ENH: replace uses of np.isscalar with pd.lib.isscalar

closes #8708
closes #12459

Author: Christopher C. Aycock

pandas/computation/ops.py

@@ -10,6 +10,7 @@
 import pandas as pd
 from pandas.compat import PY3, string_types, text_type
 import pandas.core.common as com
+import pandas.lib as lib
 from pandas.core.base import StringMixin
 from pandas.computation.common import _ensure_decoded, _result_type_many
 from pandas.computation.scope import _DEFAULT_GLOBALS
@@ -98,7 +99,7 @@ def update(self, value):
 
     @property
     def isscalar(self):
-        return np.isscalar(self._value)
+        return lib.isscalar(self._value)
 
     @property
     def type(self):

pandas/computation/tests/test_eval.py

@@ -30,6 +30,7 @@
 
 import pandas.computation.expr as expr
 import pandas.util.testing as tm
+import pandas.lib as lib
 from pandas.util.testing import (assert_frame_equal, randbool,
                                  assertRaisesRegexp, assert_numpy_array_equal,
                                  assert_produces_warning, assert_series_equal)
@@ -196,7 +197,7 @@ def check_complex_cmp_op(self, lhs, cmp1, rhs, binop, cmp2):
         ex = '(lhs {cmp1} rhs) {binop} (lhs {cmp2} rhs)'.format(cmp1=cmp1,
                                                                 binop=binop,
                                                                 cmp2=cmp2)
-        scalar_with_in_notin = (np.isscalar(rhs) and (cmp1 in skip_these or
+        scalar_with_in_notin = (lib.isscalar(rhs) and (cmp1 in skip_these or
                                                       cmp2 in skip_these))
         if scalar_with_in_notin:
             with tm.assertRaises(TypeError):
@@ -327,7 +328,7 @@ def check_pow(self, lhs, arith1, rhs):
         expected = self.get_expected_pow_result(lhs, rhs)
         result = pd.eval(ex, engine=self.engine, parser=self.parser)
 
-        if (np.isscalar(lhs) and np.isscalar(rhs) and
+        if (lib.isscalar(lhs) and lib.isscalar(rhs) and
                 _is_py3_complex_incompat(result, expected)):
             self.assertRaises(AssertionError, tm.assert_numpy_array_equal,
                               result, expected)
@@ -360,16 +361,16 @@ def check_compound_invert_op(self, lhs, cmp1, rhs):
         skip_these = 'in', 'not in'
         ex = '~(lhs {0} rhs)'.format(cmp1)
 
-        if np.isscalar(rhs) and cmp1 in skip_these:
+        if lib.isscalar(rhs) and cmp1 in skip_these:
             self.assertRaises(TypeError, pd.eval, ex, engine=self.engine,
                               parser=self.parser, local_dict={'lhs': lhs,
                                                               'rhs': rhs})
         else:
             # compound
-            if np.isscalar(lhs) and np.isscalar(rhs):
+            if lib.isscalar(lhs) and lib.isscalar(rhs):
                 lhs, rhs = map(lambda x: np.array([x]), (lhs, rhs))
             expected = _eval_single_bin(lhs, cmp1, rhs, self.engine)
-            if np.isscalar(expected):
+            if lib.isscalar(expected):
                 expected = not expected
             else:
                 expected = ~expected
@@ -639,17 +640,17 @@ def test_identical(self):
         x = 1
         result = pd.eval('x', engine=self.engine, parser=self.parser)
         self.assertEqual(result, 1)
-        self.assertTrue(np.isscalar(result))
+        self.assertTrue(lib.isscalar(result))
 
         x = 1.5
         result = pd.eval('x', engine=self.engine, parser=self.parser)
         self.assertEqual(result, 1.5)
-        self.assertTrue(np.isscalar(result))
+        self.assertTrue(lib.isscalar(result))
 
         x = False
         result = pd.eval('x', engine=self.engine, parser=self.parser)
         self.assertEqual(result, False)
-        self.assertTrue(np.isscalar(result))
+        self.assertTrue(lib.isscalar(result))
 
         x = np.array([1])
         result = pd.eval('x', engine=self.engine, parser=self.parser)

pandas/core/algorithms.py

@@ -468,7 +468,7 @@ def _get_score(at):
 
         return score
 
-    if np.isscalar(q):
+    if lib.isscalar(q):
         return _get_score(q)
     else:
         q = np.asarray(q, np.float64)

pandas/core/categorical.py

@@ -1901,7 +1901,7 @@ def _convert_to_list_like(list_like):
     if (is_sequence(list_like) or isinstance(list_like, tuple) or
             isinstance(list_like, types.GeneratorType)):
         return list(list_like)
-    elif np.isscalar(list_like):
+    elif lib.isscalar(list_like):
         return [list_like]
     else:
         # is this reached?

pandas/core/common.py

@@ -333,7 +333,7 @@ def notnull(obj):
     pandas.isnull : boolean inverse of pandas.notnull
     """
     res = isnull(obj)
-    if np.isscalar(res):
+    if lib.isscalar(res):
         return not res
     return ~res
 
