test fixes, enhancements, and code review

Author: jreback

doc/source/whatsnew/v0.18.0.txt

@@ -19,6 +19,7 @@ Highlights include:
 
 - Window functions are now methods on ``.groupby`` like objects, see :ref:`here <whatsnew_0180.enhancements.moments>`.
 - ``pd.test()`` top-level nose test runner is available (:issue:`4327`)
+- Adding support for a ``RangeIndex`` as a specialized form of the ``Int64Index`` for memory savings, see :ref:`here <whatsnew_0180.enhancements.rangeindex>`.
 
 Check the :ref:`API Changes <whatsnew_0180.api>` and :ref:`deprecations <whatsnew_0180.deprecations>` before updating.
 
@@ -102,6 +103,39 @@ And multiple aggregations
    r.agg({'A' : ['mean','std'],
           'B' : ['mean','std']})
 
+.. _whatsnew_0180.enhancements.rangeindex:
+
+Range Index
+^^^^^^^^^^^
+
+A ``RangeIndex`` has been added to the ``Int64Index`` sub-classes to support a memory saving alternative for common use cases. This has a similar implementation to the python ``range`` object (``xrange`` in python 2), in that it only stores the start, stop, and step values for the index. It will transparently interact with the user API, converting to ``Int64Index`` if needed.
+
+This will now be the default constructed index for ``NDFrame`` objects, rather than previous an ``Int64Index``. (:issue:`939`)
+
+Previous Behavior:
+
+.. code-block:: python
+
+   In [3]: s = Series(range(1000))
+
+   In [4]: s.index
+   Out[4]:
+   Int64Index([  0,   1,   2,   3,   4,   5,   6,   7,   8,   9,
+               ...
+               990, 991, 992, 993, 994, 995, 996, 997, 998, 999], dtype='int64', length=1000)
+
+   In [6]: s.index.nbytes
+   Out[6]: 8000
+
+
+New Behavior:
+
+.. ipython:: python
+
+   s = Series(range(1000))
+   s.index
+   s.index.nbytes
+
 .. _whatsnew_0180.enhancements.other:
 
 Other enhancements

pandas/core/api.py

@@ -8,7 +8,8 @@
 from pandas.core.categorical import Categorical
 from pandas.core.groupby import Grouper
 from pandas.core.format import set_eng_float_format
-from pandas.core.index import Index, CategoricalIndex, Int64Index, RangeIndex, Float64Index, MultiIndex
+from pandas.core.index import (Index, CategoricalIndex, Int64Index,
+                               RangeIndex, Float64Index, MultiIndex)
 
 from pandas.core.series import Series, TimeSeries
 from pandas.core.frame import DataFrame

pandas/core/common.py

@@ -1800,8 +1800,7 @@ def is_bool_indexer(key):
 
 def _default_index(n):
     from pandas.core.index import RangeIndex
-    result = RangeIndex(0, int(n), name=None)
-    return result
+    return RangeIndex(0, n, name=None)
 
 
 def ensure_float(arr):
@@ -2200,11 +2199,6 @@ def is_integer_dtype(arr_or_dtype):
             not issubclass(tipo, (np.datetime64, np.timedelta64)))
 
 
-def is_int64_dtype(arr_or_dtype):
-    tipo = _get_dtype_type(arr_or_dtype)
-    return issubclass(tipo, np.int64)
-
-
 def is_int_or_datetime_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return (issubclass(tipo, np.integer) or

pandas/core/dtypes.py

@@ -214,5 +214,6 @@ def __eq__(self, other):
         if isinstance(other, compat.string_types):
             return other == self.name
 
-        return isinstance(other, DatetimeTZDtype) and self.unit == other.unit \
-            and self.tz == other.tz
+        return isinstance(other, DatetimeTZDtype) and \
+            self.unit == other.unit and \
+            str(self.tz) == str(other.tz)