Resolving merge conflict by incorporating @jreback suggestions

Author: Carlos Souza

.travis.yml

@@ -1,12 +1,15 @@
 sudo: false
 language: python
+# Default Python version is usually 2.7
+python: 3.5
 
 # To turn off cached cython files and compiler cache
 # set NOCACHE-true
 # To delete caches go to https://travis-ci.org/OWNER/REPOSITORY/caches or run
 # travis cache --delete inside the project directory from the travis command line client
 # The cash directories will be deleted if anything in ci/ changes in a commit
 cache:
+ ccache: true
  directories:
   - $HOME/.cache # cython cache
   - $HOME/.ccache # compiler cache
@@ -23,75 +26,67 @@ git:
 
 matrix:
     fast_finish: true
+    exclude:
+      # Exclude the default Python 3.5 build
+      - python: 3.5
     include:
-    - language: objective-c
-      os: osx
-      compiler: clang
-      cache:
-        ccache: true
-        directories:
-          - $HOME/.cache # cython cache
-          - $HOME/.ccache # compiler cache
+    - os: osx
+      language: generic
       env:
-        - JOB="3.5_OSX" TEST_ARGS="--skip-slow --skip-network" TRAVIS_PYTHON_VERSION=3.5
-    - python: 2.7
+        - JOB="3.5_OSX" TEST_ARGS="--skip-slow --skip-network"
+    - os: linux
       env:
         - JOB="2.7_LOCALE" TEST_ARGS="--only-slow --skip-network" LOCALE_OVERRIDE="zh_CN.UTF-8"
       addons:
         apt:
           packages:
           - language-pack-zh-hans
-    - python: 2.7
+    - os: linux
       env:
         - JOB="2.7" TEST_ARGS="--skip-slow" LINT=true
       addons:
         apt:
           packages:
           - python-gtk2
-    - python: 3.5
+    - os: linux
       env:
         - JOB="3.5" TEST_ARGS="--skip-slow --skip-network" COVERAGE=true
       addons:
         apt:
           packages:
           - xsel
-    - python: 3.6
+    - os: linux
       env:
         - JOB="3.6" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" CONDA_FORGE=true
-      addons:
-        apt:
-          packages:
-          - libatlas-base-dev
-          - gfortran
     # In allow_failures
-    - python: 2.7
+    - os: linux
       env:
         - JOB="2.7_SLOW" TEST_ARGS="--only-slow --skip-network"
     # In allow_failures
-    - python: 2.7
+    - os: linux
       env:
         - JOB="2.7_BUILD_TEST" TEST_ARGS="--skip-slow" BUILD_TEST=true
     # In allow_failures
-    - python: 3.6
+    - os: linux
       env:
         - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
     # In allow_failures
-    - python: 3.5
+    - os: linux
       env:
-        - JOB="3.5_DOC_BUILD" DOC_BUILD=true
+        - JOB="3.5_DOC" DOC=true
     allow_failures:
-      - python: 2.7
+      - os: linux
         env:
           - JOB="2.7_SLOW" TEST_ARGS="--only-slow --skip-network"
-      - python: 2.7
+      - os: linux
         env:
           - JOB="2.7_BUILD_TEST" TEST_ARGS="--skip-slow" BUILD_TEST=true
-      - python: 3.6
+      - os: linux
         env:
           - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
-      - python: 3.5
+      - os: linux
         env:
-          - JOB="3.5_DOC_BUILD" DOC_BUILD=true
+          - JOB="3.5_DOC" DOC=true
 
 before_install:
   - echo "before_install"

ci/build_docs.sh

@@ -17,7 +17,7 @@ if [ "$?" != "0" ]; then
 fi
 
 
-if [ x"$DOC_BUILD" != x"" ]; then
+if [ "$DOC" ]; then
 
     echo "Will build docs"
 

