warn("scalar indexers for index type {0} should be integers and not floating point".format(
-                        type(self).__name__),FutureWarning)
-                return to_int()
+                key = to_int()
+                warnings.warn("scalar indexers for index type {0} should be integers and not floating point".format(
+                    type(self).__name__),FutureWarning)
+                return key
             return self._convert_indexer_error(key, 'label')
 
         if is_float(key):
@@ -498,17 +498,9 @@ def _validate_slicer(self, key, f):
         """ validate and raise if needed on a slice indexers according to the
         passed in function """
 
-        if not f(key.start):
-            self._convert_indexer_error(key.start, 'slice start value')
-        if not f(key.stop):
-            self._convert_indexer_error(key.stop, 'slice stop value')
-        if not f(key.step):
-            self._convert_indexer_error(key.step, 'slice step value')
-
-    def _convert_slice_indexer_iloc(self, key):
-        """ convert a slice indexer for iloc only """
-        self._validate_slicer(key, lambda v: v is None or is_integer(v))
-        return key
+        for c in ['start','stop','step']:
+            if not f(getattr(key,c)):
+                self._convert_indexer_error(key.start, 'slice {0} value'.format(c))
 
     def _convert_slice_indexer_getitem(self, key, is_index_slice=False):
         """ called from the getitem slicers, determine how to treat the key
@@ -520,6 +512,25 @@ def _convert_slice_indexer_getitem(self, key, is_index_slice=False):
     def _convert_slice_indexer(self, key, typ=None):
         """ convert a slice indexer. disallow floats in the start/stop/step """
 
+        # validate iloc
+        if typ == 'iloc':
+
+            # need to coerce to_int if needed
+            def f(c):
+                v = getattr(key,c)
+                if v is None or is_integer(v):
+                    return v
+
+                # warn if its a convertible float
+                if v == int(v):
+                    warnings.warn("slice indexers when using iloc should be integers "
+                                  "and not floating point",FutureWarning)
+                    return int(v)
+
+                self._convert_indexer_error(v, 'slice {0} value'.format(c))
+
+            return slice(*[ f(c) for c in ['start','stop','step']])
+
         # validate slicers
         def validate(v):
             if v is None or is_integer(v):
@@ -530,7 +541,6 @@ def validate(v):
                 return False
 
             return True
-
         self._validate_slicer(key, validate)
 
         # figure out if this is a positional indexer
@@ -543,9 +553,7 @@ def is_int(v):
         is_index_slice = is_int(start) and is_int(stop)
         is_positional = is_index_slice and not self.is_integer()
 
-        if typ == 'iloc':
-            return self._convert_slice_indexer_iloc(key)
-        elif typ == 'getitem':
+        if typ == 'getitem':
             return self._convert_slice_indexer_getitem(
                 key, is_index_slice=is_index_slice)
 
@@ -1980,7 +1988,7 @@ def _convert_slice_indexer(self, key, typ=None):
         """ convert a slice indexer, by definition these are labels
             unless we are iloc """
         if typ == 'iloc':
-            return self._convert_slice_indexer_iloc(key)
+            return super(Float64Index, self)._convert_slice_indexer(key, typ=typ)
 
         # allow floats here
         self._validate_slicer(
@@ -2386,14 +2394,6 @@ def __unicode__(self):
     def __len__(self):
         return len(self.labels[0])
 
-    def _convert_slice_indexer(self, key, typ=None):
-        """ convert a slice indexer. disallow floats in the start/stop/step """
-
-        if typ == 'iloc':
-            return self._convert_slice_indexer_iloc(key)
-
-        return super(MultiIndex, self)._convert_slice_indexer(key, typ=typ)
-
     def _get_names(self):
         return FrozenList(level.name for level in self.levels)
 
@@ -2997,7 +2997,7 @@ def _drop_from_level(self, labels, level):
         index = self.levels[i]
         values = index.get_indexer(labels)
 
-        mask = -lib.ismember(self.labels[i], set(values))
+        mask = ~lib.ismember(self.labels[i], set(values))
 
         return self[mask]
 

pandas/core/indexing.py

@@ -7,7 +7,7 @@
 import pandas.core.common as com
 from pandas.core.common import (_is_bool_indexer, is_integer_dtype,
                                 _asarray_tuplesafe, is_list_like, isnull,
-                                ABCSeries, ABCDataFrame, ABCPanel)
+                                ABCSeries, ABCDataFrame, ABCPanel, is_float)
 import pandas.lib as lib
 
 import numpy as np
@@ -1319,6 +1319,7 @@ def _get_slice_axis(self, slice_obj, axis=0):
         if not _need_slice(slice_obj):
             return obj
 
+        slice_obj = self._convert_slice_indexer(slice_obj, axis)
         if isinstance(slice_obj, slice):
             return self._slice(slice_obj, axis=axis, typ='iloc')
         else:
@@ -1363,7 +1364,15 @@ def _getitem_axis(self, key, axis=0, validate_iterable=False):
 
     def _convert_to_indexer(self, obj, axis=0, is_setter=False):
         """ much simpler as we only have to deal with our valid types """
-        if self._has_valid_type(obj, axis):
+
+        # make need to convert a float key
+        if isinstance(obj, slice):
+            return self._convert_slice_indexer(obj, axis)
+
+        elif is_float(obj):
+            return self._convert_scalar_indexer(obj, axis)
+
+        elif self._has_valid_type(obj, axis):
             return obj
 
         raise ValueError("Can only index by location with a [%s]" %

pandas/core/internals.py

@@ -1049,7 +1049,7 @@ def to_native_types(self, slicer=None, na_rep='', float_format=None,
         mask = isnull(values)
         values[mask] = na_rep
         if float_format:
-            imask = (-mask).ravel()
+            imask = (~mask).ravel()
             values.flat[imask] = np.array(
                 [float_format % val for val in values.ravel()[imask]])
         return values.tolist()
@@ -1181,7 +1181,7 @@ def to_native_types(self, slicer=None, na_rep=None, **kwargs):
         if na_rep is None:
             na_rep = 'NaT'
         rvalues[mask] = na_rep
-        imask = (-mask).ravel()
+        imask = (~mask).ravel()
         rvalues.flat[imask] = np.array([lib.repr_timedelta64(val)
                                         for val in values.ravel()[imask]],
                                        dtype=object)
@@ -1531,7 +1531,7 @@ def to_native_types(self, slicer=None, na_rep=None, date_format=None,
         if na_rep is None:
             na_rep = 'NaT'
         rvalues[mask] = na_rep
-        imask = (-mask).ravel()
+        imask = (~mask).ravel()
 
         if date_format is None:
             date_formatter = lambda x: Timestamp(x)._repr_base

pandas/core/nanops.py

@@ -190,9 +190,9 @@ def _isfinite(values):
     if issubclass(values.dtype.type, (np.timedelta64, np.datetime64)):
         return isnull(values)
     elif isinstance(values.dtype, object):
-        return -np.isfinite(values.astype('float64'))
+        return ~np.isfinite(values.astype('float64'))
 
-    return -np.isfinite(values)
+    return ~np.isfinite(values)
 
 
 def _na_ok_dtype(dtype):