Merge pull request #2930 from jreback/series_format

BUG: formatting for Series was printing multiple Dtype lines for long display

Author: jreback

pandas/core/format.py

@@ -65,14 +65,14 @@
 
 class SeriesFormatter(object):
 
-    def __init__(self, series, buf=None, header=True, length=True,
-                 na_rep='NaN', name=False, float_format=None, dtype=True):
+    def __init__(self, series, buf=None, header=True, length=True, dtype=True,
+                 na_rep='NaN', name=False, float_format=None):
         self.series = series
         self.buf = buf if buf is not None else StringIO(u"")
         self.name = name
-        self.dtype = dtype
         self.na_rep = na_rep
         self.length = length
+        self.dtype  = dtype
         self.header = header
 
         if float_format is None:

pandas/core/series.py

@@ -1047,9 +1047,10 @@ def __unicode__(self):
         elif len(self.index) > 0:
             result = self._get_repr(print_header=True,
                                     length=len(self) > 50,
-                                    name=True)
+                                    name=True,
+                                    dtype=True)
         else:
-            result = u'Series([], dtype=%s)' % self.dtype
+            result = u'Series([], Dtype: %s)' % self.dtype
 
         assert type(result) == unicode
         return result
@@ -1069,9 +1070,10 @@ def _tidy_repr(self, max_vals=20):
         """
         num = max_vals // 2
         head = self[:num]._get_repr(print_header=True, length=False,
-                                    name=False)
+                                    dtype=False, name=False)
         tail = self[-(max_vals - num):]._get_repr(print_header=False,
                                                   length=False,
+                                                  dtype=False,
                                                   name=False)
         result = head + '\n...\n' + tail
         result = '%s\n%s' % (result, self._repr_footer())
@@ -1085,7 +1087,7 @@ def _repr_footer(self):
                                              com.pprint_thing(self.dtype.name))
 
     def to_string(self, buf=None, na_rep='NaN', float_format=None,
-                  nanRep=None, length=False, name=False):
+                  nanRep=None, length=False, dtype=False, name=False):
         """
         Render a string representation of the Series
 
@@ -1100,6 +1102,8 @@ def to_string(self, buf=None, na_rep='NaN', float_format=None,
             default None
         length : boolean, default False
             Add the Series length
+        dtype : boolean, default False
+            Add the Series dtype
         name : boolean, default False
             Add the Series name (which may be None)
 
@@ -1114,7 +1118,7 @@ def to_string(self, buf=None, na_rep='NaN', float_format=None,
             na_rep = nanRep
 
         the_repr = self._get_repr(float_format=float_format, na_rep=na_rep,
-                                  length=length, name=name)
+                                  length=length, dtype=dtype, name=name)
 
         assert type(the_repr) == unicode
 
@@ -1123,15 +1127,15 @@ def to_string(self, buf=None, na_rep='NaN', float_format=None,
         else:
             print >> buf, the_repr
 
-    def _get_repr(self, name=False, print_header=False, length=True,
+    def _get_repr(self, name=False, print_header=False, length=True, dtype=True,
                   na_rep='NaN', float_format=None):
         """
 
         Internal function, should always return unicode string
         """
 
         formatter = fmt.SeriesFormatter(self, name=name, header=print_header,
-                                        length=length, na_rep=na_rep,
+                                        length=length, dtype=dtype, na_rep=na_rep,
                                         float_format=float_format)
         result = formatter.to_string()
         assert type(result) == unicode
@@ -3287,7 +3291,8 @@ def _repr_footer(self):
 
         namestr = "Name: %s, " % str(
             self.name) if self.name is not None else ""
-        return '%s%sLength: %d' % (freqstr, namestr, len(self))
+        return '%s%sLength: %d, Dtype: %s' % (freqstr, namestr, len(self),
+                                              com.pprint_thing(self.dtype.name))
 
     def to_timestamp(self, freq=None, how='start', copy=True):
         """

pandas/tests/test_format.py

@@ -585,6 +585,15 @@ def test_wide_repr_wide_long_columns(self):
             self.assertTrue('ccccc' in result)
             self.assertTrue('ddddd' in result)
 
+    def test_long_series(self):
+        n = 1000
+        s = Series(np.random.randint(-50,50,n),index=['s%04d' % x for x in xrange(n)], dtype='int64')
+
+        import re
+        str_rep = str(s)
+        nmatches = len(re.findall('Dtype',str_rep))
+        self.assert_(nmatches == 1)
+
     def test_to_string(self):
         from pandas import read_table
         import re
@@ -1119,7 +1128,7 @@ def test_to_string(self):
         format = '%.4f'.__mod__
         result = self.ts.to_string(float_format=format)
         result = [x.split()[1] for x in result.split('\n')]
-        expected = [format(x) for x in self.ts] + [u'float64']
+        expected = [format(x) for x in self.ts]
         self.assertEqual(result, expected)
 
         # empty string
@@ -1132,7 +1141,7 @@ def test_to_string(self):
         # name and length
         cp = self.ts.copy()
         cp.name = 'foo'
-        result = cp.to_string(length=True, name=True)
+        result = cp.to_string(length=True, name=True, dtype=True)
         last_line = result.split('\n')[-1].strip()
         self.assertEqual(last_line, "Freq: B, Name: foo, Length: %d, Dtype: float64" % len(cp))
 
@@ -1149,8 +1158,7 @@ def test_to_string_mixed(self):
         expected = (u'0     foo\n'
                     u'1     NaN\n'
                     u'2   -1.23\n'
-                    u'3    4.56\n'
-                    u'Dtype: object')
+                    u'3    4.56')
         self.assertEqual(result, expected)
 
         # but don't count NAs as floats
@@ -1159,17 +1167,15 @@ def test_to_string_mixed(self):
         expected = (u'0    foo\n'
                     '1    NaN\n'
                     '2    bar\n'
-                    '3    baz\n'
-                    u'Dtype: object')
+                    '3    baz')
         self.assertEqual(result, expected)
 
         s = Series(['foo', 5, 'bar', 'baz'])
         result = s.to_string()
         expected = (u'0    foo\n'
                     '1      5\n'
                     '2    bar\n'
-                    '3    baz\n'
-                    u'Dtype: object')
+                    '3    baz')
         self.assertEqual(result, expected)
 
     def test_to_string_float_na_spacing(self):
@@ -1181,8 +1187,7 @@ def test_to_string_float_na_spacing(self):
                     '1    1.5678\n'
                     '2       NaN\n'
                     '3   -3.0000\n'
-                    '4       NaN\n'
-                    u'Dtype: float64')
+                    '4       NaN')
         self.assertEqual(result, expected)
 
     def test_unicode_name_in_footer(self):
@@ -1216,14 +1221,12 @@ def test_timedelta64(self):
         result = y.to_string()
         self.assertTrue('1 days, 00:00:00' in result)
         self.assertTrue('NaT' in result)
-        self.assertTrue('timedelta64[ns]' in result)
 
         # with frac seconds
         s = Series(date_range('2012-1-1', periods=3, freq='D'))
         y = s-datetime(2012,1,1,microsecond=150)
         result = y.to_string()
         self.assertTrue('00:00:00.000150' in result)
-        self.assertTrue('timedelta64[ns]' in result)
 
     def test_mixed_datetime64(self):
         df = DataFrame({'A': [1, 2],