ci/install_travis.sh

@@ -77,8 +77,9 @@ if [ -z "$NOCACHE" ] && [ "${TRAVIS_OS_NAME}" == "linux" ]; then
     echo "[ccache]: $ccache"
     export CC='ccache gcc'
 elif [ -z "$NOCACHE" ] && [ "${TRAVIS_OS_NAME}" == "osx" ]; then
+    echo "[Install ccache]"
+    brew install ccache > /dev/null 2>&1
     echo "[Using ccache]"
-    time brew install ccache
     export PATH=/usr/local/opt/ccache/libexec:$PATH
     gcc=$(which gcc)
     echo "[gcc]: $gcc"

ci/requirements-3.5_DOC_BUILD.build renamed to ci/requirements-3.5_DOC.build

@@ -1,6 +1,5 @@
 python=3.5*
 python-dateutil
 pytz
-nomkl
 numpy
 cython

ci/requirements-3.5_DOC_BUILD.run renamed to ci/requirements-3.5_DOC.run

@@ -4,11 +4,6 @@ echo "[script multi]"
 
 source activate pandas
 
-# don't run the tests for the doc build
-if [ x"$DOC_BUILD" != x"" ]; then
-    exit 0
-fi
-
 if [ -n "$LOCALE_OVERRIDE" ]; then
     export LC_ALL="$LOCALE_OVERRIDE";
     echo "Setting LC_ALL to $LOCALE_OVERRIDE"
@@ -26,6 +21,8 @@ echo PYTHONHASHSEED=$PYTHONHASHSEED
 if [ "$BUILD_TEST" ]; then
     cd /tmp
     python -c "import pandas; pandas.test(['-n 2'])"
+elif [ "$DOC" ]; then
+    echo "We are not running pytest as this is a doc-build"
 elif [ "$COVERAGE" ]; then
     echo pytest -s -n 2 -m "not single" --cov=pandas --cov-report xml:/tmp/cov-multiple.xml --junitxml=/tmp/multiple.xml $TEST_ARGS pandas
     pytest -s -n 2 -m "not single" --cov=pandas --cov-report xml:/tmp/cov-multiple.xml --junitxml=/tmp/multiple.xml $TEST_ARGS pandas

ci/requirements-3.5_DOC_BUILD.sh renamed to ci/requirements-3.5_DOC.sh

@@ -4,11 +4,6 @@ echo "[script_single]"
 
 source activate pandas
 
-# don't run the tests for the doc build
-if [ x"$DOC_BUILD" != x"" ]; then
-    exit 0
-fi
-
 if [ -n "$LOCALE_OVERRIDE" ]; then
     export LC_ALL="$LOCALE_OVERRIDE";
     echo "Setting LC_ALL to $LOCALE_OVERRIDE"
@@ -18,7 +13,9 @@ if [ -n "$LOCALE_OVERRIDE" ]; then
 fi
 
 if [ "$BUILD_TEST" ]; then
-    echo "We are not running pytest as this is simply a build test."
+    echo "We are not running pytest as this is a build test."
+elif [ "$DOC" ]; then
+    echo "We are not running pytest as this is a doc-build"
 elif [ "$COVERAGE" ]; then
     echo pytest -s -m "single" --cov=pandas --cov-report xml:/tmp/cov-single.xml --junitxml=/tmp/single.xml $TEST_ARGS pandas
     pytest -s -m "single" --cov=pandas --cov-report xml:/tmp/cov-single.xml --junitxml=/tmp/single.xml $TEST_ARGS pandas

ci/script_multi.sh

@@ -84,29 +84,28 @@ will be completed:
 
