Merge pull request #9901 from jreback/repr-name

Index repr changes to make them consistent

Author: jreback

doc/source/advanced.rst

@@ -675,10 +675,7 @@ values NOT in the categories, similarly to how you can reindex ANY pandas index.
                                }).set_index('B')
 
       In [11]: df3.index
-      Out[11]:
-      CategoricalIndex([u'a', u'a', u'b', u'b', u'c', u'a'],
-                       categories=[u'a', u'b', u'c'],
-                       ordered=False)
+      Out[11]: CategoricalIndex([u'a', u'a', u'b', u'b', u'c', u'a'], categories=[u'a', u'b', u'c'], ordered=False, name=u'B', dtype='category')
 
       In [12]: pd.concat([df2,df3]
       TypeError: categories must match existing categories when appending

doc/source/whatsnew/v0.16.1.txt

@@ -13,7 +13,10 @@ Highlights include:
 - New section on how-to-contribute to *pandas*, see :ref:`here <contributing>`
 - Revised "Merge, join, and concatenate" documentation, including graphical examples to make it easier to understand each operations, see :ref:`here <merging>`
 - New method ``sample`` for drawing random samples from Series, DataFrames and Panels. See :ref:`here <whatsnew_0161.enhancements.sample>`
-- ``BusinessHour`` date-offset is now supported, see :ref:`here <timeseries.businesshour>`
+- The default ``Index`` printing has changed to a more uniform format, see :ref:`here <whatsnew_0161.index_repr>`
+- ``BusinessHour`` datetime-offset is now supported, see :ref:`here <timeseries.businesshour>`
+
+>>>>>>> more fixes
 -  Further enhancement to the ``.str`` accessor to make string operations easier, see :ref:`here <whatsnew_0161.enhancements.string>`
 
 .. contents:: What's new in v0.16.1
@@ -268,6 +271,52 @@ API changes
 
 - By default, ``read_csv`` and ``read_table`` will now try to infer the compression type based on the file extension. Set ``compression=None`` to restore the previous behavior (no decompression). (:issue:`9770`)
 
+.. _whatsnew_0161.index_repr:
+
+Index Representation
+~~~~~~~~~~~~~~~~~~~~
+
+The string representation of ``Index`` and its sub-classes have now been unified. These will show a single-line display if there are few values; a wrapped multi-line display for a lot of values (but less than ``display.max_seq_items``; if lots of items (> ``display.max_seq_items``) will show a truncated display (the head and tail of the data). The formatting for ``MultiIndex`` is unchanges (a multi-line wrapped display). The display width responds to the option ``display.max_seq_items``, which is defaulted to 100. (:issue:`6482`)
+
+Previous Behavior
+
+.. code-block:: python
+
+   In [2]: pd.Index(range(4),name='foo')
+   Out[2]: Int64Index([0, 1, 2, 3], dtype='int64')
+
+   In [3]: pd.Index(range(104),name='foo')
+   Out[3]: Int64Index([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, ...], dtype='int64')
+
+   In [4]: pd.date_range('20130101',periods=4,name='foo',tz='US/Eastern')
+   Out[4]:
+   <class 'pandas.tseries.index.DatetimeIndex'>
+   [2013-01-01 00:00:00-05:00, ..., 2013-01-04 00:00:00-05:00]
+   Length: 4, Freq: D, Timezone: US/Eastern
+
+   In [5]: pd.date_range('20130101',periods=104,name='foo',tz='US/Eastern')
+   Out[5]:
+   <class 'pandas.tseries.index.DatetimeIndex'>
+   [2013-01-01 00:00:00-05:00, ..., 2013-04-14 00:00:00-04:00]
+   Length: 104, Freq: D, Timezone: US/Eastern
+
+New Behavior
+
+.. ipython:: python
+
+   pd.set_option('display.width',100)
+   pd.Index(range(4),name='foo')
+   pd.Index(range(25),name='foo')
+   pd.Index(range(104),name='foo')
+   pd.Index(['datetime', 'sA', 'sB', 'sC', 'flow', 'error', 'temp', 'ref', 'a_bit_a_longer_one']*2)
+   pd.CategoricalIndex(['a','bb','ccc','dddd'],ordered=True,name='foobar')
+   pd.CategoricalIndex(['a','bb','ccc','dddd']*10,ordered=True,name='foobar')
+   pd.CategoricalIndex(['a','bb','ccc','dddd']*100,ordered=True,name='foobar')
+   pd.CategoricalIndex(np.arange(1000),ordered=True,name='foobar')
+   pd.date_range('20130101',periods=4,name='foo',tz='US/Eastern')
+   pd.date_range('20130101',periods=25,name='foo',tz='US/Eastern')
+   pd.date_range('20130101',periods=104,name='foo',tz='US/Eastern')
+
 .. _whatsnew_0161.deprecations:
 
 Deprecations

pandas/core/common.py

@@ -3132,7 +3132,7 @@ def in_ipython_frontend():
 #    working with straight ascii.
 
