Merge branch 'master' into docstring_rsplit

Author: ryankarlos

Makefile

@@ -23,3 +23,4 @@ doc:
 	cd doc; \
 	python make.py clean; \
 	python make.py html
+	python make.py spellcheck

asv_bench/benchmarks/frame_methods.py

@@ -512,3 +512,21 @@ def time_nlargest(self, keep):
 
     def time_nsmallest(self, keep):
         self.df.nsmallest(100, 'A', keep=keep)
+
+
+class Describe(object):
+
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame({
+            'a': np.random.randint(0, 100, int(1e6)),
+            'b': np.random.randint(0, 100, int(1e6)),
+            'c': np.random.randint(0, 100, int(1e6))
+        })
+
+    def time_series_describe(self):
+        self.df['a'].describe()
+
+    def time_dataframe_describe(self):
+        self.df.describe()

doc/make.py

@@ -224,8 +224,9 @@ def _sphinx_build(self, kind):
         --------
         >>> DocBuilder(num_jobs=4)._sphinx_build('html')
         """
-        if kind not in ('html', 'latex'):
-            raise ValueError('kind must be html or latex, not {}'.format(kind))
+        if kind not in ('html', 'latex', 'spelling'):
+            raise ValueError('kind must be html, latex or '
+                             'spelling, not {}'.format(kind))
 
         self._run_os('sphinx-build',
                      '-j{}'.format(self.num_jobs),
@@ -304,6 +305,18 @@ def zip_html(self):
                      '-q',
                      *fnames)
 
+    def spellcheck(self):
+        """Spell check the documentation."""
+        self._sphinx_build('spelling')
+        output_location = os.path.join('build', 'spelling', 'output.txt')
+        with open(output_location) as output:
+            lines = output.readlines()
+            if lines:
+                raise SyntaxError(
+                    'Found misspelled words.'
+                    ' Check pandas/doc/build/spelling/output.txt'
+                    ' for more details.')
+
 
 def main():
     cmds = [method for method in dir(DocBuilder) if not method.startswith('_')]

doc/source/advanced.rst

@@ -342,7 +342,7 @@ As usual, **both sides** of the slicers are included as this is label indexing.
                        columns=micolumns).sort_index().sort_index(axis=1)
    dfmi
 
-Basic multi-index slicing using slices, lists, and labels.
+Basic MultiIndex slicing using slices, lists, and labels.
 
 .. ipython:: python
 
@@ -1039,7 +1039,7 @@ On the other hand, if the index is not monotonic, then both slice bounds must be
     KeyError: 'Cannot get right slice bound for non-unique label: 3'
 
 :meth:`Index.is_monotonic_increasing` and :meth:`Index.is_monotonic_decreasing` only check that
-an index is weakly monotonic. To check for strict montonicity, you can combine one of those with
+an index is weakly monotonic. To check for strict monotonicity, you can combine one of those with
 :meth:`Index.is_unique`
 
 .. ipython:: python

doc/source/basics.rst

@@ -168,7 +168,7 @@ either match on the *index* or *columns* via the **axis** keyword:
 
    df_orig = df
 
-Furthermore you can align a level of a multi-indexed DataFrame with a Series.
+Furthermore you can align a level of a MultiIndexed DataFrame with a Series.
 
 .. ipython:: python
 
@@ -593,7 +593,7 @@ categorical columns:
     frame = pd.DataFrame({'a': ['Yes', 'Yes', 'No', 'No'], 'b': range(4)})
     frame.describe()
 
-This behaviour can be controlled by providing a list of types as ``include``/``exclude``
+This behavior can be controlled by providing a list of types as ``include``/``exclude``
 arguments. The special value ``all`` can also be used:
 
 .. ipython:: python
@@ -1034,7 +1034,7 @@ Passing a single function to ``.transform()`` with a ``Series`` will yield a sin
 Transform with multiple functions
 +++++++++++++++++++++++++++++++++
 
-Passing multiple functions will yield a column multi-indexed DataFrame.
+Passing multiple functions will yield a column MultiIndexed DataFrame.
 The first level will be the original frame column names; the second level
 will be the names of the transforming functions.
 
