ENH: repr now shows index name #6482

move tests to generically tests for index
generify __unicode__ for Index

adjust index display to max_seq_items

Author: hsperr

pandas/core/index.py

@@ -392,8 +392,68 @@ def __unicode__(self):
         Invoked by unicode(df) in py2 only. Yields a Unicode String in both
         py2/py3.
         """
-        prepr = default_pprint(self)
-        return "%s(%s, dtype='%s')" % (type(self).__name__, prepr, self.dtype)
+        klass = self.__class__.__name__
+        data = self._format_data()
+        attrs = self._format_attrs()
+        max_seq_items = get_option('display.max_seq_items')
+        if len(self) > max_seq_items:
+            space = "\n%s" % (' ' * (len(klass) + 1))
+        else:
+            space = " "
+
+        prepr = (u(",%s") % space).join([u("%s=%s") % (k, v)
+                                          for k, v in attrs])
+        res = u("%s(%s,%s%s)") % (klass,
+                                  data,
+                                  space,
+                                  prepr)
+
+        return res
+
+    @property
+    def _formatter_func(self):
+        """
+        Return the formatted data as a unicode string
+        """
+        return default_pprint
+
+    def _format_data(self):
+        """
+        Return the formatted data as a unicode string
+        """
+
+        max_seq_items = get_option('display.max_seq_items')
+        formatter = self._formatter_func
+        n = len(self)
+        if n == 0:
+            summary = '[]'
+        elif n == 1:
+            first = formatter(self[0])
+            summary = '[%s]' % first
+        elif n == 2:
+            first = formatter(self[0])
+            last = formatter(self[-1])
+            summary = '[%s, %s]' % (first, last)
+        elif n > max_seq_items:
+            n = min(max_seq_items//2,2)
+            head = ', '.join([ formatter(x) for x in self[:n] ])
+            tail = ', '.join([ formatter(x) for x in self[-n:] ])
+            summary = '[%s, ..., %s]' % (head, tail)
+        else:
+            summary = "[%s]" % ', '.join([ formatter(x) for x in self ])
+
+        return summary
+
+
+    def _format_attrs(self):
+        """
+        Return a list of tuples of the (attr,formatted_value)
+        """
+        attrs = []
+        if self.name is not None:
+            attrs.append(('name',default_pprint(self.name)))
+        attrs.append(('dtype',"'%s'" % self.dtype))
+        return attrs
 
     def to_series(self, **kwargs):
         """

pandas/tests/test_index.py

@@ -120,6 +120,19 @@ def test_ndarray_compat_properties(self):
         idx.nbytes
         idx.values.nbytes
 
+    def test_repr_roundtrip(self):
+
+        idx = self.create_index()
+        tm.assert_index_equal(eval(repr(idx)),idx)
+
+    def test_str(self):
+
+        # test the string repr
+        idx = self.create_index()
+        idx.name = 'foo'
+        self.assertTrue("'foo'" in str(idx))
+        self.assertTrue(idx.__class__.__name__ in str(idx))
+
     def test_wrong_number_names(self):
         def testit(ind):
             ind.names = ["apple", "banana", "carrot"]
@@ -2475,6 +2488,26 @@ def test_slice_keep_name(self):
 
 class DatetimeLike(Base):
 
+    def test_repr_roundtrip(self):
+        raise nose.SkipTest("Short reprs are not supported repr for Datetimelike indexes")
+
+    def test_str(self):
+
+        # test the string repr
+        idx = self.create_index()
+        idx.name = 'foo'
+        self.assertTrue("length=%s" % len(idx) in str(idx))
+        self.assertTrue("u'foo'" in str(idx))
+        self.assertTrue(idx.__class__.__name__ in str(idx))
+
+        if hasattr(idx,'tz'):
+            if idx.tz is not None:
+                self.assertTrue("tz='%s'" % idx.tz in str(idx))
+            else:
+                self.assertTrue("tz=None" in str(idx))
+        if hasattr(idx,'freq'):
+            self.assertTrue("freq='%s'" % idx.freqstr in str(idx))
+
     def test_view(self):
         super(DatetimeLike, self).test_view()
 
