BUG: show series length in repr when truncated (GH15962) (#15974)

Author: jorisvandenbossche

doc/source/whatsnew/v0.20.0.txt

@@ -518,6 +518,8 @@ Other Enhancements
 - :method:`~MultiIndex.remove_unused_levels` has been added to facilitate :ref:`removing unused levels <advanced.shown_levels>`. (:issue:`15694`)
 - ``pd.read_csv()`` will now raise a ``ParserError`` error whenever any parsing error occurs (:issue:`15913`, :issue:`15925`)
 - ``pd.read_csv()`` now supports the ``error_bad_lines`` and ``warn_bad_lines`` arguments for the Python parser (:issue:`15925`)
+- The ``display.show_dimensions`` option can now also be used to specify
+  whether the length of a ``Series`` should be shown in its repr (:issue:`7117`).
 - ``parallel_coordinates()`` has gained a ``sort_labels`` keyword arg that sorts class labels and the colours assigned to them (:issue:`15908`)
 
 
@@ -1560,6 +1562,7 @@ I/O
 - Bug in ``pd.read_hdf()`` passing a ``Timestamp`` to the ``where`` parameter with a non date column (:issue:`15492`)
 - Bug in ``DataFrame.to_stata()`` and ``StataWriter`` which produces incorrectly formatted files to be produced for some locales (:issue:`13856`)
 - Bug in ``StataReader`` and ``StataWriter`` which allows invalid encodings (:issue:`15723`)
+- Bug in the ``Series`` repr not showing the length when the output was truncated (:issue:`15962`).
 
 Plotting
 ^^^^^^^^

pandas/core/series.py

@@ -980,9 +980,10 @@ def __unicode__(self):
         width, height = get_terminal_size()
         max_rows = (height if get_option("display.max_rows") == 0 else
                     get_option("display.max_rows"))
+        show_dimensions = get_option("display.show_dimensions")
 
         self.to_string(buf=buf, name=self.name, dtype=self.dtype,
-                       max_rows=max_rows)
+                       max_rows=max_rows, length=show_dimensions)
         result = buf.getvalue()
 
         return result
@@ -1021,44 +1022,27 @@ def to_string(self, buf=None, na_rep='NaN', float_format=None, header=True,
         formatted : string (if not buffer passed)
         """
 
-        the_repr = self._get_repr(float_format=float_format, na_rep=na_rep,
-                                  header=header, index=index, length=length,
-                                  dtype=dtype, name=name, max_rows=max_rows)
-
-        # catch contract violations
-        if not isinstance(the_repr, compat.text_type):
-            raise AssertionError("result must be of type unicode, type"
-                                 " of result is {0!r}"
-                                 "".format(the_repr.__class__.__name__))
-
-        if buf is None:
-            return the_repr
-        else:
-            try:
-                buf.write(the_repr)
-            except AttributeError:
-                with open(buf, 'w') as f:
-                    f.write(the_repr)
-
-    def _get_repr(self, name=False, header=True, index=True, length=True,
-                  dtype=True, na_rep='NaN', float_format=None, max_rows=None):
-        """
-
-        Internal function, should always return unicode string
-        """
         formatter = fmt.SeriesFormatter(self, name=name, length=length,
                                         header=header, index=index,
                                         dtype=dtype, na_rep=na_rep,
                                         float_format=float_format,
                                         max_rows=max_rows)
         result = formatter.to_string()
 
-        # TODO: following check prob. not neces.
+        # catch contract violations
         if not isinstance(result, compat.text_type):
             raise AssertionError("result must be of type unicode, type"
                                  " of result is {0!r}"
                                  "".format(result.__class__.__name__))
-        return result
+
+        if buf is None:
+            return result
+        else:
+            try:
+                buf.write(result)
+            except AttributeError:
+                with open(buf, 'w') as f:
+                    f.write(result)
 
     def __iter__(self):
         """ provide iteration over the values of the Series

pandas/io/formats/format.py

@@ -199,7 +199,8 @@ def _get_footer(self):
                                        escape_chars=('\t', '\r', '\n'))
             footer += ("Name: %s" % series_name) if name is not None else ""
 
-        if self.length:
+        if (self.length is True or
+                (self.length == 'truncate' and self.truncate_v)):
             if footer:
                 footer += ', '
             footer += 'Length: %d' % len(self.series)

pandas/tests/io/formats/test_format.py

@@ -1770,12 +1770,14 @@ def test_east_asian_unicode_series(self):
                        name=u'おおおおおおお')
 
             expected = (u"0       あ\n     ... \n"
-                        u"3    ええええ\nName: おおおおおおお, dtype: object")
+                        u"3    ええええ\n"
+                        u"Name: おおおおおおお, Length: 4, dtype: object")
             self.assertEqual(_rep(s), expected)
 
             s.index = [u'ああ', u'いいいい', u'う', u'えええ']
             expected = (u"ああ        あ\n       ... \n"
-                        u"えええ    ええええ\nName: おおおおおおお, dtype: object")
+                        u"えええ    ええええ\n"
+                        u"Name: おおおおおおお, Length: 4, dtype: object")
             self.assertEqual(_rep(s), expected)
 