@@ -1060,7 +1060,7 @@ Passing a dict of functions will allow selective transforming per column.
 
    tsdf.transform({'A': np.abs, 'B': lambda x: x+1})
 
-Passing a dict of lists will generate a multi-indexed DataFrame with these
+Passing a dict of lists will generate a MultiIndexed DataFrame with these
 selective transforms.
 
 .. ipython:: python
@@ -1889,12 +1889,12 @@ faster than sorting the entire Series and calling ``head(n)`` on the result.
    df.nsmallest(5, ['a', 'c'])
 
 
-.. _basics.multi-index_sorting:
+.. _basics.multiindex_sorting:
 
-Sorting by a multi-index column
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Sorting by a MultiIndex column
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-You must be explicit about sorting when the column is a multi-index, and fully specify
+You must be explicit about sorting when the column is a MultiIndex, and fully specify
 all levels to ``by``.
 
 .. ipython:: python

doc/source/conf.py

@@ -73,10 +73,14 @@
               'sphinx.ext.ifconfig',
               'sphinx.ext.linkcode',
               'nbsphinx',
+              'sphinxcontrib.spelling'
               ]
 
 exclude_patterns = ['**.ipynb_checkpoints']
 
+spelling_word_list_filename = ['spelling_wordlist.txt', 'names_wordlist.txt']
+spelling_ignore_pypi_package_names = True
+
 with open("index.rst") as f:
     index_rst_lines = f.readlines()
 

doc/source/contributing.rst

@@ -436,6 +436,25 @@ the documentation are also built by Travis-CI. These docs are then hosted `here
 <http://pandas-docs.github.io/pandas-docs-travis>`__, see also
 the :ref:`Continuous Integration <contributing.ci>` section.
 
+Spell checking documentation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When contributing to documentation to **pandas** it's good to check if your work
+contains any spelling errors. Sphinx provides an easy way to spell check documentation
+and docstrings.
+
+Running the spell check is easy. Just navigate to your local ``pandas/doc/`` directory and run::
+
+    python make.py spellcheck
+
+The spellcheck will take a few minutes to run (between 1 to 6 minutes). Sphinx will alert you
+with warnings and misspelt words - these misspelt words will be added to a file called
+``output.txt`` and you can find it on your local directory ``pandas/doc/build/spelling/``.
+
+The Sphinx spelling extension uses an EN-US dictionary to correct words, what means that in
+some cases you might need to add a word to this dictionary. You can do so by adding the word to
+the bag-of-words file named ``spelling_wordlist.txt`` located in the folder ``pandas/doc/``.
+
 .. _contributing.code:
 
 Contributing to the code base

doc/source/contributing_docstring.rst

@@ -103,7 +103,7 @@ left before or after the docstring. The text starts in the next line after the
 opening quotes. The closing quotes have their own line
 (meaning that they are not at the end of the last sentence).
 
-In rare occasions reST styles like bold text or itallics will be used in
+In rare occasions reST styles like bold text or italics will be used in
 docstrings, but is it common to have inline code, which is presented between
 backticks. It is considered inline code:
 
@@ -243,7 +243,7 @@ their use cases, if it is not too generic.
         """
         Pivot a row index to columns.
 
-        When using a multi-index, a level can be pivoted so each value in
+        When using a MultiIndex, a level can be pivoted so each value in
         the index becomes a column. This is especially useful when a subindex
         is repeated for the main index, and data is easier to visualize as a
         pivot table.
@@ -706,7 +706,7 @@ than 5, to show the example with the default values. If doing the ``mean``, we
 could use something like ``[1, 2, 3]``, so it is easy to see that the value
 returned is the mean.
 
-For more complex examples (groupping for example), avoid using data without
+For more complex examples (grouping for example), avoid using data without
 interpretation, like a matrix of random numbers with columns A, B, C, D...
 And instead use a meaningful example, which makes it easier to understand the
 concept. Unless required by the example, use names of animals, to keep examples
@@ -877,7 +877,7 @@ be tricky. Here are some attention points:
   the actual error only the error name is sufficient.
 
 * If there is a small part of the result that can vary (e.g. a hash in an object
-  represenation), you can use ``...`` to represent this part.
+  representation), you can use ``...`` to represent this part.
 
