Add an option to switch back to info repr for large DataFrames

Author: takluyver

doc/source/v0.13.0.txt

@@ -611,7 +611,8 @@ Enhancements
   a truncated view of the table once it exceeds a certain size, rather
   than switching to the short info view (:issue:`4886`, :issue:`5550`).
   This makes the representation more consistent as small DataFrames get
-  larger. To get the info view, call :meth:`DataFrame.info`.
+  larger. To get the info view, call :meth:`DataFrame.info`, or restore
+  the old behaviour with ``set_option('display.large_repr', 'info')``.
 
 .. _whatsnew_0130.experimental:
 

pandas/core/config_init.py

@@ -173,6 +173,14 @@
 max_info_rows has been deprecated, as reprs no longer use the info view.
 """
 
+pc_large_repr_doc = """
+: 'truncate'/'info'
+
+    For DataFrames exceeding max_rows/max_cols, the repr (and HTML repr) can
+    show a truncated table (the default from 0.13), or switch to the view from
+    df.info() (the behaviour in earlier versions of pandas).
+"""
+
 pc_mpl_style_doc = """
 : bool
 
@@ -218,6 +226,8 @@ def mpl_style_cb(key):
     cf.register_option('max_colwidth', 50, max_colwidth_doc, validator=is_int)
     cf.register_option('max_columns', 20, pc_max_cols_doc,
                        validator=is_instance_factory([type(None), int]))
+    cf.register_option('large_repr', 'truncate', pc_large_repr_doc,
+                       validator=is_one_of_factory(['truncate', 'info']))
     cf.register_option('max_info_columns', 100, pc_max_info_cols_doc,
                        validator=is_int)
     cf.register_option('colheader_justify', 'right', colheader_justify_doc,

pandas/core/frame.py

@@ -429,6 +429,12 @@ def _repr_fits_horizontal_(self, ignore_width=False):
 
         return repr_width < width
 
+    def _info_repr(self):
+        """True if the repr should show the info view."""
+        info_repr_option = (get_option("display.large_repr") == "info")
+        return info_repr_option and not \
+                (self._repr_fits_horizontal_() and self._repr_fits_vertical_())
+
     def __unicode__(self):
         """
         Return a string representation for a particular DataFrame
@@ -437,6 +443,10 @@ def __unicode__(self):
         py2/py3.
         """
         buf = StringIO(u(""))
+        if self._info_repr():
+            self.info(buf=buf)
+            return buf.getvalue()
+
         max_rows = get_option("display.max_rows")
         max_cols = get_option("display.max_columns")
         if get_option("display.expand_frame_repr"):
@@ -464,6 +474,11 @@ def _repr_html_(self):
         if com.in_qtconsole():
             raise ValueError('Disable HTML output in QtConsole')
 
+        if self._info_repr():
+            buf = StringIO(u(""))
+            self.info(buf=buf)
+            return '<pre>' + buf.getvalue() + '</pre>'
+
         if get_option("display.notebook_repr_html"):
             max_rows = get_option("display.max_rows")
             max_cols = get_option("display.max_columns")

pandas/tests/test_format.py

@@ -31,6 +31,10 @@ def curpath():
     pth, _ = os.path.split(os.path.abspath(__file__))
     return pth
 
+def has_info_repr(df):
+    r = repr(df)
+    return r.split('\n')[0].startswith("<class")
+
 def has_horizontally_truncated_repr(df):
     r = repr(df)
     return any(l.strip().endswith('...') for l in r.splitlines())
@@ -1477,6 +1481,40 @@ def test_repr_html_long_and_wide(self):
         df = pandas.DataFrame(dict((k,np.arange(1,1+h)) for k in np.arange(w)))
         assert '...'  in df._repr_html_()
 
+    def test_info_repr(self):
+        max_rows = get_option('display.max_rows')
+        max_cols = get_option('display.max_columns')
+        # Long
+        h, w = max_rows+1, max_cols-1
+        df = pandas.DataFrame(dict((k,np.arange(1,1+h)) for k in np.arange(w)))
+        assert has_vertically_truncated_repr(df)
+        with option_context('display.large_repr', 'info'):
+            assert has_info_repr(df)
+
+        # Wide
+        h, w = max_rows-1, max_cols+1
+        df = pandas.DataFrame(dict((k,np.arange(1,1+h)) for k in np.arange(w)))
+        assert has_vertically_truncated_repr(df)
+        with option_context('display.large_repr', 'info'):
+            assert has_info_repr(df)
+
+    def test_info_repr_html(self):
+        max_rows = get_option('display.max_rows')
+        max_cols = get_option('display.max_columns')
+        # Long
+        h, w = max_rows+1, max_cols-1
+        df = pandas.DataFrame(dict((k,np.arange(1,1+h)) for k in np.arange(w)))
+        assert '<class' not in df._repr_html_()
+        with option_context('display.large_repr', 'info'):
+            assert '<class' in df._repr_html_()
+
+        # Wide
+        h, w = max_rows-1, max_cols+1
+        df = pandas.DataFrame(dict((k,np.arange(1,1+h)) for k in np.arange(w)))
+        assert '<class' not in df._repr_html_()
+        with option_context('display.large_repr', 'info'):
+            assert '<class' in df._repr_html_()
+
     def test_fake_qtconsole_repr_html(self):
         def get_ipython():
             return {'config':