Merge branch 'master' of https://github.com/pydata/pandas

Author: cscanlin

asv_bench/benchmarks/categoricals.py

@@ -46,6 +46,22 @@ def time_fastpath(self):
         Categorical(self.codes, self.cat_idx, fastpath=True)
 
 
+class categorical_constructor_with_datetimes(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.datetimes = pd.Series(pd.date_range(
+            '1995-01-01 00:00:00', periods=10000, freq='s'))
+
+    def time_datetimes(self):
+        Categorical(self.datetimes)
+
+    def time_datetimes_with_nat(self):
+        t = self.datetimes
+        t.iloc[-1] = pd.NaT
+        Categorical(t)
+
+
 class categorical_rendering(object):
     goal_time = 3e-3
 

asv_bench/benchmarks/timeseries.py

@@ -1059,33 +1059,27 @@ class timeseries_to_datetime_iso8601(object):
     goal_time = 0.2
 
     def setup(self):
-        self.N = 100000
-        self.rng = date_range(start='1/1/2000', periods=self.N, freq='T')
-        if hasattr(Series, 'convert'):
-            Series.resample = Series.convert
-        self.ts = Series(np.random.randn(self.N), index=self.rng)
         self.rng = date_range(start='1/1/2000', periods=20000, freq='H')
         self.strings = [x.strftime('%Y-%m-%d %H:%M:%S') for x in self.rng]
+        self.strings_nosep = [x.strftime('%Y%m%d %H:%M:%S') for x in self.rng]
+        self.strings_tz_space = [x.strftime('%Y-%m-%d %H:%M:%S') + ' -0800'
+                                 for x in self.rng]
 
     def time_timeseries_to_datetime_iso8601(self):
         to_datetime(self.strings)
 
-
-class timeseries_to_datetime_iso8601_format(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 100000
-        self.rng = date_range(start='1/1/2000', periods=self.N, freq='T')
-        if hasattr(Series, 'convert'):
-            Series.resample = Series.convert
-        self.ts = Series(np.random.randn(self.N), index=self.rng)
-        self.rng = date_range(start='1/1/2000', periods=20000, freq='H')
-        self.strings = [x.strftime('%Y-%m-%d %H:%M:%S') for x in self.rng]
+    def time_timeseries_to_datetime_iso8601_nosep(self):
+        to_datetime(self.strings_nosep)
 
     def time_timeseries_to_datetime_iso8601_format(self):
         to_datetime(self.strings, format='%Y-%m-%d %H:%M:%S')
 
+    def time_timeseries_to_datetime_iso8601_format_no_sep(self):
+        to_datetime(self.strings_nosep, format='%Y%m%d %H:%M:%S')
+
+    def time_timeseries_to_datetime_iso8601_tz_spaceformat(self):
+        to_datetime(self.strings_tz_space)
+
 
 class timeseries_with_format_no_exact(object):
     goal_time = 0.2
@@ -1160,4 +1154,4 @@ def setup(self):
         self.cdayh = pd.offsets.CustomBusinessDay(calendar=self.hcal)
 
     def time_timeseries_year_incr(self):
-        (self.date + self.year)
+        (self.date + self.year)

ci/requirements-2.7_DOC_BUILD.run

@@ -1,4 +1,4 @@
-ipython=3.2.1
+ipython
 nbconvert
 matplotlib
 scipy

conda.recipe/meta.yaml

@@ -6,14 +6,13 @@ build:
     number: {{ environ.get('GIT_DESCRIBE_NUMBER', 0) }}
 
 source:
-    path: ../../
+    path: ../
 
 requirements:
   build:
     - python
     - cython
     - numpy x.x
-    - libpython # [py2k and win]
     - setuptools
     - pytz
     - python-dateutil

doc/source/install.rst

@@ -192,32 +192,31 @@ installed), make sure you have `nose
 
 ::
 
