Verbose info configuration

pandas/core/config_init.py

@@ -1,5 +1,6 @@
 import pandas.core.config as cf
-from pandas.core.config import is_int, is_bool, is_text, is_float
+from pandas.core.config import (is_int, is_bool, is_text, is_float,
+                                is_instance_factory)
 from pandas.core.format import detect_console_encoding
 
 """
@@ -123,10 +124,24 @@
     will be displayed as exactly 0 by repr and friends.
 """
 
+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.
+"""
+
+
 with cf.config_prefix('display'):
     cf.register_option('precision', 7, pc_precision_doc, validator=is_int)
     cf.register_option('float_format', None, float_format_doc)
     cf.register_option('column_space', 12, validator=is_int)
+    cf.register_option('max_info_rows', 1000000, pc_max_info_rows_doc,
+                       validator=is_instance_factory((int, type(None))))
     cf.register_option('max_rows', 100, pc_max_rows_doc, validator=is_int)
     cf.register_option('max_colwidth', 50, max_colwidth_doc, validator=is_int)
     cf.register_option('max_columns', 20, pc_max_cols_doc, validator=is_int)

pandas/core/frame.py

@@ -51,7 +51,7 @@
 import pandas.tslib as tslib
 import pandas.algos as _algos
 
-from pandas.core.config import get_option
+from pandas.core.config import get_option, set_option
 
 
 #----------------------------------------------------------------------
@@ -331,7 +331,6 @@ def f(self, other):
 
 class DataFrame(NDFrame):
     _auto_consolidate = True
-    _verbose_info = True
     _het_axis = 1
     _info_axis = 'columns'
     _col_klass = Series
@@ -560,6 +559,22 @@ def _wrap_array(self, arr, axes, copy=False):
         index, columns = axes
         return self._constructor(arr, index=index, columns=columns, copy=copy)
 
+    @property
+    def _verbose_info(self):
+        import warnings
+        warnings.warn('The _verbose_info property will be removed in version '
+                      '0.12', FutureWarning)
+        return get_option('display.max_info_rows') is None
+
+    @_verbose_info.setter
+    def _verbose_info(self, value):
+        import warnings
+        warnings.warn('The _verbose_info property will be removed in version '
+                      '0.12', FutureWarning)
+
+        value = None if value else 1000000
+        set_option('display.max_info_rows', value)
+
     @property
     def axes(self):
         return [self.index, self.columns]
@@ -652,7 +667,9 @@ def __unicode__(self):
         """
         buf = StringIO(u"")
         if self._need_info_repr_():
-            self.info(buf=buf, verbose=self._verbose_info)
+            max_info_rows = get_option('display.max_info_rows')
+            verbose = max_info_rows is None or self.shape[0] <= max_info_rows
+            self.info(buf=buf, verbose=verbose)
         else:
             is_wide = self._need_wide_repr()
             line_width = None

pandas/sparse/frame.py

@@ -66,7 +66,6 @@ class SparseDataFrame(DataFrame):
         Default fill_value for converting Series to SparseSeries. Will not
         override SparseSeries passed in
     """
-    _verbose_info = False
     _columns = None
     _series = None
     _is_mixed_type = False

pandas/tests/test_format.py

@@ -470,6 +470,44 @@ def test_frame_info_encoding(self):
         repr(df.T)
         fmt.set_printoptions(max_rows=200)
 
+    def test_large_frame_repr(self):
+        def wrap_rows_options(f):
+            def _f(*args, **kwargs):
+                old_max_rows = pd.get_option('display.max_rows')
+                old_max_info_rows = pd.get_option('display.max_info_rows')
+                o = f(*args, **kwargs)
+                pd.set_option('display.max_rows', old_max_rows)
+                pd.set_option('display.max_info_rows', old_max_info_rows)
+                return o
+            return _f
+
+        @wrap_rows_options
+        def test_setting(value, nrows=3, ncols=2):
+            if value is None:
+                expected_difference = 0
+            elif isinstance(value, int):
+                expected_difference = ncols
+            else:
+                raise ValueError("'value' must be int or None")
+
+            pd.set_option('display.max_rows', nrows - 1)
+            pd.set_option('display.max_info_rows', value)
+
+            smallx = DataFrame(np.random.rand(nrows, ncols))
+            repr_small = repr(smallx)
+
+            bigx = DataFrame(np.random.rand(nrows + 1, ncols))
+            repr_big = repr(bigx)
+
+            diff = len(repr_small.splitlines()) - len(repr_big.splitlines())
+
+            # the difference in line count is the number of columns
+            self.assertEqual(diff, expected_difference)
+
+        test_setting(None)
+        test_setting(3)
+        self.assertRaises(ValueError, test_setting, 'string')
+
     def test_wide_repr(self):
         with option_context('mode.sim_interactive', True):
             col = lambda l, k: [tm.rands(k) for _ in xrange(l)]