Merge branch 'upstream' into pyx-diff

Author: nparley

doc/source/basics.rst

@@ -1159,14 +1159,17 @@ mapping (a dict or Series) or an arbitrary function.
    s.rename(str.upper)
 
 If you pass a function, it must return a value when called with any of the
-labels (and must produce a set of unique values). But if you pass a dict or
-Series, it need only contain a subset of the labels as keys:
+labels (and must produce a set of unique values). A dict or
+Series can also be used:
 
 .. ipython:: python
 
    df.rename(columns={'one' : 'foo', 'two' : 'bar'},
              index={'a' : 'apple', 'b' : 'banana', 'd' : 'durian'})
 
+If the mapping doesn't include a column/index label, it isn't renamed. Also
+extra labels in the mapping don't throw an error.
+
 The :meth:`~DataFrame.rename` method also provides an ``inplace`` named
 parameter that is by default ``False`` and copies the underlying data. Pass
 ``inplace=True`` to rename the data in place.

doc/source/ecosystem.rst

@@ -77,8 +77,16 @@ more advanced types of plots then those offered by pandas.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 The `Vincent <https://github.com/wrobstory/vincent>`__ project leverages `Vega <https://github.com/trifacta/vega>`__
-(that in turn, leverages `d3 <http://d3js.org/>`__) to create plots . It has great support
-for pandas data objects.
+(that in turn, leverages `d3 <http://d3js.org/>`__) to create
+plots. Although functional, as of Summer 2016 the Vincent project has not been updated 
+in over two years and is `unlikely to receive further updates <https://github.com/wrobstory/vincent#2015-08-12-update>`__.
+
+`IPython Vega <https://github.com/vega/ipyvega>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Like Vincent, the `IPython Vega <https://github.com/vega/ipyvega>`__ project leverages `Vega
+<https://github.com/trifacta/vega>`__ to create plots, but primarily
+targets the IPython Notebook environment.
 
 `Plotly <https://plot.ly/python>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

doc/source/groupby.rst

@@ -1015,6 +1015,23 @@ Regroup columns of a DataFrame according to their sum, and sum the aggregated on
    df
    df.groupby(df.sum(), axis=1).sum()
 
+Groupby by Indexer to 'resample' data
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Resampling produces new hypothetical samples(resamples) from already existing observed data or from a model that generates data. These new samples are similar to the pre-existing samples.
+
+In order to resample to work on indices that are non-datetimelike , the following procedure can be utilized.
+
+In the following examples, **df.index // 5** returns a binary array which is used to determine what get's selected for the groupby operation.
+
+.. note:: The below example shows how we can downsample by consolidation of samples into fewer samples. Here by using **df.index // 5**, we are aggregating the samples in bins. By applying **std()** function, we aggregate the information contained in many samples into a small subset of values which is their standard deviation thereby reducing the number of samples.
+
+.. ipython:: python
+
+   df = pd.DataFrame(np.random.randn(10,2))
+   df
+   df.index // 5
+   df.groupby(df.index // 5).std()
 
 Returning a Series to propagate names
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

doc/source/whatsnew/v0.18.1.txt

@@ -658,7 +658,7 @@ Bug Fixes
 - Bug in ``CategoricalIndex.get_loc`` returns different result from regular ``Index`` (:issue:`12531`)
 - Bug in ``PeriodIndex.resample`` where name not propagated (:issue:`12769`)
 
-
+- Bug in ``date_range`` ``closed`` keyword and timezones (:issue:`12684`).
 
 - Bug in ``pd.concat`` raises ``AttributeError`` when input data contains tz-aware datetime and timedelta (:issue:`12620`)
 - Bug in ``pd.concat`` did not handle empty ``Series`` properly (:issue:`11082`)

pandas/core/generic.py

@@ -555,8 +555,8 @@ def swaplevel(self, i=-2, j=-1, axis=0):
     _shared_docs['rename'] = """
         Alter axes input function or functions. Function / dict values must be
         unique (1-to-1). Labels not contained in a dict / Series will be left
-        as-is. Alternatively, change ``Series.name`` with a scalar
-        value (Series only).
+        as-is. Extra labels listed don't throw an error. Alternatively, change
+        ``Series.name`` with a scalar value (Series only).
 