-    $ nosetests pandas
-    ..........................................................................
-    .......................S..................................................
-    ..........................................................................
-    ..........................................................................
-    ..........................................................................
-    ..........................................................................
-    ..........................................................................
-    ..........................................................................
-    ..........................................................................
-    ..........................................................................
-    .................S........................................................
-    ....
+    >>> import pandas as pd
+    >>> pd.test()
+    Running unit tests for pandas
+    pandas version 0.18.0
+    numpy version 1.10.2
+    pandas is installed in pandas
+    Python version 2.7.11 |Continuum Analytics, Inc.|
+       (default, Dec  6 2015, 18:57:58) [GCC 4.2.1 (Apple Inc. build 5577)]
+    nose version 1.3.7
+    ..................................................................S......
+    ........S................................................................
+    .........................................................................
+
     ----------------------------------------------------------------------
-    Ran 818 tests in 21.631s
+    Ran 9252 tests in 368.339s
 
-    OK (SKIP=2)
+    OK (SKIP=117)
 
 Dependencies
 ------------
 
 * `setuptools <http://pythonhosted.org/setuptools>`__
 * `NumPy <http://www.numpy.org>`__: 1.7.1 or higher
-* `python-dateutil <http://labix.org/python-dateutil>`__ 1.5 or higher
-* `pytz <http://pytz.sourceforge.net/>`__
-   * Needed for time zone support
+* `python-dateutil <http://labix.org/python-dateutil>`__: 1.5 or higher
+* `pytz <http://pytz.sourceforge.net/>`__: Needed for time zone support
 
 .. _install.recommended_dependencies:
 
@@ -226,7 +225,7 @@ Recommended Dependencies
 
 * `numexpr <https://github.com/pydata/numexpr>`__: for accelerating certain numerical operations.
   ``numexpr`` uses multiple cores as well as smart chunking and caching to achieve large speedups.
-  If installed, must be Version 2.1 or higher.
+  If installed, must be Version 2.1 or higher. Version 2.4.6 or higher on Windows is highly recommended.
 
