Feature/groupby repr ellipses 1135

pandas/core/frame.py

@@ -554,7 +554,7 @@ def _repr_fits_horizontal_(self, ignore_width=False):
         Check if full repr fits in horizontal boundaries imposed by the display
         options width and max_columns.
 
-        In case off non-interactive session, no boundaries apply.
+        In case of non-interactive session, no boundaries apply.
 
         `ignore_width` is here so ipnb+HTML output can behave the way
         users expect. display.max_columns remains in effect.

pandas/core/groupby/grouper.py

@@ -236,7 +236,6 @@ class Grouping(object):
 
     def __init__(self, index, grouper=None, obj=None, name=None, level=None,
                  sort=True, observed=False, in_axis=False):
-
         self.name = name
         self.level = level
         self.grouper = _convert_grouper(index, grouper)

pandas/core/groupby/ops.py

@@ -235,6 +235,7 @@ def size(self):
     @cache_readonly
     def groups(self):
         """ dict {group name -> group labels} """
+
         if len(self.groupings) == 1:
             return self.groupings[0].groups
         else:
@@ -361,7 +362,7 @@ def get_group_levels(self):
 
     def _is_builtin_func(self, arg):
         """
-        if we define an builtin function for this argument, return it,
+        if we define a builtin function for this argument, return it,
         otherwise return the arg
         """
         return SelectionMixin._builtin_table.get(arg, arg)

pandas/core/indexes/base.py

@@ -38,6 +38,7 @@
 from pandas.core.arrays import ExtensionArray
 from pandas.core.base import IndexOpsMixin, PandasObject
 import pandas.core.common as com
+from pandas.core.config import get_option
 from pandas.core.indexes.frozen import FrozenList
 import pandas.core.missing as missing
 from pandas.core.ops import get_op_result_name, make_invalid_op
@@ -4493,7 +4494,7 @@ def groupby(self, values):
         # map to the label
         result = {k: self.take(v) for k, v in compat.iteritems(result)}
 
-        return result
+        return IndexGroupbyGroups(result)
 
     def map(self, mapper, na_action=None):
         """
@@ -5290,6 +5291,27 @@ def _add_logical_methods_disabled(cls):
 Index._add_comparison_methods()
 
 
+class IndexGroupbyGroups(dict):
+    def __repr__(self):
+        nitems = get_option('display.max_rows') or len(self)
+
+        fmt = u("{{{things}}}")
+        pfmt = u("{key}: {val}")
+
+        pairs = []
+        for k, v in list(self.items()):
+            pairs.append(pfmt.format(key=k, val=v))
+
+        if nitems < len(self):
+            print("Truncating repr")
+            start_cnt, end_cnt = nitems - int(nitems / 2), int(nitems / 2)
+            return fmt.format(things=", ".join(pairs[:start_cnt]) +
+                                     ", ... , " +
+                                     ", ".join(pairs[-end_cnt:]))
+        else:
+            return fmt.format(things=", ".join(pairs))
+
+
 def ensure_index_from_sequences(sequences, names=None):
     """
     Construct an index from sequences of data.

pandas/io/formats/printing.py

@@ -95,7 +95,7 @@ def _join_unicode(lines, sep=''):
 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.
+    rather than calling this directly.
 
     bounds length of printed sequence, depending on options
     """
@@ -127,8 +127,9 @@ def _pprint_seq(seq, _nest_lvl=0, max_seq_items=None, **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.
+    rather than calling this directly.
     """
+
     fmt = u("{{{things}}}")
     pairs = []
 

pandas/tests/io/formats/test_format.py

@@ -1797,6 +1797,22 @@ def test_period(self):
         assert str(df) == exp
 
 
+class TestDataFrameGroupByFormatting(object):
+    def test_groups_repr_truncates(self):
+        df = pd.DataFrame({
+            'a': [1, 1, 1, 2, 2, 3],
+            'b': [1, 2, 3, 4, 5, 6]
+        })
+
+        with option_context('display.max_rows', 2):
+            x = df.groupby('a').groups
+            assert ', ... ,' in x.__repr__()
+
+        with option_context('display.max_rows', 5):
+            x = df.groupby('a').groups
+            assert ', ... ,' not in x.__repr__()
+
+
 def gen_series_formatting():
     s1 = pd.Series(['a'] * 100)
     s2 = pd.Series(['ab'] * 100)