    @verbatim
    In [1]: df2.<TAB>
-   df2.A                  df2.boxplot
-   df2.abs                df2.C
-   df2.add                df2.clip
-   df2.add_prefix         df2.clip_lower
-   df2.add_suffix         df2.clip_upper
-   df2.align              df2.columns
-   df2.all                df2.combine
-   df2.any                df2.combineAdd
+   df2.A                  df2.bool
+   df2.abs                df2.boxplot
+   df2.add                df2.C
+   df2.add_prefix         df2.clip
+   df2.add_suffix         df2.clip_lower
+   df2.align              df2.clip_upper
+   df2.all                df2.columns
+   df2.any                df2.combine
    df2.append             df2.combine_first
-   df2.apply              df2.combineMult
-   df2.applymap           df2.compound
-   df2.as_blocks          df2.consolidate
-   df2.asfreq             df2.convert_objects
-   df2.as_matrix          df2.copy
-   df2.astype             df2.corr
-   df2.at                 df2.corrwith
-   df2.at_time            df2.count
-   df2.axes               df2.cov
-   df2.B                  df2.cummax
-   df2.between_time       df2.cummin
-   df2.bfill              df2.cumprod
-   df2.blocks             df2.cumsum
-   df2.bool               df2.D
+   df2.apply              df2.compound
+   df2.applymap           df2.consolidate
+   df2.as_blocks          df2.convert_objects
+   df2.asfreq             df2.copy
+   df2.as_matrix          df2.corr
+   df2.astype             df2.corrwith
+   df2.at                 df2.count
+   df2.at_time            df2.cov
+   df2.axes               df2.cummax
+   df2.B                  df2.cummin
+   df2.between_time       df2.cumprod
+   df2.bfill              df2.cumsum
+   df2.blocks             df2.D
 
 As you can see, the columns ``A``, ``B``, ``C``, and ``D`` are automatically
 tab completed. ``E`` is there as well; the rest of the attributes have been

ci/script_single.sh

@@ -230,6 +230,15 @@ Categories must be unique or a `ValueError` is raised:
     except ValueError as e:
         print("ValueError: " + str(e))
 