 
-def _pprint_seq(seq, _nest_lvl=0, **kwds):
+def _pprint_seq(seq, _nest_lvl=0, max_seq_items=None, **kwds):
     """
     internal. pprinter for iterables. you should probably use pprint_thing()
     rather then calling this directly.
@@ -3144,12 +3144,15 @@ def _pprint_seq(seq, _nest_lvl=0, **kwds):
     else:
         fmt = u("[%s]") if hasattr(seq, '__setitem__') else u("(%s)")
 
-    nitems = get_option("max_seq_items") or len(seq)
+    if max_seq_items is False:
+        nitems = len(seq)
+    else:
+        nitems = max_seq_items or get_option("max_seq_items") or len(seq)
 
     s = iter(seq)
     r = []
     for i in range(min(nitems, len(seq))):  # handle sets, no slicing
-        r.append(pprint_thing(next(s), _nest_lvl + 1, **kwds))
+        r.append(pprint_thing(next(s), _nest_lvl + 1, max_seq_items=max_seq_items, **kwds))
     body = ", ".join(r)
 
     if nitems < len(seq):
@@ -3160,7 +3163,7 @@ def _pprint_seq(seq, _nest_lvl=0, **kwds):
     return fmt % body
 
 
-def _pprint_dict(seq, _nest_lvl=0, **kwds):
+def _pprint_dict(seq, _nest_lvl=0, max_seq_items=None, **kwds):
     """
     internal. pprinter for iterables. you should probably use pprint_thing()
     rather then calling this directly.
@@ -3170,11 +3173,14 @@ def _pprint_dict(seq, _nest_lvl=0, **kwds):
 
     pfmt = u("%s: %s")
 
-    nitems = get_option("max_seq_items") or len(seq)
+    if max_seq_items is False:
+        nitems = len(seq)
+    else:
+        nitems = max_seq_items or get_option("max_seq_items") or len(seq)
 
     for k, v in list(seq.items())[:nitems]:
-        pairs.append(pfmt % (pprint_thing(k, _nest_lvl + 1, **kwds),
-                             pprint_thing(v, _nest_lvl + 1, **kwds)))
+        pairs.append(pfmt % (pprint_thing(k, _nest_lvl + 1, max_seq_items=max_seq_items, **kwds),
+                             pprint_thing(v, _nest_lvl + 1, max_seq_items=max_seq_items, **kwds)))
 
     if nitems < len(seq):
         return fmt % (", ".join(pairs) + ", ...")
@@ -3183,7 +3189,7 @@ def _pprint_dict(seq, _nest_lvl=0, **kwds):
 
 
 def pprint_thing(thing, _nest_lvl=0, escape_chars=None, default_escapes=False,
-                 quote_strings=False):
+                 quote_strings=False, max_seq_items=None):
     """
     This function is the sanctioned way of converting objects
     to a unicode representation.
@@ -3202,6 +3208,8 @@ def pprint_thing(thing, _nest_lvl=0, escape_chars=None, default_escapes=False,
         replacements
     default_escapes : bool, default False
         Whether the input escape characters replaces or adds to the defaults
+    max_seq_items : False, int, default None
+        Pass thru to other pretty printers to limit sequence printing
 
     Returns
     -------
@@ -3240,11 +3248,11 @@ def as_escaped_unicode(thing, escape_chars=escape_chars):
         return compat.text_type(thing)
     elif (isinstance(thing, dict) and
           _nest_lvl < get_option("display.pprint_nest_depth")):
-        result = _pprint_dict(thing, _nest_lvl, quote_strings=True)
+        result = _pprint_dict(thing, _nest_lvl, quote_strings=True, max_seq_items=max_seq_items)
     elif is_sequence(thing) and _nest_lvl < \
             get_option("display.pprint_nest_depth"):
         result = _pprint_seq(thing, _nest_lvl, escape_chars=escape_chars,
-                             quote_strings=quote_strings)
+                             quote_strings=quote_strings, max_seq_items=max_seq_items)
     elif isinstance(thing, compat.string_types) and quote_strings:
         if compat.PY3:
             fmt = "'%s'"