Merge remote-tracking branch 'upstream/master' into groupby_tuples

Author: GuessWhoSamFoo

Makefile

@@ -12,6 +12,9 @@ clean_pyc:
 build: clean_pyc
 	python setup.py build_ext --inplace
 
+lint-diff:
+	git diff master --name-only -- "*.py" | grep "pandas" | xargs flake8
+
 develop: build
 	-python setup.py develop
 

asv_bench/benchmarks/categoricals.py

@@ -26,6 +26,9 @@ def setup(self):
         self.datetimes = pd.Series(pd.date_range(
             '1995-01-01 00:00:00', periods=10000, freq='s'))
 
+        self.values_some_nan = list(np.tile(self.categories + [np.nan], N))
+        self.values_all_nan = [np.nan] * len(self.values)
+
     def time_concat(self):
         concat([self.s, self.s])
 
@@ -46,6 +49,12 @@ def time_constructor_datetimes_with_nat(self):
         t.iloc[-1] = pd.NaT
         Categorical(t)
 
+    def time_constructor_with_nan(self):
+        Categorical(self.values_some_nan)
+
+    def time_constructor_all_nan(self):
+        Categorical(self.values_all_nan)
+
 
 class Categoricals2(object):
     goal_time = 0.2

asv_bench/benchmarks/index_object.py

@@ -219,3 +219,22 @@ def time_min(self):
 
     def time_min_trivial(self):
         self.idx_inc.min()
+
+
+class IndexOps(object):
+    goal_time = 0.2
+
+    def setup(self):
+        N = 10000
+        self.ridx = [RangeIndex(i * 100, (i + 1) * 100) for i in range(N)]
+        self.iidx = [idx.astype(int) for idx in self.ridx]
+        self.oidx = [idx.astype(str) for idx in self.iidx]
+
+    def time_concat_range(self):
+        self.ridx[0].append(self.ridx[1:])
+
+    def time_concat_int(self):
+        self.iidx[0].append(self.iidx[1:])
+
+    def time_concat_obj(self):
+        self.oidx[0].append(self.oidx[1:])

asv_bench/benchmarks/indexing.py

@@ -287,3 +287,19 @@ def setup(self):
 
     def time_subset(self):
         self.p.ix[(self.inds, self.inds, self.inds)]
+
+
+class IndexerLookup(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.s = Series(range(10))
+
+    def time_lookup_iloc(self):
+        self.s.iloc
+
+    def time_lookup_ix(self):
+        self.s.ix
+
+    def time_lookup_loc(self):
+        self.s.loc

ci/lint.sh

@@ -16,6 +16,13 @@ if [ "$LINT" ]; then
     fi
     echo "Linting *.py DONE"
 
+    echo "Linting setup.py"
+    flake8 setup.py
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
+    echo "Linting setup.py DONE"
+
     echo "Linting *.pyx"
     flake8 pandas --filename=*.pyx --select=E501,E302,E203,E111,E114,E221,E303,E128,E231,E126
     if [ $? -ne "0" ]; then

