pandas-dev · kotfic · Nov 11, 2014 · Nov 11, 2014 · Mar 22, 2015 · Mar 22, 2015
diff --git a/doc/source/10min.rst b/doc/source/10min.rst
@@ -12,7 +12,11 @@
    from pandas import options
    import pandas as pd
    np.set_printoptions(precision=4, suppress=True)
-   options.display.mpl_style='default'
+   import matplotlib
+   try:
+      matplotlib.style.use('ggplot')
+   except AttributeError:
+      options.display.mpl_style = 'default'
    options.display.max_rows=15
 
    #### portions of this were borrowed from the
@@ -695,8 +699,6 @@ Plotting
 
    import matplotlib.pyplot as plt
    plt.close('all')
-   from pandas import options
-   options.display.mpl_style='default'
 
 .. ipython:: python
 

diff --git a/doc/source/api.rst b/doc/source/api.rst
@@ -517,8 +517,6 @@ String handling
 strings and apply several methods to it. These can be acccessed like
 ``Series.str.<function/property>``.
 
-.. currentmodule:: pandas.core.strings
-
 .. autosummary::
    :toctree: generated/
    :template: autosummary/accessor_method.rst
@@ -863,6 +861,7 @@ Combining / joining / merging
    :toctree: generated/
 
    DataFrame.append
+   DataFrame.assign
    DataFrame.join
    DataFrame.merge
    DataFrame.update

diff --git a/doc/source/categorical.rst b/doc/source/categorical.rst
@@ -13,7 +13,6 @@
    from pandas import *
    import pandas as pd
    np.set_printoptions(precision=4, suppress=True)
-   options.display.mpl_style='default'
    options.display.max_rows=15
 
 

diff --git a/doc/source/computation.rst b/doc/source/computation.rst
@@ -10,9 +10,13 @@
    import pandas.util.testing as tm
    randn = np.random.randn
    np.set_printoptions(precision=4, suppress=True)
+   import matplotlib
+   try:
+      matplotlib.style.use('ggplot')
+   except AttributeError:
+      options.display.mpl_style = 'default'
    import matplotlib.pyplot as plt
    plt.close('all')
-   options.display.mpl_style='default'
    options.display.max_rows=15
 
 Computational tools

diff --git a/doc/source/cookbook.rst b/doc/source/cookbook.rst
@@ -17,7 +17,12 @@
    np.random.seed(123456)
 
    pd.options.display.max_rows=15
-   pd.options.display.mpl_style='default'
+
+   import matplotlib
+   try:
+      matplotlib.style.use('ggplot')
+   except AttributeError:
+      pd.options.display.mpl_style = 'default'
 
    np.set_printoptions(precision=4, suppress=True)
 

diff --git a/doc/source/faq.rst b/doc/source/faq.rst
@@ -21,7 +21,11 @@ Frequently Asked Questions (FAQ)
    from pandas.tseries.offsets import *
    import matplotlib.pyplot as plt
    plt.close('all')
-   options.display.mpl_style='default'
+   import matplotlib
+   try:
+      matplotlib.style.use('ggplot')
+   except AttributeError:
+      options.display.mpl_style = 'default'
    from pandas.compat import lrange
 
 

diff --git a/doc/source/groupby.rst b/doc/source/groupby.rst
@@ -12,7 +12,11 @@
    np.set_printoptions(precision=4, suppress=True)
    import matplotlib.pyplot as plt
    plt.close('all')
-   options.display.mpl_style='default'
+   import matplotlib
+   try:
+      matplotlib.style.use('ggplot')
+   except AttributeError:
+      options.display.mpl_style = 'default'
    from pandas.compat import zip
 
 *****************************
@@ -346,7 +350,7 @@ A single group can be selected using ``GroupBy.get_group()``:
 .. ipython:: python
 
    grouped.get_group('bar')
-   
+
 Or for an object grouped on multiple columns:
 
 .. ipython:: python

diff --git a/doc/source/indexing.rst b/doc/source/indexing.rst
@@ -1137,6 +1137,17 @@ should be taken instead.
    df2.drop_duplicates(['a','b'])
    df2.drop_duplicates(['a','b'], take_last=True)
 