         # Emable Unicode option -----------------------------------------
@@ -1846,14 +1848,15 @@ def test_east_asian_unicode_series(self):
                 s = Series([u'あ', u'いい', u'ううう', u'ええええ'],
                            name=u'おおおおおおお')
                 expected = (u"0          あ\n       ...   \n"
-                            u"3    ええええ\nName: おおおおおおお, dtype: object")
+                            u"3    ええええ\n"
+                            u"Name: おおおおおおお, Length: 4, dtype: object")
                 self.assertEqual(_rep(s), expected)
 
                 s.index = [u'ああ', u'いいいい', u'う', u'えええ']
                 expected = (u"ああ            あ\n"
                             u"            ...   \n"
                             u"えええ    ええええ\n"
-                            u"Name: おおおおおおお, dtype: object")
+                            u"Name: おおおおおおお, Length: 4, dtype: object")
                 self.assertEqual(_rep(s), expected)
 
             # ambiguous unicode
@@ -2021,7 +2024,8 @@ def test_max_multi_index_display(self):
     # Make sure #8532 is fixed
     def test_consistent_format(self):
         s = pd.Series([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0.9999, 1, 1] * 10)
-        with option_context("display.max_rows", 10):
+        with option_context("display.max_rows", 10,
+                            "display.show_dimensions", False):
             res = repr(s)
         exp = ('0      1.0000\n1      1.0000\n2      1.0000\n3      '
                '1.0000\n4      1.0000\n        ...  \n125    '
@@ -2040,7 +2044,8 @@ def chck_ncols(self, s):
 
     def test_format_explicit(self):
         test_sers = gen_series_formatting()
-        with option_context("display.max_rows", 4):
+        with option_context("display.max_rows", 4,
+                            "display.show_dimensions", False):
             res = repr(test_sers['onel'])
             exp = '0     a\n1     a\n     ..\n98    a\n99    a\ndtype: object'
             self.assertEqual(exp, res)
@@ -2087,6 +2092,22 @@ def getndots(s):
             strrepr = repr(s).replace('\n', '')
         self.assertEqual(getndots(strrepr), 3)
 
+    def test_show_dimensions(self):
+        # gh-7117
+        s = Series(range(5))
+
+        assert 'Length' not in repr(s)
+
+        with option_context("display.max_rows", 4):
+            assert 'Length' in repr(s)
+
+        with option_context("display.show_dimensions", True):
+            assert 'Length' in repr(s)
+
+        with option_context("display.max_rows", 4,
+                            "display.show_dimensions", False):
+            assert 'Length' not in repr(s)
+
     def test_to_string_name(self):
         s = Series(range(100), dtype='int64')
         s.name = 'myser'

pandas/tests/sparse/test_format.py

@@ -33,7 +33,7 @@ def test_sparse_max_row(self):
             # GH 10560
             result = repr(s)
             exp = ("0    1.0\n    ... \n4    NaN\n"
-                   "dtype: float64\nBlockIndex\n"
+                   "Length: 5, dtype: float64\nBlockIndex\n"
                    "Block locations: array([0, 3]{0})\n"
                    "Block lengths: array([1, 1]{0})".format(dfm))
             self.assertEqual(result, exp)
@@ -52,7 +52,8 @@ def test_sparse_mi_max_row(self):
                "Block lengths: array([1, 1]{0})".format(dfm))
         self.assertEqual(result, exp)
 
-        with option_context("display.max_rows", 3):
+        with option_context("display.max_rows", 3,
+                            "display.show_dimensions", False):
             # GH 13144
             result = repr(s)
             exp = ("A  0    1.0\n       ... \nC  2    NaN\n"
@@ -77,7 +78,7 @@ def test_sparse_bool(self):
         with option_context("display.max_rows", 3):
             result = repr(s)
             exp = ("0     True\n     ...  \n5    False\n"
-                   "dtype: bool\nBlockIndex\n"
+                   "Length: 6, dtype: bool\nBlockIndex\n"
                    "Block locations: array([0, 3]{0})\n"
                    "Block lengths: array([1, 1]{0})".format(dtype))
             self.assertEqual(result, exp)
@@ -94,7 +95,8 @@ def test_sparse_int(self):
                "Block lengths: array([1, 1]{0})".format(dtype))
         self.assertEqual(result, exp)
 
-        with option_context("display.max_rows", 3):
+        with option_context("display.max_rows", 3,
+                            "display.show_dimensions", False):
             result = repr(s)
             exp = ("0    0\n    ..\n5    0\n"
                    "dtype: int64\nBlockIndex\n"

pandas/tests/test_categorical.py

@@ -2088,7 +2088,7 @@ def test_repr(self):
 
         a = pd.Series(pd.Categorical(["a", "b"] * 25))
         exp = u("0     a\n1     b\n" + "     ..\n" + "48    a\n49    b\n" +
-                "dtype: category\nCategories (2, object): [a, b]")
+                "Length: 50, dtype: category\nCategories (2, object): [a, b]")
         with option_context("display.max_rows", 5):
             self.assertEqual(exp, repr(a))