ENH: multiindex formatting

closes #12423

Author: jreback

pandas/indexes/base.py

@@ -608,27 +608,40 @@ def _formatter_func(self):
         """
         return default_pprint
 
-    def _format_data(self):
+    def _format_data(self, display_width=None, justify=False,
+                     max_seq_items=None):
         """
         Return the formatted data as a unicode string
+
+        Parameters
+        ----------
+        display_width: number of spaces for max width, optional
+            inferred to console size or display.width option if None
+        justify: boolean, default False
+            force justification
+        max_seq_items: integer, default None
+            max number of items to display in a sequence
+
         """
         from pandas.formats.format import get_console_size, _get_adjustment
-        display_width, _ = get_console_size()
         if display_width is None:
-            display_width = get_option('display.width') or 80
+            display_width, _ = get_console_size()
+            if display_width is None:
+                display_width = get_option('display.width') or 80
 
         space1 = "\n%s" % (' ' * (len(self.__class__.__name__) + 1))
         space2 = "\n%s" % (' ' * (len(self.__class__.__name__) + 2))
 
         n = len(self)
         sep = ','
-        max_seq_items = get_option('display.max_seq_items') or n
+        max_seq_items = max_seq_items \
+            or get_option('display.max_seq_items') or n
         formatter = self._formatter_func
 
         # do we want to justify (only do so for non-objects)
         is_justify = not (self.inferred_type in ('string', 'unicode') or
                           (self.inferred_type == 'categorical' and
-                           is_object_dtype(self.categories)))
+                           is_object_dtype(self.categories))) or justify
 
         # are we a truncated display
         is_truncated = n > max_seq_items
@@ -663,7 +676,7 @@ def best_len(values):
         else:
 
             if n > max_seq_items:
-                n = min(max_seq_items // 2, 10)
+                n = min(max(max_seq_items // 2, 10), 50)
                 head = [formatter(x) for x in self[:n]]
                 tail = [formatter(x) for x in self[-n:]]
             else:

pandas/indexes/multi.py

@@ -411,11 +411,63 @@ def _format_attrs(self):
         """
         Return a list of tuples of the (attr,formatted_value)
         """
+        # extension space (includes levels/labels)
+        space3 = "\n%s" % (' ' * (len(self.__class__.__name__) + 3 + 6))
+        space4 = "\n%s" % (' ' * (len(self.__class__.__name__) + 4 + 6))
+
+        level_seq_items = get_option('display.max_seq_items') or 100
+        label_seq_items = max(level_seq_items // 2, 10)
+
+        def fd(l, max_seq_items=None, display_width=None, justify=True):
+            # call ._format_data with specified paramaters
+
+            return l._format_data(max_seq_items=max_seq_items,
+                                  display_width=display_width,
+                                  justify=justify)
+
+        # let's see what our best display width for levels / labels are
+        max_levels = max([len(fd(l, max_seq_items=level_seq_items))
+                          for l in self._levels])
+        max_labels = max([len(fd(Index(l), max_seq_items=label_seq_items))
+                          for l in self._labels])
+        display_width = max(max_levels, max_labels)
+        min_display_width = get_option('display.width') or 80
+        if display_width < min_display_width:
+            display_width = min_display_width
+
+        def strip(line):
+            # strip final whitespace + newline
+            line = line.rstrip('\n ')
+
+            # strip header space on each line
+            # replacing with space3 (and nothing for first)
+            lines = [l.lstrip() for l in line.split('\n')]
+            if len(lines) == 1:
+                return line
+            return lines[0] + space4 + space4.join(lines[1:])
+
+        # levels
+        levels = []
+        for l in self._levels:
+            formatted = fd(l,
+                           max_seq_items=level_seq_items,
+                           display_width=display_width)
+            levels.append(strip(formatted))
+        levels = '[' + (space3.join(levels))[:-1] + ']'
+
+        # labels
+        labels = []
+        for l in self._labels:
+            formatted = fd(Index(l),
+                           max_seq_items=label_seq_items,
+                           display_width=display_width)
+            labels.append(strip(formatted))
+        labels = '[' + (space3.join(labels))[:-1] + ']'
+
         attrs = [
-            ('levels', ibase.default_pprint(self._levels,
-                                            max_seq_items=False)),
-            ('labels', ibase.default_pprint(self._labels,
-                                            max_seq_items=False))]
+            ('levels', levels),
+            ('labels', labels),
+        ]
         if not all(name is None for name in self.names):
             attrs.append(('names', ibase.default_pprint(self.names)))
         if self.sortorder is not None:

