Merge branch 'master' of https://github.com/pandas-dev/pandas into div_zero2

Author: jbrockmendel

asv_bench/benchmarks/rolling.py

@@ -11,8 +11,8 @@ class Methods(object):
               [10, 1000],
               ['int', 'float'],
               ['median', 'mean', 'max', 'min', 'std', 'count', 'skew', 'kurt',
-               'sum', 'corr', 'cov'])
-    param_names = ['constructor', 'window', 'dtype', 'method']
+               'sum'])
+    param_names = ['contructor', 'window', 'dtype', 'method']
 
     def setup(self, constructor, window, dtype, method):
         N = 10**5
@@ -23,6 +23,27 @@ def time_rolling(self, constructor, window, dtype, method):
         getattr(self.roll, method)()
 
 
+class Pairwise(object):
+
+    sample_time = 0.2
+    params = ([10, 1000, None],
+              ['corr', 'cov'],
+              [True, False])
+    param_names = ['window', 'method', 'pairwise']
+
+    def setup(self, window, method, pairwise):
+        N = 10**4
+        arr = np.random.random(N)
+        self.df = pd.DataFrame(arr)
+
+    def time_pairwise(self, window, method, pairwise):
+        if window is None:
+            r = self.df.expanding()
+        else:
+            r = self.df.rolling(window=window)
+        getattr(r, method)(self.df, pairwise=pairwise)
+
+
 class Quantile(object):
 
     sample_time = 0.2

doc/source/categorical.rst

@@ -209,19 +209,12 @@ Window Functions
 
 .. currentmodule:: pandas.core.window
 
-.. warning::
-
-   Prior to version 0.18.0, ``pd.rolling_*``, ``pd.expanding_*``, and ``pd.ewm*`` were module level
-   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>`.
-
-For working with data, a number of windows functions are provided for
+For working with data, a number of window functions are provided for
 computing common *window* or *rolling* statistics. Among these are count, sum,
 mean, median, correlation, variance, covariance, standard deviation, skewness,
 and kurtosis.
 
-Starting in version 0.18.1, the ``rolling()`` and ``expanding()``
+The ``rolling()`` and ``expanding()``
 functions can be used directly from DataFrameGroupBy objects,
 see the :ref:`groupby docs <groupby.transform.window_resample>`.
 

doc/source/computation.rst

@@ -190,7 +190,7 @@ Sum/Prod of Empties/Nans
 .. warning::
 
    This behavior is now standard as of v0.21.0; previously sum/prod would give different
-   results if the ``bottleneck`` package was installed. 
+   results if the ``bottleneck`` package was installed.
    See the :ref:`v0.21.0 whatsnew <whatsnew_0210.api_breaking.bottleneck>`.
 
 With ``sum`` or ``prod`` on an empty or all-``NaN`` ``Series``, or columns of a ``DataFrame``, the result will be all-``NaN``.
@@ -353,7 +353,11 @@ examined :ref:`in the API <api.dataframe.missing>`.
 Interpolation
 ~~~~~~~~~~~~~
 
-Both Series and DataFrame objects have an :meth:`~DataFrame.interpolate` method 
+.. versionadded:: 0.21.0
+
+  The ``limit_area`` keyword argument was added.
+
+Both Series and DataFrame objects have an :meth:`~DataFrame.interpolate` method
 that, by default, performs linear interpolation at missing datapoints.
 
 .. ipython:: python
@@ -477,33 +481,54 @@ at the new values.
 .. _documentation: http://docs.scipy.org/doc/scipy/reference/interpolate.html#univariate-interpolation
 .. _guide: http://docs.scipy.org/doc/scipy/reference/tutorial/interpolate.html
 
+.. _missing_data.interp_limits:
+
 Interpolation Limits
 ^^^^^^^^^^^^^^^^^^^^
 
 Like other pandas fill methods, ``interpolate`` accepts a ``limit`` keyword
-argument. Use this argument to limit the number of consecutive interpolations,
-keeping ``NaN`` values for interpolations that are too far from the last valid
-observation:
+argument. Use this argument to limit the number of consecutive ``NaN`` values
+filled since the last valid observation:
 
 .. ipython:: python
 
-   ser = pd.Series([np.nan, np.nan, 5, np.nan, np.nan, np.nan, 13])
-   ser.interpolate(limit=2)
+   ser = pd.Series([np.nan, np.nan, 5, np.nan, np.nan, np.nan, 13, np.nan, np.nan])
 
-By default, ``limit`` applies in a forward direction, so that only ``NaN``
-values after a non-``NaN`` value can be filled. If you provide ``'backward'`` or
-``'both'`` for the ``limit_direction`` keyword argument, you can fill ``NaN``
-values before non-``NaN`` values, or both before and after non-``NaN`` values,
-respectively:
+   # fill all consecutive values in a forward direction
+   ser.interpolate()
 
-.. ipython:: python
+   # fill one consecutive value in a forward direction
+   ser.interpolate(limit=1)
+
+By default, ``NaN`` values are filled in a ``forward`` direction. Use
+``limit_direction`` parameter to fill ``backward`` or from ``both`` directions.
 
-   ser.interpolate(limit=1)  # limit_direction == 'forward'
+.. ipython:: python
 
+   # fill one consecutive value backwards
    ser.interpolate(limit=1, limit_direction='backward')
 
+   # fill one consecutive value in both directions
    ser.interpolate(limit=1, limit_direction='both')
 
+   # fill all consecutive values in both directions
+   ser.interpolate(limit_direction='both')
+
+By default, ``NaN`` values are filled whether they are inside (surrounded by)
+existing valid values, or outside existing valid values. Introduced in v0.23
+the ``limit_area`` parameter restricts filling to either inside or outside values.
+
+.. ipython:: python
+
+   # fill one consecutive inside value in both directions
+   ser.interpolate(limit_direction='both', limit_area='inside', limit=1)
+
+   # fill all consecutive outside values backward
+   ser.interpolate(limit_direction='backward', limit_area='outside')
+
+   # fill all consecutive outside values in both directions
+   ser.interpolate(limit_direction='both', limit_area='outside')
+
 .. _missing_data.replace:
 
 Replacing Generic Values