@@ -343,7 +343,7 @@ def is_null_datelike_scalar(other):
     but guard against passing a non-scalar """
     if other is pd.NaT or other is None:
         return True
-    elif np.isscalar(other):
+    elif lib.isscalar(other):
 
         # a timedelta
         if hasattr(other, 'dtype'):
@@ -489,7 +489,7 @@ def mask_missing(arr, values_to_mask):
 
             # if x is a string and arr is not, then we get False and we must
             # expand the mask to size arr.shape
-            if np.isscalar(mask):
+            if lib.isscalar(mask):
                 mask = np.zeros(arr.shape, dtype=bool)
         else:
 
@@ -1276,7 +1276,7 @@ def changeit():
 
             # we have a scalar or len 0 ndarray
             # and its nan and we are changing some values
-            if (np.isscalar(other) or
+            if (lib.isscalar(other) or
                     (isinstance(other, np.ndarray) and other.ndim < 1)):
                 if isnull(other):
                     return changeit()
@@ -1336,7 +1336,7 @@ def _possibly_downcast_to_dtype(result, dtype):
     or could be an astype of float64->float32
     """
 
-    if np.isscalar(result):
+    if lib.isscalar(result):
         return result
 
     def trans(x):

pandas/core/generic.py

@@ -898,7 +898,7 @@ def bool(self):
         v = self.squeeze()
         if isinstance(v, (bool, np.bool_)):
             return bool(v)
-        elif np.isscalar(v):
+        elif lib.isscalar(v):
             raise ValueError("bool cannot act on a non-boolean single element "
                              "{0}".format(self.__class__.__name__))
 
@@ -1750,10 +1750,10 @@ def xs(self, key, axis=0, level=None, copy=None, drop_level=True):
                 else:
                     return self.take(loc, axis=axis, convert=True)
 
-            if not np.isscalar(loc):
+            if not lib.isscalar(loc):
                 new_index = self.index[loc]
 
-        if np.isscalar(loc):
+        if lib.isscalar(loc):
             from pandas import Series
             new_values = self._data.fast_xs(loc)
 

pandas/core/groupby.py

@@ -712,7 +712,7 @@ def _try_cast(self, result, obj):
         else:
             dtype = obj.dtype
 
-        if not np.isscalar(result):
+        if not lib.isscalar(result):
             result = _possibly_downcast_to_dtype(result, dtype)
 
         return result
@@ -2384,7 +2384,8 @@ def is_in_obj(gpr):
 
 
 def _is_label_like(val):
-    return isinstance(val, compat.string_types) or np.isscalar(val)
+    return (isinstance(val, compat.string_types) or
+            (val is not None and lib.isscalar(val)))
 
 
 def _convert_grouper(axis, grouper):

pandas/core/indexing.py

@@ -4,6 +4,7 @@
 from pandas.compat import range, zip
 import pandas.compat as compat
 import pandas.core.common as com
+import pandas.lib as lib
 from pandas.core.common import (is_bool_indexer, is_integer_dtype,
                                 _asarray_tuplesafe, is_list_like, isnull,
                                 is_null_slice, is_full_slice, ABCSeries,
@@ -67,7 +68,7 @@ def __getitem__(self, key):
         if type(key) is tuple:
             try:
                 values = self.obj.get_value(*key)
-                if np.isscalar(values):
+                if lib.isscalar(values):
                     return values
             except Exception:
                 pass
@@ -677,7 +678,7 @@ def _align_series(self, indexer, ser, multiindex_indexer=False):
 
                     return ser
 
-        elif np.isscalar(indexer):
+        elif lib.isscalar(indexer):
             ax = self.obj._get_axis(1)
 
             if ser.index.equals(ax):
@@ -753,7 +754,7 @@ def _align_frame(self, indexer, df):
                 val = df.reindex(index=ax)._values
             return val
 
-        elif np.isscalar(indexer) and is_panel:
+        elif lib.isscalar(indexer) and is_panel:
             idx = self.obj.axes[1]
             cols = self.obj.axes[2]
 
@@ -960,7 +961,7 @@ def _getitem_nested_tuple(self, tup):
             axis += 1
 
             # if we have a scalar, we are done
-            if np.isscalar(obj) or not hasattr(obj, 'ndim'):
+            if lib.isscalar(obj) or not hasattr(obj, 'ndim'):
                 break
 
             # has the dim of the obj changed?

pandas/core/internals.py

@@ -665,7 +665,7 @@ def _is_scalar_indexer(indexer):
                 if arr_value.ndim == 1:
                     if not isinstance(indexer, tuple):
                         indexer = tuple([indexer])
-                    return all([np.isscalar(idx) for idx in indexer])
+                    return all([lib.isscalar(idx) for idx in indexer])
                 return False
 
             def _is_empty_indexer(indexer):
@@ -702,7 +702,7 @@ def _is_empty_indexer(indexer):
                 values[indexer] = value
 
             # coerce and try to infer the dtypes of the result
-            if np.isscalar(value):
+            if lib.isscalar(value):
                 dtype, _ = _infer_dtype_from_scalar(value)
             else:
                 dtype = 'infer'
@@ -3209,7 +3209,7 @@ def get(self, item, fastpath=True):
                 indexer = np.arange(len(self.items))[isnull(self.items)]
 