pandas/tests/indexes/common.py

@@ -157,10 +157,13 @@ def test_dtype_str(self):
     def test_repr_max_seq_item_setting(self):
         # GH10182
         idx = self.create_index()
-        idx = idx.repeat(50)
-        with pd.option_context("display.max_seq_items", None):
-            repr(idx)
-            self.assertFalse('...' in str(idx))
+
+        # format tested sep
+        if not isinstance(idx, MultiIndex):
+            idx = idx.repeat(50)
+            with pd.option_context("display.max_seq_items", None):
+                repr(idx)
+                self.assertFalse('...' in str(idx))
 
     def test_wrong_number_names(self):
         def testit(ind):

pandas/tests/indexes/test_base.py

@@ -1443,69 +1443,72 @@ def test_string_index_repr(self):
             self.assertEqual(coerce(idx), expected)
 
         # truncated
-        idx = pd.Index(['a', 'bb', 'ccc'] * 100)
-        if PY3:
-            expected = u"""\
-Index(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
-       ...
-       'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
-      dtype='object', length=300)"""
+        with cf.option_context('display.width', 200,
+                               'display.max_seq_items', 10):
 
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""\
-Index([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
-       ...
-       u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc'],
-      dtype='object', length=300)"""
+            idx = pd.Index(['a', 'bb', 'ccc'] * 100)
+            if PY3:
+                expected = u"""\
+                Index(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
+                ...
+                'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
+                dtype='object', length=300)"""
 
-            self.assertEqual(coerce(idx), expected)
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""\
+                Index([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
+                ...
+                u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc'],
+                dtype='object', length=300)"""
 
-        # short
-        idx = pd.Index([u'あ', u'いい', u'ううう'])
-        if PY3:
-            expected = u"""Index(['あ', 'いい', 'ううう'], dtype='object')"""
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""\
-Index([u'あ', u'いい', u'ううう'], dtype='object')"""
-            self.assertEqual(coerce(idx), expected)
+                self.assertEqual(coerce(idx), expected)
 
-        # multiple lines
-        idx = pd.Index([u'あ', u'いい', u'ううう'] * 10)
-        if PY3:
-            expected = u"""Index(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
-       'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
-       'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-      dtype='object')"""
+            # short
+            idx = pd.Index([u'あ', u'いい', u'ううう'])
+            if PY3:
+                expected = u"""Index(['あ', 'いい', 'ううう'], dtype='object')"""
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""\
+                Index([u'あ', u'いい', u'ううう'], dtype='object')"""
+                self.assertEqual(coerce(idx), expected)
 
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""Index([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
-       u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
-       u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう'],
-      dtype='object')"""
+            # multiple lines
+            idx = pd.Index([u'あ', u'いい', u'ううう'] * 10)
+            if PY3:
+                expected = u"""Index(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
+                'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
+                'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
+                dtype='object')"""
 
-            self.assertEqual(coerce(idx), expected)
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""Index([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
+                u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
+                u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう'],
+                dtype='object')"""
 
-        # truncated
-        idx = pd.Index([u'あ', u'いい', u'ううう'] * 100)
-        if PY3:
-            expected = u"""Index(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
-       ...
-       'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-      dtype='object', length=300)"""
+                self.assertEqual(coerce(idx), expected)
 
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""Index([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
-       ...
-       u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう'],
-      dtype='object', length=300)"""
+            # truncated
+            idx = pd.Index([u'あ', u'いい', u'ううう'] * 100)
+            if PY3:
+                expected = u"""Index(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
+                ...
+                'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
+                dtype='object', length=300)"""
 
-            self.assertEqual(coerce(idx), expected)
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""Index([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
+                ...
+                u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう'],
+                dtype='object', length=300)"""
+
+                self.assertEqual(coerce(idx), expected)
 
-        # Emable Unicode option -----------------------------------------
+            # Emable Unicode option -----------------------------------------
         with cf.option_context('display.unicode.east_asian_width', True):
 
             # short

pandas/tests/indexes/test_category.py

@@ -562,23 +562,16 @@ def test_string_categorical_index_repr(self):
             self.assertEqual(unicode(idx), expected)
 