doc/source/advanced.rst

@@ -833,15 +833,15 @@ Of course if you need integer based selection, then use ``iloc``
 IntervalIndex
 ~~~~~~~~~~~~~
 
+.. versionadded:: 0.20.0
+
 :class:`IntervalIndex` together with its own dtype, ``interval`` as well as the
 :class:`Interval` scalar type,  allow first-class support in pandas for interval
 notation.
 
 The ``IntervalIndex`` allows some unique indexing and is also used as a
 return type for the categories in :func:`cut` and :func:`qcut`.
 
-.. versionadded:: 0.20.0
-
 .. warning::
 
    These indexing behaviors are provisional and may change in a future version of pandas.
@@ -862,7 +862,7 @@ selecting that particular interval.
    df.loc[2]
    df.loc[[2, 3]]
 
-If you select a lable *contained* within an interval, this will also select the interval.
+If you select a label *contained* within an interval, this will also select the interval.
 
 .. ipython:: python
 

doc/source/api.rst

@@ -1794,6 +1794,7 @@ Methods
     Timestamp.strftime
     Timestamp.strptime
     Timestamp.time
+    Timestamp.timestamp
     Timestamp.timetuple
     Timestamp.timetz
     Timestamp.to_datetime64

doc/source/basics.rst

@@ -1738,11 +1738,6 @@ description.
 Sorting
 -------
 
-.. warning::
-
-   The sorting API is substantially changed in 0.17.0, see :ref:`here <whatsnew_0170.api_breaking.sorting>` for these changes.
-   In particular, all sorting methods now return a new object by default, and **DO NOT** operate in-place (except by passing ``inplace=True``).
-
 There are two obvious kinds of sorting that you may be interested in: sorting
 by label and sorting by actual values.
 
@@ -1829,8 +1824,6 @@ faster than sorting the entire Series and calling ``head(n)`` on the result.
    s.nsmallest(3)
    s.nlargest(3)
 
-.. versionadded:: 0.17.0
-
 ``DataFrame`` also has the ``nlargest`` and ``nsmallest`` methods.
 
 .. ipython:: python
@@ -1881,7 +1874,7 @@ dtypes
 ------
 
 The main types stored in pandas objects are ``float``, ``int``, ``bool``,
-``datetime64[ns]`` and ``datetime64[ns, tz]`` (in >= 0.17.0), ``timedelta[ns]``,
+``datetime64[ns]`` and ``datetime64[ns, tz]``, ``timedelta[ns]``,
 ``category`` and ``object``. In addition these dtypes have item sizes, e.g.
 ``int64`` and ``int32``. See :ref:`Series with TZ <timeseries.timezone_series>`
 for more detail on ``datetime64[ns, tz]`` dtypes.

doc/source/categorical.rst

@@ -632,8 +632,6 @@ To get a single value `Series` of type ``category`` pass in a list with a single
 String and datetime accessors
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. versionadded:: 0.17.1
-
 The accessors  ``.dt`` and ``.str`` will work if the ``s.cat.categories`` are of an appropriate
 type:
 

doc/source/computation.rst

@@ -206,8 +206,6 @@ Window Functions
    functions and are now deprecated. These are replaced by using the :class:`~pandas.core.window.Rolling`, :class:`~pandas.core.window.Expanding` and :class:`~pandas.core.window.EWM`. objects and a corresponding method call.
 
    The deprecation warning will show the new syntax, see an example :ref:`here <whatsnew_0180.window_deprecations>`
-   You can view the previous documentation
-   `here <http://pandas.pydata.org/pandas-docs/version/0.17.1/computation.html#moving-rolling-statistics-moments>`__
 
 For working with data, a number of windows functions are provided for
 computing common *window* or *rolling* statistics. Among these are count, sum,

doc/source/contributing.rst

@@ -877,12 +877,12 @@ directive is used. The sphinx syntax for that is:
 
 .. code-block:: rst
 
-  .. versionadded:: 0.17.0
+  .. versionadded:: 0.21.0
 
-This will put the text *New in version 0.17.0* wherever you put the sphinx
+This will put the text *New in version 0.21.0* wherever you put the sphinx
 directive. This should also be put in the docstring when adding a new function
-or method (`example <https://github.com/pandas-dev/pandas/blob/v0.16.2/pandas/core/generic.py#L1959>`__)
