Merge pull request #8701 from jreback/show_counts

ENH: provide a null_counts keyword to df.info() to force showing of null counts

Author: jreback

doc/source/options.rst

@@ -86,7 +86,7 @@ pandas namespace.  To change an option, call ``set_option('option regex', new_va
    pd.set_option('mode.sim_interactive', True)
    pd.get_option('mode.sim_interactive')
 
-**Note:** that the option 'mode.sim_interactive' is mostly used for debugging purposes.  
+**Note:** that the option 'mode.sim_interactive' is mostly used for debugging purposes.
 
 All options also have a default value, and you can use ``reset_option`` to do just that:
 
@@ -213,7 +213,8 @@ will be given.
 
 ``display.max_info_rows``: ``df.info()`` will usually show null-counts for each column.
 For large frames this can be quite slow. ``max_info_rows`` and ``max_info_cols``
-limit this null check only to frames with smaller dimensions then specified.
+limit this null check only to frames with smaller dimensions then specified. Note that you
+can specify the option ``df.info(null_counts=True)`` to override on showing a particular frame.
 
 .. ipython:: python
 

doc/source/whatsnew/v0.15.1.txt

@@ -159,6 +159,7 @@ Enhancements
 - Added support for 3-character ISO and non-standard country codes in :func:``io.wb.download()`` (:issue:`8482`)
 - :ref:`World Bank data requests <remote_data.wb>` now will warn/raise based on an ``errors`` argument, as well as a list of hard-coded country codes and the World Bank's JSON response.  In prior versions, the error messages didn't look at the World Bank's JSON response.  Problem-inducing input were simply dropped prior to the request.  The issue was that many good countries were cropped in the hard-coded approach.  All countries will work now, but some bad countries will raise exceptions because some edge cases break the entire response. (:issue:`8482`)
 - Added option to ``Series.str.split()`` to return a ``DataFrame`` rather than a ``Series`` (:issue:`8428`)
+- Added option to ``df.info(null_counts=None|True|False)`` to override the default display options and force showing of the null-counts (:issue:`8701`)
 
 .. _whatsnew_0151.performance:
 

pandas/core/frame.py

@@ -1424,7 +1424,7 @@ def to_latex(self, buf=None, columns=None, col_space=None, colSpace=None,
         if buf is None:
             return formatter.buf.getvalue()
 
-    def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None):
+    def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None, null_counts=None):
         """
         Concise summary of a DataFrame.
 
@@ -1444,6 +1444,12 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None):
             the `display.memory_usage` setting. True or False overrides
             the `display.memory_usage` setting. Memory usage is shown in
             human-readable units (base-2 representation).
+        null_counts : boolean, default None
+            Whether to show the non-null counts
+            If None, then only show if the frame is smaller than max_info_rows and max_info_columns.
+            If True, always show counts.
+            If False, never show counts.
+
         """
         from pandas.core.format import _put_lines
 
@@ -1469,8 +1475,11 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None):
 
         max_rows = get_option('display.max_info_rows', len(self) + 1)
 
-        show_counts = ((len(self.columns) <= max_cols) and
-                       (len(self) < max_rows))
+        if null_counts is None:
+            show_counts = ((len(self.columns) <= max_cols) and
+                           (len(self) < max_rows))
+        else:
+            show_counts = null_counts
         exceeds_info_cols = len(self.columns) > max_cols
 
         def _verbose_repr():

pandas/tests/test_format.py

@@ -117,6 +117,26 @@ def test_eng_float_formatter(self):
         repr(self.frame)
         self.reset_display_options()
 
+    def test_show_null_counts(self):
+
+        df = DataFrame(1,columns=range(10),index=range(10))
+        df.iloc[1,1] = np.nan
+
+        def check(null_counts, result):
+            buf = StringIO()
+            r = df.info(buf=buf,null_counts=null_counts)
+            self.assertTrue(('non-null' in buf.getvalue()) is result)
+
+        with option_context('display.max_info_rows',20,'display.max_info_columns',20):
+            check(None, True)
+            check(True, True)
+            check(False, False)
+
+        with option_context('display.max_info_rows',5,'display.max_info_columns',5):
+            check(None, False)
+            check(True, False)
+            check(False, False)
+
     def test_repr_tuples(self):
         buf = StringIO()