@@ -4388,8 +4421,9 @@ def test_repr_with_unicode_data(self):
             index = pd.DataFrame(d).set_index(["a", "b"]).index
             self.assertFalse("\\u" in repr(index))  # we don't want unicode-escaped
 
-    def test_repr_roundtrip(self):
-        tm.assert_index_equal(eval(repr(self.index)), self.index)
+    def test_str(self):
+        # tested elsewhere
+        pass
 
     def test_unicode_string_with_unicode(self):
         d = {"a": [u("\u05d0"), 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]}

pandas/tseries/base.py

@@ -265,30 +265,24 @@ def _formatter_func(self):
         """
         return str
 
-    def _format_footer(self):
-        raise AbstractMethodError(self)
-
-    def __unicode__(self):
-        formatter = self._formatter_func
-        summary = str(self.__class__) + '\n'
-
-        n = len(self)
-        if n == 0:
-            pass
-        elif n == 1:
-            first = formatter(self[0])
-            summary += '[%s]\n' % first
-        elif n == 2:
-            first = formatter(self[0])
-            last = formatter(self[-1])
-            summary += '[%s, %s]\n' % (first, last)
-        else:
-            first = formatter(self[0])
-            last = formatter(self[-1])
-            summary += '[%s, ..., %s]\n' % (first, last)
-
-        summary += self._format_footer()
-        return summary
+    def _format_attrs(self):
+        """
+        Return a list of tuples of the (attr,formatted_value)
+        """
+        attrs = super(DatetimeIndexOpsMixin, self)._format_attrs()
+        attrs.append(('length',len(self)))
+        for attrib in self._attributes:
+            if attrib == 'freq':
+                freq = self.freqstr
+                if freq is not None:
+                    freq = "'%s'" % freq
+                attrs.append(('freq',freq))
+            elif attrib == 'tz':
+                tz = self.tz
+                if tz is not None:
+                    tz = "'%s'" % tz
+                attrs.append(('tz',tz))
+        return attrs
 
     @cache_readonly
     def _resolution(self):

pandas/tseries/index.py

@@ -597,7 +597,7 @@ def _is_dates_only(self):
     def _formatter_func(self):
         from pandas.core.format import _get_format_datetime64
         formatter = _get_format_datetime64(is_dates_only=self._is_dates_only)
-        return lambda x: formatter(x, tz=self.tz)
+        return lambda x: "'%s'" % formatter(x, tz=self.tz)
 
     def __reduce__(self):
 
@@ -684,10 +684,6 @@ def _format_native_types(self, na_rep=u('NaT'),
     def to_datetime(self, dayfirst=False):
         return self.copy()
 
-    def _format_footer(self):
-        tagline = 'Length: %d, Freq: %s, Timezone: %s'
-        return tagline % (len(self), self.freqstr, self.tz)
-
     def astype(self, dtype):
         dtype = np.dtype(dtype)
 

pandas/tseries/period.py

@@ -697,10 +697,6 @@ def __array_finalize__(self, obj):
         self.name = getattr(obj, 'name', None)
         self._reset_identity()
 
-    def _format_footer(self):
-        tagline = 'Length: %d, Freq: %s'
-        return tagline % (len(self), self.freqstr)
-
     def take(self, indices, axis=None):
         """
         Analogous to ndarray.take

pandas/tseries/tdi.py

@@ -274,10 +274,6 @@ def _formatter_func(self):
         from pandas.core.format import _get_format_timedelta64
         return _get_format_timedelta64(self, box=True)
 
-    def _format_footer(self):
-        tagline = 'Length: %d, Freq: %s'
-        return tagline % (len(self), self.freqstr)
-
     def __setstate__(self, state):
         """Necessary for making this object picklable"""
         if isinstance(state, dict):