From df2418774861111238bdca1edfb8908fe9db3da9 Mon Sep 17 00:00:00 2001
From: Stephan Hoyer <shoyer@climate.com>
Date: Wed, 22 Oct 2014 00:30:54 -0700
Subject: [PATCH] Use '+' to qualify memory usage in df.info() if appropriate

This should resolve @kay1793's complaint in #8578.
---
 doc/source/faq.rst         |  4 ++++
 doc/source/v0.15.1.txt     |  2 ++
 pandas/core/frame.py       | 14 ++++++++++----
 pandas/tests/test_frame.py | 15 +++++++++++++++
 4 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/doc/source/faq.rst b/doc/source/faq.rst
index 2befb22ab5de4..b93e5ae9c922a 100644
--- a/doc/source/faq.rst
+++ b/doc/source/faq.rst
@@ -50,6 +50,10 @@ when calling ``df.info()``:
 
     df.info()
 
+The ``+`` symbol indicates that the true memory usage could be higher, because
+pandas does not count the memory used by values in columns with
+``dtype=object``.
+
 By default the display option is set to ``True`` but can be explicitly
 overridden by passing the ``memory_usage`` argument when invoking ``df.info()``.
 
diff --git a/doc/source/v0.15.1.txt b/doc/source/v0.15.1.txt
index 2bd88531f92d9..fa1b8b24e75b5 100644
--- a/doc/source/v0.15.1.txt
+++ b/doc/source/v0.15.1.txt
@@ -28,6 +28,8 @@ Enhancements
 
 - Added option to select columns when importing Stata files (:issue:`7935`)
 
+- Qualify memory usage in ``DataFrame.info()`` by adding ``+`` if it is a lower bound (:issue:`8578`)
+
 
 .. _whatsnew_0151.performance:
 
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 2c172d6fe1af0..d90ef76ddfa5e 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -1478,13 +1478,13 @@ def _verbose_repr():
         def _non_verbose_repr():
             lines.append(self.columns.summary(name='Columns'))
 
-        def _sizeof_fmt(num):
+        def _sizeof_fmt(num, size_qualifier):
             # returns size in human readable format
             for x in ['bytes', 'KB', 'MB', 'GB', 'TB']:
                 if num < 1024.0:
-                    return "%3.1f %s" % (num, x)
+                    return "%3.1f%s %s" % (num, size_qualifier, x)
                 num /= 1024.0
-            return "%3.1f %s" % (num, 'PB')
+            return "%3.1f%s %s" % (num, size_qualifier, 'PB')
 
         if verbose:
             _verbose_repr()
@@ -1502,8 +1502,14 @@ def _sizeof_fmt(num):
         if memory_usage is None:
             memory_usage = get_option('display.memory_usage')
         if memory_usage:  # append memory usage of df to display
+            # size_qualifier is just a best effort; not guaranteed to catch all
+            # cases (e.g., it misses categorical data even with object
+            # categories)
+            size_qualifier = ('+' if 'object' in counts
+                              or self.index.dtype.kind == 'O' else '')
+            mem_usage = self.memory_usage(index=True).sum()
             lines.append("memory usage: %s\n" %
-                            _sizeof_fmt(self.memory_usage(index=True).sum()))
+                            _sizeof_fmt(mem_usage, size_qualifier))
         _put_lines(buf, lines)
 
     def memory_usage(self, index=False):
diff --git a/pandas/tests/test_frame.py b/pandas/tests/test_frame.py
index e5064544b292e..3f4d825a4b82e 100644
--- a/pandas/tests/test_frame.py
+++ b/pandas/tests/test_frame.py
@@ -6732,6 +6732,21 @@ def test_info_memory_usage(self):
         res = buf.getvalue().splitlines()
         self.assertTrue("memory usage: " not in res[-1])
 
+        df.info(buf=buf, memory_usage=True)
+        res = buf.getvalue().splitlines()
+        # memory usage is a lower bound, so print it as XYZ+ MB
+        self.assertTrue(re.match(r"memory usage: [^+]+\+", res[-1]))
+
+        df.iloc[:, :5].info(buf=buf, memory_usage=True)
+        res = buf.getvalue().splitlines()
+        # excluded column with object dtype, so estimate is accurate
+        self.assertFalse(re.match(r"memory usage: [^+]+\+", res[-1]))
+
+        df_with_object_index = pd.DataFrame({'a': [1]}, index=['foo'])
+        df_with_object_index.info(buf=buf, memory_usage=True)
+        res = buf.getvalue().splitlines()
+        self.assertTrue(re.match(r"memory usage: [^+]+\+", res[-1]))
+
         # Test a DataFrame with duplicate columns
         dtypes = ['int64', 'int64', 'int64', 'float64']
         data = {}