         Parameters
         ----------
@@ -611,6 +611,11 @@ def swaplevel(self, i=-2, j=-1, axis=0):
         0  1  4
         1  2  5
         2  3  6
+        >>> df.rename(index=str, columns={"A": "a", "C": "c"})
+           a  B
+        0  1  4
+        1  2  5
+        2  3  6
         """
 
     @Appender(_shared_docs['rename'] % dict(axes='axes keywords for this'

pandas/tseries/index.py

@@ -541,6 +541,13 @@ def _generate(cls, start, end, periods, name, offset,
                                                  ambiguous=ambiguous)
                 index = index.view(_NS_DTYPE)
 
+                # index is localized datetime64 array -> have to convert
+                # start/end as well to compare
+                if start is not None:
+                    start = start.tz_localize(tz).asm8
+                if end is not None:
+                    end = end.tz_localize(tz).asm8
+
         if not left_closed and len(index) and index[0] == start:
             index = index[1:]
         if not right_closed and len(index) and index[-1] == end:

pandas/tseries/tests/test_daterange.py

@@ -485,7 +485,7 @@ def test_range_closed(self):
         begin = datetime(2011, 1, 1)
         end = datetime(2014, 1, 1)
 
-        for freq in ["3D", "2M", "7W", "3H", "A"]:
+        for freq in ["1D", "3D", "2M", "7W", "3H", "A"]:
             closed = date_range(begin, end, closed=None, freq=freq)
             left = date_range(begin, end, closed="left", freq=freq)
             right = date_range(begin, end, closed="right", freq=freq)
@@ -501,11 +501,11 @@ def test_range_closed(self):
             self.assert_index_equal(expected_right, right)
 
     def test_range_closed_with_tz_aware_start_end(self):
-        # GH12409
+        # GH12409, GH12684
         begin = Timestamp('2011/1/1', tz='US/Eastern')
         end = Timestamp('2014/1/1', tz='US/Eastern')
 
-        for freq in ["3D", "2M", "7W", "3H", "A"]:
+        for freq in ["1D", "3D", "2M", "7W", "3H", "A"]:
             closed = date_range(begin, end, closed=None, freq=freq)
             left = date_range(begin, end, closed="left", freq=freq)
             right = date_range(begin, end, closed="right", freq=freq)
@@ -520,15 +520,28 @@ def test_range_closed_with_tz_aware_start_end(self):
             self.assert_index_equal(expected_left, left)
             self.assert_index_equal(expected_right, right)
 
-        # test with default frequency, UTC
-        begin = Timestamp('2011/1/1', tz='UTC')
-        end = Timestamp('2014/1/1', tz='UTC')
+        begin = Timestamp('2011/1/1')
+        end = Timestamp('2014/1/1')
+        begintz = Timestamp('2011/1/1', tz='US/Eastern')
+        endtz = Timestamp('2014/1/1', tz='US/Eastern')
+
+        for freq in ["1D", "3D", "2M", "7W", "3H", "A"]:
+            closed = date_range(begin, end, closed=None, freq=freq,
+                                tz='US/Eastern')
+            left = date_range(begin, end, closed="left", freq=freq,
+                              tz='US/Eastern')
+            right = date_range(begin, end, closed="right", freq=freq,
+                               tz='US/Eastern')
+            expected_left = left
+            expected_right = right
 
-        intervals = ['left', 'right', None]
-        for i in intervals:
-            result = date_range(start=begin, end=end, closed=i)
-            self.assertEqual(result[0], begin)
-            self.assertEqual(result[-1], end)
+            if endtz == closed[-1]:
+                expected_left = closed[:-1]
+            if begintz == closed[0]:
+                expected_right = closed[1:]
+
+            self.assert_index_equal(expected_left, left)
+            self.assert_index_equal(expected_right, right)
 
     def test_range_closed_boundary(self):
         # GH 11804