         # truncated
-        idx = pd.CategoricalIndex(['a', 'bb', 'ccc'] * 100)
-        if PY3:
-            expected = u"""CategoricalIndex(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
-                  ...
-                  'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
-                 categories=['a', 'bb', 'ccc'], ordered=False, dtype='category', length=300)"""
+        with cf.option_context('display.width', 80):
+            idx = pd.CategoricalIndex(['a', 'bb', 'ccc'] * 100)
+            if PY3:
+                expected = u"""CategoricalIndex([a', bb', ccc', a', bb', ccc', a', bb',\n                  ccc', a', bb', ccc', a', bb', ccc', a',\n                  bb', ccc', a', bb', ccc', a', bb', ccc',\n                  a', bb', ccc', a', bb', ccc', a', bb',\n                  ccc', a', bb', ccc', a', bb', ccc', a',\n                  bb', ccc', a', bb', ccc', a', bb', ccc',\n                  a', bb',\n                  ...\n                  bb', ccc', a', bb', ccc', a', bb', ccc',\n                  a', bb', ccc', a', bb', ccc', a', bb',\n                  ccc', a', bb', ccc', a', bb', ccc', a',\n                  bb', ccc', a', bb', ccc', a', bb', ccc',\n                  a', bb', ccc', a', bb', ccc', a', bb',\n                  ccc', a', bb', ccc', a', bb', ccc', a',\n                  bb', ccc'],\n                 categories=[a', bb', ccc'], ordered=False, dtype='category', length=300)"""  # noqa
 
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""CategoricalIndex([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',
-                  u'ccc', u'a',
-                  ...
-                  u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
-                  u'bb', u'ccc'],
-                 categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category', length=300)"""
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""CategoricalIndex([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',\n                  u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',\n                  u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc',\n                  u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',\n                  u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',\n                  u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc',\n                  u'a', u'bb',\n                  ...\n                  u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc',\n                  u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',\n                  u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',\n                  u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc',\n                  u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',\n                  u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',\n                  u'bb', u'ccc'],\n                 categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category', length=300)"""  # noqa
 
-            self.assertEqual(unicode(idx), expected)
+                self.assertEqual(unicode(idx), expected)
 
         # larger categories
         idx = pd.CategoricalIndex(list('abcdefghijklmmo'))
@@ -622,39 +615,42 @@ def test_string_categorical_index_repr(self):
 
             self.assertEqual(unicode(idx), expected)
 
-        # truncated
-        idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 100)
-        if PY3:
-            expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
-                  ...
-                  'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""
+        with cf.option_context('display.width', 200,
+                               'display.max_seq_items', 10):
 
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
-                  u'ううう', u'あ',
-                  ...
-                  u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
-                  u'いい', u'ううう'],
-                 categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category', length=300)"""
+            # truncated
+            idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 100)
+            if PY3:
+                expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
+                ...
+                'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
+                categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""
 
-            self.assertEqual(unicode(idx), expected)
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
+                u'ううう', u'あ',
+                ...
+                u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
+                u'いい', u'ううう'],
+                categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category', length=300)"""
 
-        # larger categories
-        idx = pd.CategoricalIndex(list(u'あいうえおかきくけこさしすせそ'))
-        if PY3:
-            expected = u"""CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ', 'し',
-                  'す', 'せ', 'そ'],
-                 categories=['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', ...], ordered=False, dtype='category')"""
+                self.assertEqual(unicode(idx), expected)
 
-            self.assertEqual(repr(idx), expected)
-        else:
-            expected = u"""CategoricalIndex([u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', u'け', u'こ',
-                  u'さ', u'し', u'す', u'せ', u'そ'],
-                 categories=[u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', ...], ordered=False, dtype='category')"""
+            # larger categories
+            idx = pd.CategoricalIndex(list(u'あいうえおかきくけこさしすせそ'))
+            if PY3:
+                expected = u"""CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ', 'し',
+                'す', 'せ', 'そ'],
+                categories=['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', ...], ordered=False, dtype='category')"""
 
-            self.assertEqual(unicode(idx), expected)
+                self.assertEqual(repr(idx), expected)
+            else:
+                expected = u"""CategoricalIndex([u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', u'け', u'こ',
+                u'さ', u'し', u'す', u'せ', u'そ'],
+                categories=[u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', ...], ordered=False, dtype='category')"""
+
+                self.assertEqual(unicode(idx), expected)
 
         # Emable Unicode option -----------------------------------------
         with cf.option_context('display.unicode.east_asian_width', True):