-or a new keyword argument (`example <https://github.com/pandas-dev/pandas/blob/v0.16.2/pandas/core/frame.py#L1171>`__).
+or method (`example <https://github.com/pandas-dev/pandas/blob/v0.20.2/pandas/core/frame.py#L1495>`__)
+or a new keyword argument (`example <https://github.com/pandas-dev/pandas/blob/v0.20.2/pandas/core/generic.py#L568>`__).
 
 Contributing your changes to *pandas*
 =====================================

doc/source/ecosystem.rst

@@ -146,7 +146,10 @@ API
 
 `pandas-datareader <https://github.com/pydata/pandas-datareader>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-``pandas-datareader`` is a remote data access library for pandas. ``pandas.io`` from pandas < 0.17.0 is now refactored/split-off to and importable from ``pandas_datareader`` (PyPI:``pandas-datareader``). Many/most of the supported APIs have at least a documentation paragraph in the `pandas-datareader docs <https://pandas-datareader.readthedocs.io/en/latest/>`_:
+``pandas-datareader`` is a remote data access library for pandas (PyPI:``pandas-datareader``).
+It is based on functionality that was located in ``pandas.io.data`` and ``pandas.io.wb`` but was
+split off in v0.19.
+See more in the  `pandas-datareader docs <https://pandas-datareader.readthedocs.io/en/latest/>`_:
 
 The following data feeds are available:
 

doc/source/gotchas.rst

@@ -47,8 +47,6 @@ 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``.
 
-.. versionadded:: 0.17.1
-
 Passing ``memory_usage='deep'`` will enable a more accurate memory usage report,
 that accounts for the full usage of the contained objects. This is optional
 as it can be expensive to do this deeper introspection.

doc/source/indexing.rst

@@ -1632,8 +1632,6 @@ Missing values
 
 .. _indexing.missing:
 
-.. versionadded:: 0.17.1
-
 .. important::
 
    Even though ``Index`` can hold missing values (``NaN``), it should be avoided

doc/source/io.rst

@@ -2689,11 +2689,6 @@ of sheet names can simply be passed to ``read_excel`` with no loss in performanc
     # equivalent using the read_excel function
     data = read_excel('path_to_file.xls', ['Sheet1', 'Sheet2'], index_col=None, na_values=['NA'])
 
-.. versionadded:: 0.17
-
-``read_excel`` can take an ``ExcelFile`` object as input
-
-
 .. _io.excel.specifying_sheets:
 
 Specifying Sheets
@@ -2754,8 +2749,6 @@ respectively.
 Reading a ``MultiIndex``
 ++++++++++++++++++++++++
 
-.. versionadded:: 0.17
-
 ``read_excel`` can read a ``MultiIndex`` index, by passing a list of columns to ``index_col``
 and a ``MultiIndex`` column by passing a list of rows to ``header``.  If either the ``index``
 or ``columns`` have serialized level names those will be read in as well by specifying
@@ -2928,14 +2921,8 @@ one can pass an :class:`~pandas.io.excel.ExcelWriter`.
 Writing Excel Files to Memory
 +++++++++++++++++++++++++++++
 
-.. versionadded:: 0.17
-
 Pandas supports writing Excel files to buffer-like objects such as ``StringIO`` or
-``BytesIO`` using :class:`~pandas.io.excel.ExcelWriter`.
-
-.. versionadded:: 0.17
-
-Added support for Openpyxl >= 2.2
+``BytesIO`` using :class:`~pandas.io.excel.ExcelWriter`. Pandas also supports Openpyxl >= 2.2.
 
 .. code-block:: python
 
@@ -3191,25 +3178,6 @@ both on the writing (serialization), and reading (deserialization).
    optimizations in the io of the ``msgpack`` data. Since this is marked
    as an EXPERIMENTAL LIBRARY, the storage format may not be stable until a future release.
 
-   As a result of writing format changes and other issues:
-
-   +----------------------+------------------------+
-   | Packed with          | Can be unpacked with   |
-   +======================+========================+
-   | pre-0.17 / Python 2  | any                    |
-   +----------------------+------------------------+
-   | pre-0.17 / Python 3  | any                    |