   If you want to show that ``s.plot()`` returns a matplotlib AxesSubplot object,
   this will fail the doctest ::

doc/source/cookbook.rst

@@ -286,7 +286,7 @@ New Columns
    df = pd.DataFrame(
         {'AAA' : [1,1,1,2,2,2,3,3], 'BBB' : [2,1,3,4,5,1,2,3]}); df
 
-Method 1 : idxmin() to get the index of the mins
+Method 1 : idxmin() to get the index of the minimums
 
 .. ipython:: python
 
@@ -307,7 +307,7 @@ MultiIndexing
 
 The :ref:`multindexing <advanced.hierarchical>` docs.
 
-`Creating a multi-index from a labeled frame
+`Creating a MultiIndex from a labeled frame
 <http://stackoverflow.com/questions/14916358/reshaping-dataframes-in-pandas-based-on-column-labels>`__
 
 .. ipython:: python
@@ -330,7 +330,7 @@ The :ref:`multindexing <advanced.hierarchical>` docs.
 Arithmetic
 **********
 
-`Performing arithmetic with a multi-index that needs broadcasting
+`Performing arithmetic with a MultiIndex that needs broadcasting
 <http://stackoverflow.com/questions/19501510/divide-entire-pandas-multiindex-dataframe-by-dataframe-variable/19502176#19502176>`__
 
 .. ipython:: python
@@ -342,7 +342,7 @@ Arithmetic
 Slicing
 *******
 
-`Slicing a multi-index with xs
+`Slicing a MultiIndex with xs
 <http://stackoverflow.com/questions/12590131/how-to-slice-multindex-columns-in-pandas-dataframes>`__
 
 .. ipython:: python
@@ -363,7 +363,7 @@ To take the cross section of the 1st level and 1st axis the index:
 
    df.xs('six',level=1,axis=0)
 
-`Slicing a multi-index with xs, method #2
+`Slicing a MultiIndex with xs, method #2
 <http://stackoverflow.com/questions/14964493/multiindex-based-indexing-in-pandas>`__
 
 .. ipython:: python
@@ -386,13 +386,13 @@ To take the cross section of the 1st level and 1st axis the index:
    df.loc[(All,'Math'),('Exams')]
    df.loc[(All,'Math'),(All,'II')]
 
-`Setting portions of a multi-index with xs
+`Setting portions of a MultiIndex with xs
 <http://stackoverflow.com/questions/19319432/pandas-selecting-a-lower-level-in-a-dataframe-to-do-a-ffill>`__
 
 Sorting
 *******
 
-`Sort by specific column or an ordered list of columns, with a multi-index
+`Sort by specific column or an ordered list of columns, with a MultiIndex
 <http://stackoverflow.com/questions/14733871/mutli-index-sorting-in-pandas>`__
 
 .. ipython:: python
@@ -664,7 +664,7 @@ The :ref:`Pivot <reshaping.pivot>` docs.
 `Plot pandas DataFrame with year over year data
 <http://stackoverflow.com/questions/30379789/plot-pandas-data-frame-with-year-over-year-data>`__
 
-To create year and month crosstabulation:
+To create year and month cross tabulation:
 
 .. ipython:: python
 
@@ -677,7 +677,7 @@ To create year and month crosstabulation:
 Apply
 *****
 
-`Rolling Apply to Organize - Turning embedded lists into a multi-index frame
+`Rolling Apply to Organize - Turning embedded lists into a MultiIndex frame
 <http://stackoverflow.com/questions/17349981/converting-pandas-dataframe-with-categorical-values-into-binary-values>`__
 
 .. ipython:: python
@@ -1029,8 +1029,8 @@ Skip row between header and data
     01.01.1990 05:00;21;11;12;13
     """
 
-Option 1: pass rows explicitly to skiprows
-""""""""""""""""""""""""""""""""""""""""""
+Option 1: pass rows explicitly to skip rows
+"""""""""""""""""""""""""""""""""""""""""""
 
