Merge pull request #5550 from takluyver/long-repr-html

HTML reprs for large dataframes.

Author: y-p

doc/source/dsintro.rst

@@ -573,8 +573,9 @@ indexing semantics are quite different in places from a matrix.
 Console display
 ~~~~~~~~~~~~~~~
 
-For very large DataFrame objects, only a summary will be printed to the console
-(here I am reading a CSV version of the **baseball** dataset from the **plyr**
+Very large DataFrames will be truncated to display them in the console.
+You can also get a summary using :meth:`~pandas.DataFrame.info`.
+(Here I am reading a CSV version of the **baseball** dataset from the **plyr**
 R package):
 
 .. ipython:: python
@@ -587,6 +588,7 @@ R package):
 
    baseball = read_csv('data/baseball.csv')
    print(baseball)
+   baseball.info()
 
 .. ipython:: python
    :suppress:
@@ -622,19 +624,8 @@ option:
 
    reset_option('line_width')
 
-You can also disable this feature via the ``expand_frame_repr`` option:
-
-.. ipython:: python
-
-   set_option('expand_frame_repr', False)
-
-   DataFrame(randn(3, 12))
-
-.. ipython:: python
-   :suppress:
-
-   reset_option('expand_frame_repr')
-
+You can also disable this feature via the ``expand_frame_repr`` option.
+This will print the table in one block.
 
 DataFrame column attribute access and IPython completion
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

doc/source/faq.rst

@@ -36,21 +36,25 @@ horizontal scrolling, auto-detection of width/height.
 To appropriately address all these environments, the display behavior is controlled
 by several options, which you're encouraged to tweak to suit your setup.
 
-As of 0.12, these are the relevant options, all under the `display` namespace,
-(e.g. display.width,  etc'):
+As of 0.13, these are the relevant options, all under the `display` namespace,
+(e.g. ``display.width``,  etc.):
 
 - notebook_repr_html: if True, IPython frontends with HTML support will display
   dataframes as HTML tables when possible.
-- expand_repr (default True):  when the frame width cannot fit within the screen,
-  the output will be broken into multiple pages to accomedate. This applies to
-  textual (as opposed to HTML) display only.
-- max_columns: max dataframe columns to display. a wider frame will trigger
-  a summary view, unless `expand_repr` is True and HTML output is disabled.
-- max_rows: max dataframe rows display. a longer frame will trigger a summary view.
-- width: width of display screen in characters, used to determine the width of lines
-  when expand_repr is active,  Setting this to None will trigger auto-detection of terminal
-  width, this only works for proper terminals, not IPython frontends such as ipnb.
-  width is ignored in IPython notebook, since the browser provides horizontal scrolling.
+- large_repr (default 'truncate'): when a :class:`~pandas.DataFrame`
+  exceeds max_columns or max_rows, it can be displayed either as a
+  truncated table or, with this set to 'info', as a short summary view.
+- max_columns (default 20): max dataframe columns to display.
+- max_rows (default 60): max dataframe rows display.
+
+Two additional options only apply to displaying DataFrames in terminals,
+not to the HTML view:
+
+- expand_repr (default True):  when the frame width cannot fit within
+  the screen, the output will be broken into multiple pages.
+- width: width of display screen in characters, used to determine the
+  width of lines when expand_repr is active. Setting this to None will
+  trigger auto-detection of terminal width.
 
 IPython users can use the IPython startup file to import pandas and set these
 options automatically when starting up.

doc/source/v0.13.0.txt

@@ -375,6 +375,22 @@ HDFStore API Changes
   via the option ``io.hdf.dropna_table`` (:issue:`4625`)
 - pass thru store creation arguments; can be used to support in-memory stores
 
+DataFrame repr Changes
+~~~~~~~~~~~~~~~~~~~~~~
+
+The HTML and plain text representations of :class:`DataFrame` now show
+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.
+
+.. image:: _static/df_repr_truncated.png
+   :alt: Truncated HTML representation of a DataFrame
+
+To get the info view, call :meth:`DataFrame.info`. If you prefer the
+info view as the repr for large DataFrames, you can set this by running
+``set_option('display.large_repr', 'info')``.
+
 Enhancements
 ~~~~~~~~~~~~
 

pandas/core/config_init.py

@@ -166,13 +166,19 @@
 
 pc_max_info_rows_doc = """
 : int or None
-    max_info_rows is the maximum number of rows for which a frame will
-    perform a null check on its columns when repr'ing To a console.
-    The default is 1,000,000 rows. So, if a DataFrame has more
-    1,000,000 rows there will be no null check performed on the
-    columns and thus the representation will take much less time to
-    display in an interactive session. A value of None means always
-    perform a null check when repr'ing.
+    Deprecated.
+"""
+
+pc_max_info_rows_deprecation_warning = """\
+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 = """
@@ -220,6 +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,
@@ -258,6 +266,9 @@ def mpl_style_cb(key):
                     msg=pc_height_deprecation_warning,
                     rkey='display.max_rows')
 
+cf.deprecate_option('display.max_info_rows',
+                    msg=pc_max_info_rows_deprecation_warning)
+
 tc_sim_interactive_doc = """
 : boolean
     Whether to simulate interactive mode for purposes of testing