-   +----------------------+------------------------+
-   | 0.17 / Python 2      | - 0.17 / Python 2      |
-   |                      | - >=0.18 / any Python  |
-   +----------------------+------------------------+
-   | 0.17 / Python 3      | >=0.18 / any Python    |
-   +----------------------+------------------------+
-   | 0.18                 | >= 0.18                |
-   +----------------------+------------------------+
-
-   Reading (files packed by older versions) is backward-compatibile, except for files packed with 0.17 in Python 2, in which case only they can only be unpacked in Python 2.
-
 .. ipython:: python
 
    df = pd.DataFrame(np.random.rand(5,2),columns=list('AB'))
@@ -3287,10 +3255,6 @@ for some advanced strategies
    If you see a subset of results being returned, upgrade to ``PyTables`` >= 3.2.
    Stores created previously will need to be rewritten using the updated version.
 
-.. warning::
-
-   As of version 0.17.0, ``HDFStore`` will not drop rows that have all missing values by default. Previously, if all values (except the index) were missing, ``HDFStore`` would not write those rows to disk.
-
 .. ipython:: python
    :suppress:
    :okexcept:
@@ -3388,7 +3352,7 @@ similar to how ``read_csv`` and ``to_csv`` work.
    os.remove('store_tl.h5')
 
 
-As of version 0.17.0, HDFStore will no longer drop rows that are all missing by default. This behavior can be enabled by setting ``dropna=True``.
+HDFStore will by default not drop rows that are all missing. This behavior can be changed by setting ``dropna=True``.
 
 .. ipython:: python
    :suppress:
@@ -3632,12 +3596,6 @@ Querying
 Querying a Table
 ++++++++++++++++
 
-.. warning::
-
-   This query capabilities have changed substantially starting in ``0.13.0``.
-   Queries from prior version are accepted (with a ``DeprecationWarning``) printed
-   if its not string-like.
-
 ``select`` and ``delete`` operations have an optional criterion that can
 be specified to select/delete only a subset of the data. This allows one
 to have a very large on-disk table and retrieve only a portion of the
@@ -5098,10 +5056,8 @@ whether imported ``Categorical`` variables are ordered.
 SAS Formats
 -----------
 
-.. versionadded:: 0.17.0
-
 The top-level function :func:`read_sas` can read (but not write) SAS
-`xport` (.XPT) and `SAS7BDAT` (.sas7bdat) format files were added in *v0.18.0*.
+`xport` (.XPT) and (since *v0.18.0*) `SAS7BDAT` (.sas7bdat) format files.
 
 SAS files only contain two value types: ASCII text and floating point
 values (usually 8 bytes but sometimes truncated).  For xport files,

doc/source/merging.rst

@@ -550,8 +550,6 @@ standard database join operations between DataFrame objects:
   merge key only appears in ``'right'`` DataFrame, and ``both`` if the
   observation's merge key is found in both.
 
-  .. versionadded:: 0.17.0
-
 - ``validate`` : string, default None.
   If specified, checks if merge is of specified type.
 
@@ -766,9 +764,7 @@ If the user is aware of the duplicates in the right `DataFrame` but wants to ens
 The merge indicator
 ~~~~~~~~~~~~~~~~~~~
 
-.. versionadded:: 0.17.0
-
-``merge`` now accepts the argument ``indicator``. If ``True``, a Categorical-type column called ``_merge`` will be added to the output object that takes on values:
+``merge`` accepts the argument ``indicator``. If ``True``, a Categorical-type column called ``_merge`` will be added to the output object that takes on values:
 
   ===================================   ================
   Observation Origin                    ``_merge`` value

doc/source/missing_data.rst

@@ -352,10 +352,6 @@ examined :ref:`in the API <api.dataframe.missing>`.
 Interpolation
 ~~~~~~~~~~~~~
 
-.. versionadded:: 0.17.0
-
-  The ``limit_direction`` keyword argument was added.
-
 Both Series and DataFrame objects have an ``interpolate`` method that, by default,
 performs linear interpolation at missing datapoints.