 .. ipython:: python
 

doc/source/dsintro.rst

@@ -353,7 +353,7 @@ From a list of dicts
 From a dict of tuples
 ~~~~~~~~~~~~~~~~~~~~~
 
-You can automatically create a multi-indexed frame by passing a tuples
+You can automatically create a MultiIndexed frame by passing a tuples
 dictionary.
 
 .. ipython:: python
@@ -1014,7 +1014,7 @@ Deprecate Panel
 Over the last few years, pandas has increased in both breadth and depth, with new features,
 datatype support, and manipulation routines. As a result, supporting efficient indexing and functional
 routines for ``Series``, ``DataFrame`` and ``Panel`` has contributed to an increasingly fragmented and
-difficult-to-understand codebase.
+difficult-to-understand code base.
 
 The 3-D structure of a ``Panel`` is much less common for many types of data analysis,
 than the 1-D of the ``Series`` or the 2-D of the ``DataFrame``. Going forward it makes sense for
@@ -1023,7 +1023,7 @@ pandas to focus on these areas exclusively.
 Oftentimes, one can simply use a MultiIndex ``DataFrame`` for easily working with higher dimensional data.
 
 In addition, the ``xarray`` package was built from the ground up, specifically in order to
-support the multi-dimensional analysis that is one of ``Panel`` s main usecases.
+support the multi-dimensional analysis that is one of ``Panel`` s main use cases.
 `Here is a link to the xarray panel-transition documentation <http://xarray.pydata.org/en/stable/pandas.html#panel-transition>`__.
 
 .. ipython:: python

doc/source/ecosystem.rst

@@ -38,7 +38,10 @@ Statsmodels leverages pandas objects as the underlying data container for comput
 Use pandas DataFrames in your `scikit-learn <http://scikit-learn.org/>`__
 ML pipeline.
 
+`Featuretools <https://github.com/featuretools/featuretools/>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
+Featuretools is a Python library for automated feature engineering built on top of pandas. It excels at transforming temporal and relational datasets into feature matrices for machine learning using reusable feature engineering "primitives". Users can contribute their own primitives in Python and share them with the rest of the community. 
 
 .. _ecosystem.visualization:
 
@@ -184,9 +187,9 @@ and metadata disseminated in
 `SDMX <http://www.sdmx.org>`_ 2.1, an ISO-standard
 widely used by institutions such as statistics offices, central banks,   
 and international organisations. pandaSDMX can expose datasets and related 
-structural metadata including dataflows, code-lists, 
-and datastructure definitions as pandas Series 
-or multi-indexed DataFrames.  
+structural metadata including data flows, code-lists,
+and data structure definitions as pandas Series
+or MultiIndexed DataFrames.
 
 `fredapi <https://github.com/mortada/fredapi>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -260,7 +263,7 @@ Data validation
 `Engarde <http://engarde.readthedocs.io/en/latest/>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Engarde is a lightweight library used to explicitly state your assumptions abour your datasets
+Engarde is a lightweight library used to explicitly state your assumptions about your datasets
 and check that they're *actually* true.
 
 .. _ecosystem.extensions:

doc/source/enhancingperf.rst

@@ -32,7 +32,7 @@ Cython (Writing C extensions for pandas)
 ----------------------------------------
 
 For many use cases writing pandas in pure Python and NumPy is sufficient. In some
-computationally heavy applications however, it can be possible to achieve sizeable
+computationally heavy applications however, it can be possible to achieve sizable
 speed-ups by offloading work to `cython <http://cython.org/>`__.
 
 This tutorial assumes you have refactored as much as possible in Python, for example
@@ -806,7 +806,7 @@ truncate any strings that are more than 60 characters in length. Second, we
 can't pass ``object`` arrays to ``numexpr`` thus string comparisons must be
 evaluated in Python space.
 
-The upshot is that this *only* applies to object-dtype'd expressions. So, if
+The upshot is that this *only* applies to object-dtype expressions. So, if
 you have an expression--for example
 
 .. ipython:: python

doc/source/extending.rst

@@ -167,7 +167,7 @@ you can retain subclasses through ``pandas`` data manipulations.
 
 There are 3 constructor properties to be defined:
 
-- ``_constructor``: Used when a manipulation result has the same dimesions as the original.
+- ``_constructor``: Used when a manipulation result has the same dimensions as the original.
 - ``_constructor_sliced``: Used when a manipulation result has one lower dimension(s) as the original, such as ``DataFrame`` single columns slicing.
 - ``_constructor_expanddim``: Used when a manipulation result has one higher dimension as the original, such as ``Series.to_frame()`` and ``DataFrame.to_panel()``.