+An alternative way to drop duplicates on the index is ``.groupby(level=0)`` combined with ``first()`` or ``last()``.
+
+.. ipython:: python
+
+   df3 = df2.set_index('b')
+   df3
+   df3.groupby(level=0).first()
+
+   # a bit more verbose
+   df3.reset_index().drop_duplicates(subset='b', take_last=False).set_index('b')
+
 .. _indexing.dictionarylike:
 
 Dictionary-like :meth:`~pandas.DataFrame.get` method

diff --git a/doc/source/sparse.rst b/doc/source/sparse.rst
@@ -10,9 +10,6 @@
    import pandas.util.testing as tm
    randn = np.random.randn
    np.set_printoptions(precision=4, suppress=True)
-   import matplotlib.pyplot as plt
-   plt.close('all')
-   options.display.mpl_style='default'
    options.display.max_rows = 15
 
 **********************
@@ -222,4 +219,3 @@ row and columns coordinates of the matrix. Note that this will consume a signifi
 
    ss_dense = SparseSeries.from_coo(A, dense_index=True)
    ss_dense
-
diff --git a/doc/source/visualization.rst b/doc/source/visualization.rst
@@ -31,10 +31,14 @@ We use the standard convention for referencing the matplotlib API:
 
    import matplotlib.pyplot as plt
 
-.. versionadded:: 0.11.0
+The plots in this document are made using matplotlib's ``ggplot`` style (new in version 1.4):
 
-The plots in this document are made using matplotlib's ``ggplot`` style (new in version 1.4).
-If your version of matplotlib is 1.3 or lower, setting the ``display.mpl_style`` to ``'default'``
+.. code-block:: python
+
+   import matplotlib
+   matplotlib.style.use('ggplot')
+
+If your version of matplotlib is 1.3 or lower, you can set ``display.mpl_style`` to ``'default'``
 with ``pd.options.display.mpl_style = 'default'``
 to produce more appealing plots.
 When set, matplotlib's ``rcParams`` are changed (globally!) to nicer-looking settings.

diff --git a/doc/source/whatsnew.rst b/doc/source/whatsnew.rst
@@ -18,6 +18,8 @@ What's New
 
 These are new features and improvements of note in each release.
 
+.. include:: whatsnew/v0.16.1.txt
+
 .. include:: whatsnew/v0.16.0.txt
 
 .. include:: whatsnew/v0.15.2.txt

diff --git a/doc/source/whatsnew/v0.16.1.txt b/doc/source/whatsnew/v0.16.1.txt
@@ -3,24 +3,34 @@
 v0.16.1 (April ??, 2015)
 ------------------------
 
-This is a minor bug-fix release from 0.16.0 and includes a small number of API changes, several new features,
-enhancements, and performance improvements along with a large number of bug fixes. We recommend that all
-users upgrade to this version.
+This is a minor bug-fix release from 0.16.0 and includes a a large number of
+bug fixes along several new features, enhancements, and performance improvements.
+We recommend that all users upgrade to this version.
+
+.. contents:: What's new in v0.16.1
+    :local:
+    :backlinks: none
+
+
+.. _whatsnew_0161.enhancements:
+
+Enhancements
+~~~~~~~~~~~~
+
+
+
+
 
-- :ref:`Enhancements <whatsnew_0161.enhancements>`
-- :ref:`API Changes <whatsnew_0161.api>`
-- :ref:`Performance Improvements <whatsnew_0161.performance>`
-- :ref:`Bug Fixes <whatsnew_0161.bug_fixes>`
 
 .. _whatsnew_0161.api:
 
 API changes
 ~~~~~~~~~~~
 
-.. _whatsnew_0161.enhancements:
 
-Enhancements
-~~~~~~~~~~~~
+
+
+
 
 - Add support for separating years and quarters using dashes, for
   example 2014-Q1.  (:issue:`9688`)
@@ -30,7 +40,27 @@ Enhancements
 Performance Improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
+
+
+
+
+
 .. _whatsnew_0161.bug_fixes:
 
 Bug Fixes
 ~~~~~~~~~
+
+
+
+
+
+- Bug in ``transform`` causing length mismatch when null entries were present and a fast aggregator was being used (:issue:`9697`)
+
+
+
+
+
+
+
+
+- Bug in ``Series.quantile`` on empty Series of type ``Datetime`` or ``Timedelta`` (:issue:`9675`)
diff --git a/pandas/core/format.py b/pandas/core/format.py
@@ -608,14 +608,20 @@ def get_col_type(dtype):
             strcols = self._to_str_columns()
 