 * `bottleneck <http://berkeleyanalytics.com/bottleneck>`__: for accelerating certain types of ``nan``
   evaluations. ``bottleneck`` uses specialized cython routines to achieve large speedups.
@@ -246,21 +245,16 @@ Optional Dependencies
   version. Version 0.19.1 or higher.
 * `SciPy <http://www.scipy.org>`__: miscellaneous statistical functions
 * `PyTables <http://www.pytables.org>`__: necessary for HDF5-based storage. Version 3.0.0 or higher required, Version 3.2.1 or higher highly recommended.
-* `SQLAlchemy <http://www.sqlalchemy.org>`__: for SQL database support. Version 0.8.1 or higher recommended.
-  * Besides SQLAlchemy, you also need a database specific driver.
-    Examples of such drivers are `psycopg2 <http://initd.org/psycopg/>`__ for PostgreSQL
-    or `pymysql <https://github.com/PyMySQL/PyMySQL>`__ for MySQL. For
-    `SQLite <https://docs.python.org/3.5/library/sqlite3.html>`__ this is
-    included in Python's standard library by default.
-    You can find an overview of supported drivers for each SQL dialect in the
-    `SQLAlchemy docs <http://docs.sqlalchemy.org/en/latest/dialects/index.html>`__.
+* `SQLAlchemy <http://www.sqlalchemy.org>`__: for SQL database support. Version 0.8.1 or higher recommended. Besides SQLAlchemy, you also need a database specific driver. You can find an overview of supported drivers for each SQL dialect in the `SQLAlchemy docs <http://docs.sqlalchemy.org/en/latest/dialects/index.html>`__. Some common drivers are:
+
+    - `psycopg2 <http://initd.org/psycopg/>`__: for PostgreSQL
+    - `pymysql <https://github.com/PyMySQL/PyMySQL>`__: for MySQL.
+    - `SQLite <https://docs.python.org/3.5/library/sqlite3.html>`__: for SQLite, this is included in Python's standard library by default.
+
 * `matplotlib <http://matplotlib.sourceforge.net/>`__: for plotting
-* `statsmodels <http://statsmodels.sourceforge.net/>`__
-   * Needed for parts of :mod:`pandas.stats`
-* `openpyxl <http://packages.python.org/openpyxl/>`__, `xlrd/xlwt <http://www.python-excel.org/>`__
-   * Needed for Excel I/O
-* `XlsxWriter <https://pypi.python.org/pypi/XlsxWriter>`__
-   * Alternative Excel writer
+* `statsmodels <http://statsmodels.sourceforge.net/>`__: Needed for parts of :mod:`pandas.stats`
+* `openpyxl <http://packages.python.org/openpyxl/>`__, `xlrd/xlwt <http://www.python-excel.org/>`__: Needed for Excel I/O
+* `XlsxWriter <https://pypi.python.org/pypi/XlsxWriter>`__: Alternative Excel writer
 * `Jinja2 <http://jinja.pocoo.org/>`__: Template engine for conditional HTML formatting.
 * `boto <https://pypi.python.org/pypi/boto>`__: necessary for Amazon S3
   access.
@@ -271,16 +265,10 @@ Optional Dependencies
   <http://www.pygtk.org/>`__, `xsel
   <http://www.vergenet.net/~conrad/software/xsel/>`__, or `xclip
   <http://sourceforge.net/projects/xclip/>`__: necessary to use
-  :func:`~pandas.io.clipboard.read_clipboard`. Most package managers on Linux
-  distributions will have xclip and/or xsel immediately available for
-  installation.
+  :func:`~pandas.io.clipboard.read_clipboard`. Most package managers on Linux distributions will have ``xclip`` and/or ``xsel`` immediately available for installation.
 * Google's `python-gflags <http://code.google.com/p/python-gflags/>`__
-  and `google-api-python-client <http://github.com/google/google-api-python-client>`__
-  * Needed for :mod:`~pandas.io.gbq`
-* `setuptools <https://pypi.python.org/pypi/setuptools/>`__
-  * Needed for :mod:`~pandas.io.gbq` (specifically, it utilizes `pkg_resources`)
-* `httplib2 <http://pypi.python.org/pypi/httplib2>`__
-  * Needed for :mod:`~pandas.io.gbq`
+  and `google-api-python-client <http://github.com/google/google-api-python-client>`__: Needed for :mod:`~pandas.io.gbq`
+* `httplib2 <http://pypi.python.org/pypi/httplib2>`__: Needed for :mod:`~pandas.io.gbq`
 * One of the following combinations of libraries is needed to use the
   top-level :func:`~pandas.io.html.read_html` function:
 
@@ -327,5 +315,5 @@ Optional Dependencies
 
    Without the optional dependencies, many useful features will not
    work. Hence, it is highly recommended that you install these. A packaged
-   distribution like `Enthought Canopy
+   distribution like `Anaconda <http://docs.continuum.io/anaconda/>`__, or `Enthought Canopy
    <http://enthought.com/products/canopy>`__ may be worth considering.

doc/source/reshaping.rst

@@ -228,6 +228,27 @@ which level in the columns to stack:
    df2.stack('exp')
    df2.stack('animal')
 
+Unstacking can result in missing values if subgroups do not have the same
+set of labels.  By default, missing values will be replaced with the default
+fill value for that data type, ``NaN`` for float, ``NaT`` for datetimelike,
+etc.  For integer types, by default data will converted to float and missing
+values will be set to ``NaN``.
+
+.. ipython:: python
+
+   df3 = df.iloc[[0, 1, 4, 7], [1, 2]]
+   df3
+   df3.unstack()
+
+.. versionadded: 0.18.0
+
+Alternatively, unstack takes an optional ``fill_value`` argument, for specifying
+the value of missing data.
+
+.. ipython:: python
+
+   df3.unstack(fill_value=-1e9)
+
 With a MultiIndex
 ~~~~~~~~~~~~~~~~~