                 # allow a single nan location indexer
-                if not np.isscalar(indexer):
+                if not lib.isscalar(indexer):
                     if len(indexer) == 1:
                         loc = indexer.item()
                     else:

pandas/core/nanops.py

@@ -351,7 +351,7 @@ def _get_counts_nanvar(mask, axis, ddof, dtype=float):
     d = count - dtype.type(ddof)
 
     # always return NaN, never inf
-    if np.isscalar(count):
+    if lib.isscalar(count):
         if count <= ddof:
             count = np.nan
             d = np.nan
@@ -623,7 +623,7 @@ def _get_counts(mask, axis, dtype=float):
         return dtype.type(mask.size - mask.sum())
 
     count = mask.shape[axis] - mask.sum(axis)
-    if np.isscalar(count):
+    if lib.isscalar(count):
         return dtype.type(count)
     try:
         return count.astype(dtype)

pandas/core/panel.py

@@ -576,7 +576,7 @@ def __setitem__(self, key, value):
                                  'object was {1}'.format(
                                      shape[1:], tuple(map(int, value.shape))))
             mat = np.asarray(value)
-        elif np.isscalar(value):
+        elif lib.isscalar(value):
             dtype, value = _infer_dtype_from_scalar(value)
             mat = np.empty(shape[1:], dtype=dtype)
             mat.fill(value)
@@ -703,7 +703,7 @@ def _combine(self, other, func, axis=0):
             return self._combine_panel(other, func)
         elif isinstance(other, DataFrame):
             return self._combine_frame(other, func, axis=axis)
-        elif np.isscalar(other):
+        elif lib.isscalar(other):
             return self._combine_const(other, func)
         else:
             raise NotImplementedError("%s is not supported in combine "

pandas/core/series.py

@@ -559,7 +559,7 @@ def __getitem__(self, key):
         try:
             result = self.index.get_value(self, key)
 
-            if not np.isscalar(result):
+            if not lib.isscalar(result):
                 if is_list_like(result) and not isinstance(result, Series):
 
                     # we need to box if we have a non-unique index here

pandas/core/strings.py

@@ -331,7 +331,7 @@ def str_repeat(arr, repeats):
     -------
     repeated : Series/Index of objects
     """
-    if np.isscalar(repeats):
+    if lib.isscalar(repeats):
 
         def rep(x):
             try:

pandas/indexes/base.py

@@ -260,7 +260,7 @@ def __new__(cls, data=None, dtype=None, copy=False, name=None,
         elif hasattr(data, '__array__'):
             return Index(np.asarray(data), dtype=dtype, copy=copy, name=name,
                          **kwargs)
-        elif data is None or np.isscalar(data):
+        elif data is None or lib.isscalar(data):
             cls._scalar_data_error(data)
         else:
             if (tupleize_cols and isinstance(data, list) and data and
@@ -486,7 +486,7 @@ def _coerce_to_ndarray(cls, data):
         """
 
         if not isinstance(data, (np.ndarray, Index)):
-            if data is None or np.isscalar(data):
+            if data is None or lib.isscalar(data):
                 cls._scalar_data_error(data)
 
             # other iterable of some kind
@@ -1269,7 +1269,7 @@ def __getitem__(self, key):
         getitem = self._data.__getitem__
         promote = self._shallow_copy
 
-        if np.isscalar(key):
+        if lib.isscalar(key):
             return getitem(key)
 
         if isinstance(key, slice):
@@ -1282,7 +1282,7 @@ def __getitem__(self, key):
 
         key = _values_from_object(key)
         result = getitem(key)
-        if not np.isscalar(result):
+        if not lib.isscalar(result):
             return promote(result)
         else:
             return result
@@ -1941,7 +1941,7 @@ def get_value(self, series, key):
                 raise e1
         except TypeError:
             # python 3
-            if np.isscalar(key):  # pragma: no cover
+            if lib.isscalar(key):  # pragma: no cover
                 raise IndexError(key)
             raise InvalidIndexError(key)
 

pandas/indexes/multi.py

@@ -978,7 +978,7 @@ def __setstate__(self, state):
         self._reset_identity()
 
     def __getitem__(self, key):
-        if np.isscalar(key):
+        if lib.isscalar(key):
             retval = []
             for lev, lab in zip(self.levels, self.labels):
                 if lab[key] == -1:

pandas/indexes/numeric.py

@@ -295,7 +295,7 @@ def _format_native_types(self, na_rep='', float_format=None, decimal='.',
 
     def get_value(self, series, key):
         """ we always want to get an index value, never a value """
-        if not np.isscalar(key):
+        if not lib.isscalar(key):
             raise InvalidIndexError
 
         from pandas.core.indexing import maybe_droplevels
@@ -305,7 +305,7 @@ def get_value(self, series, key):
         loc = self.get_loc(k)
         new_values = com._values_from_object(series)[loc]
 
-        if np.isscalar(new_values) or new_values is None:
+        if lib.isscalar(new_values) or new_values is None:
             return new_values
 
         new_index = self[loc]