         if self.index and isinstance(self.frame.index, MultiIndex):
-            clevels = self.frame.columns.nlevels
             strcols.pop(0)
-            name = any(self.frame.columns.names)
-            for i, lev in enumerate(self.frame.index.levels):
-                lev2 = lev.format(name=name)
-                width = len(lev2[0])
-                lev3 = [' ' * width] * clevels + lev2
-                strcols.insert(i, lev3)
+
+
+            fmt = self._get_formatter('__index__')
+            fmt_index = self.frame.index.format(sparsify=self.sparsify,
+                                                adjoin=False,
+                                                names=True,
+                                                formatter=fmt)
+
+            for i, lev in enumerate(fmt_index):
+                width = len(lev[0])
+                lev2 = [width * ' ' if l == '' else l for l in lev]
+                lev2.insert(0, width * ' ')
+                strcols.insert(i, lev2)
 
         if column_format is None:
             dtypes = self.frame.dtypes.values

diff --git a/pandas/core/groupby.py b/pandas/core/groupby.py
@@ -2453,7 +2453,7 @@ def _transform_fast(self, func):
         if isinstance(func, compat.string_types):
             func = getattr(self,func)
         values = func().values
-        counts = self.count().values
+        counts = self.size().values
         values = np.repeat(values, com._ensure_platform_int(counts))
 
         return self._set_result_index_ordered(Series(values))

diff --git a/pandas/core/series.py b/pandas/core/series.py
@@ -2095,7 +2095,7 @@ def _maybe_box(self, func, dropna=False):
             boxer = com.i8_boxer(self)
 
             if len(values) == 0:
-                return boxer(iNaT)
+                return boxer(tslib.iNaT)
 
             values = values.view('i8')
             result = func(values)

diff --git a/pandas/tests/test_groupby.py b/pandas/tests/test_groupby.py
@@ -1058,6 +1058,19 @@ def test_transform_function_aliases(self):
         expected = self.df.groupby('A')['C'].transform(np.mean)
         assert_series_equal(result, expected)
 
+    def test_transform_length(self):
+        # GH 9697
+        df = pd.DataFrame({'col1':[1,1,2,2], 'col2':[1,2,3,np.nan]})
+        expected = pd.Series([3.0]*4)
+        def nsum(x):
+            return np.nansum(x)
+        results = [df.groupby('col1').transform(sum)['col2'],
+                   df.groupby('col1')['col2'].transform(sum),
+                   df.groupby('col1').transform(nsum)['col2'],
+                   df.groupby('col1')['col2'].transform(nsum)]
+        for result in results:
+            assert_series_equal(result, expected)
+
     def test_with_na(self):
         index = Index(np.arange(10))
 

diff --git a/pandas/tests/test_series.py b/pandas/tests/test_series.py
@@ -6837,6 +6837,11 @@ def test_repeat(self):
     def test_unique_data_ownership(self):
         # it works! #1807
         Series(Series(["a", "c", "b"]).unique()).sort()
+
+    def test_datetime_timedelta_quantiles(self):
+        # covers #9694
+        self.assertTrue(pd.isnull(Series([],dtype='M8[ns]').quantile(.5)))
+        self.assertTrue(pd.isnull(Series([],dtype='m8[ns]').quantile(.5)))
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],

diff --git a/pandas/tseries/tests/test_tslib.py b/pandas/tseries/tests/test_tslib.py
@@ -167,7 +167,7 @@ def test_repr(self):
 
         # dateutil zone change (only matters for repr)
         import dateutil
-        if dateutil.__version__ >= LooseVersion('2.3') and dateutil.__version__ <= LooseVersion('2.4'):
+        if dateutil.__version__ >= LooseVersion('2.3') and dateutil.__version__ <= LooseVersion('2.4.0'):
             timezones = ['UTC', 'Asia/Tokyo', 'US/Eastern', 'dateutil/US/Pacific']
         else:
             timezones = ['UTC', 'Asia/Tokyo', 'US/Eastern', 'dateutil/America/Los_Angeles']