+Categories must also not be ``NaN`` or a `ValueError` is raised:
+
+.. ipython:: python
+
+    try:
+        s.cat.categories = [1,2,np.nan]
+    except ValueError as e:
+        print("ValueError: " + str(e))
+
 Appending new categories
 ~~~~~~~~~~~~~~~~~~~~~~~~
 

doc/source/10min.rst

@@ -93,8 +93,8 @@ targets the IPython Notebook environment.
 
 `Plotly’s <https://plot.ly/>`__ `Python API <https://plot.ly/python/>`__ enables interactive figures and web shareability. Maps, 2D, 3D, and live-streaming graphs are rendered with WebGL and `D3.js <http://d3js.org/>`__. The library supports plotting directly from a pandas DataFrame and cloud-based collaboration. Users of `matplotlib, ggplot for Python, and Seaborn <https://plot.ly/python/matplotlib-to-plotly-tutorial/>`__ can convert figures into interactive web-based plots. Plots can be drawn in `IPython Notebooks <https://plot.ly/ipython-notebooks/>`__ , edited with R or MATLAB, modified in a GUI, or embedded in apps and dashboards. Plotly is free for unlimited sharing, and has `cloud <https://plot.ly/product/plans/>`__, `offline <https://plot.ly/python/offline/>`__, or `on-premise <https://plot.ly/product/enterprise/>`__ accounts for private use.
 
-Visualizing Data in Qt applications
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+`QtPandas <https://github.com/draperjames/qtpandas>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Spun off from the main pandas library, the `qtpandas <https://github.com/draperjames/qtpandas>`__
 library enables DataFrame visualization and manipulation in PyQt4 and PySide applications.

doc/source/categorical.rst

@@ -91,11 +91,12 @@ filepath_or_buffer : various
   locations), or any object with a ``read()`` method (such as an open file or
   :class:`~python:io.StringIO`).
 sep : str, defaults to ``','`` for :func:`read_csv`, ``\t`` for :func:`read_table`
-  Delimiter to use. If sep is ``None``,
-  will try to automatically determine this. Separators longer than 1 character
-  and different from ``'\s+'`` will be interpreted as regular expressions, will
-  force use of the python parsing engine and will ignore quotes in the data.
-  Regex example: ``'\\r\\t'``.
+  Delimiter to use. If sep is ``None``, the C engine cannot automatically detect
+  the separator, but the Python parsing engine can, meaning the latter will be
+  used automatically. In addition, separators longer than 1 character and
+  different from ``'\s+'`` will be interpreted as regular expressions and
+  will also force the use of the Python parsing engine. Note that regex
+  delimiters are prone to ignoring quoted data. Regex example: ``'\\r\\t'``.
 delimiter : str, default ``None``
   Alternative argument name for sep.
 delim_whitespace : boolean, default False
@@ -2766,6 +2767,20 @@ indices to be parsed.
 
    read_excel('path_to_file.xls', 'Sheet1', parse_cols=[0, 2, 3])
 
+
+Parsing Dates
++++++++++++++
+
+Datetime-like values are normally automatically converted to the appropriate
+dtype when reading the excel file. But if you have a column of strings that
+*look* like dates (but are not actually formatted as dates in excel), you can
+use the `parse_dates` keyword to parse those strings to datetimes:
+
+.. code-block:: python
+
+   read_excel('path_to_file.xls', 'Sheet1', parse_dates=['date_strings'])
+
+
 Cell Converters
 +++++++++++++++
 

doc/source/ecosystem.rst

@@ -146,8 +146,8 @@ following code will cause trouble because of the regular expression meaning of
    # We need to escape the special character (for >1 len patterns)
    dollars.str.replace(r'-\$', '-')
 
-The ``replace`` method can also take a callable as replacement. It is called 
-on every ``pat`` using :func:`re.sub`. The callable should expect one 
+The ``replace`` method can also take a callable as replacement. It is called
+on every ``pat`` using :func:`re.sub`. The callable should expect one
 positional argument (a regex object) and return a string.
 
 .. versionadded:: 0.20.0
@@ -372,21 +372,20 @@ You can check whether elements contain a pattern:
 
 .. ipython:: python
 
-   pattern = r'[a-z][0-9]'
+   pattern = r'[0-9][a-z]'
    pd.Series(['1', '2', '3a', '3b', '03c']).str.contains(pattern)
 
 or match a pattern:
 
-
 .. ipython:: python
 
-   pd.Series(['1', '2', '3a', '3b', '03c']).str.match(pattern, as_indexer=True)
+   pd.Series(['1', '2', '3a', '3b', '03c']).str.match(pattern)
 
 The distinction between ``match`` and ``contains`` is strictness: ``match``
 relies on strict ``re.match``, while ``contains`` relies on ``re.search``.
 
 Methods like ``match``, ``contains``, ``startswith``, and ``endswith`` take
- an extra ``na`` argument so missing values can be considered True or False:
+an extra ``na`` argument so missing values can be considered True or False:
 
 .. ipython:: python
 

doc/source/io.rst

@@ -270,7 +270,7 @@ To convert a ``SparseDataFrame`` back to sparse SciPy matrix in COO format, you
 
 .. _whatsnew_0200.enhancements.other:
 
-Other enhancements
+Other Enhancements
 ^^^^^^^^^^^^^^^^^^
 
 - Integration with the ``feather-format``, including a new top-level ``pd.read_feather()`` and ``DataFrame.to_feather()`` method, see :ref:`here <io.feather>`.
@@ -314,6 +314,7 @@ Other enhancements
 - ``pd.types.concat.union_categoricals`` gained the ``ignore_ordered`` argument to allow ignoring the ordered attribute of unioned categoricals (:issue:`13410`). See the :ref:`categorical union docs <categorical.union>` for more information.
 - ``pandas.io.json.json_normalize()`` with an empty ``list`` will return an empty ``DataFrame`` (:issue:`15534`)
 - ``pd.DataFrame.to_latex`` and ``pd.DataFrame.to_string`` now allow optional header aliases. (:issue:`15536`)
+- Re-enable the ``parse_dates`` keyword of ``read_excel`` to parse string columns as dates (:issue:`14326`)
 
 .. _ISO 8601 duration: https://en.wikipedia.org/wiki/ISO_8601#Durations
 
@@ -771,7 +772,8 @@ Other API Changes
   since pandas version 0.13.0 and can be done with the ``Series.str.extract``
   method (:issue:`5224`). As a consequence, the ``as_indexer`` keyword is
   ignored (no longer needed to specify the new behaviour) and is deprecated.
-
+- ``NaT`` will now correctly report ``False`` for datetimelike boolean operations such as ``is_month_start`` (:issue:`15781`)
+- ``NaT`` will now correctly return ``np.nan`` for ``Timedelta`` and ``Period`` accessors such as ``days`` and ``quarter`` (:issue:`15782`)
 
 .. _whatsnew_0200.deprecations:
 
@@ -816,9 +818,11 @@ Removal of prior version deprecations/changes
   in favor of ``iloc`` and ``iat`` as explained :ref:`here <whatsnew_0170.deprecations>` (:issue:`10711`).
 - The deprecated ``DataFrame.iterkv()`` has been removed in favor of ``DataFrame.iteritems()`` (:issue:`10711`)
 - The ``Categorical`` constructor has dropped the ``name`` parameter (:issue:`10632`)
+- ``Categorical`` has dropped support for ``NaN`` categories (:issue:`10748`)
 - The ``take_last`` parameter has been dropped from ``duplicated()``, ``drop_duplicates()``, ``nlargest()``, and ``nsmallest()`` methods (:issue:`10236`, :issue:`10792`, :issue:`10920`)
 - ``Series``, ``Index``, and ``DataFrame`` have dropped the ``sort`` and ``order`` methods (:issue:`10726`)
 - Where clauses in ``pytables`` are only accepted as strings and expressions types and not other data-types (:issue:`12027`)
+- ``DataFrame`` has dropped the ``combineAdd`` and ``combineMult`` methods in favor of ``add`` and ``mul`` respectively (:issue:`10735`)
 
 .. _whatsnew_0200.performance:
 
@@ -879,6 +883,8 @@ Bug Fixes
 
 - Bug in the display of ``.info()`` where a qualifier (+) would always be displayed with a ``MultiIndex`` that contains only non-strings (:issue:`15245`)
 - Bug in ``.replace()`` may result in incorrect dtypes. (:issue:`12747`, :issue:`15765`)
+- Bug in ``Series.replace`` and ``DataFrame.replace`` which failed on empty replacement dicts (:issue:`15289`)
+- Bug in ``Series.replace`` which replaced a numeric by string (:issue:`15743`)
 
 - Bug in ``.asfreq()``, where frequency was not set for empty ``Series`` (:issue:`14320`)
 
@@ -981,7 +987,6 @@ Bug Fixes
 
 - Bug in ``DataFrame.hist`` where ``plt.tight_layout`` caused an ``AttributeError``  (use ``matplotlib >= 2.0.1``) (:issue:`9351`)
 - Bug in ``DataFrame.boxplot`` where ``fontsize`` was not applied to the tick labels on both axes (:issue:`15108`)
-- Bug in ``Series.replace`` and ``DataFrame.replace`` which failed on empty replacement dicts (:issue:`15289`)
 - Bug in ``pd.melt()`` where passing a tuple value for ``value_vars`` caused a ``TypeError`` (:issue:`15348`)
 - Bug in ``.eval()`` which caused multiline evals to fail with local variables not on the first line (:issue:`15342`)
 - Bug in ``pd.read_msgpack`` which did not allow to load dataframe with an index of type ``CategoricalIndex`` (:issue:`15487`)