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

Author: jbrockmendel

appveyor.yml

@@ -74,12 +74,18 @@ install:
   # create our env
   - cmd: conda create -n pandas python=%PYTHON_VERSION% cython pytest>=3.1.0 pytest-xdist
   - cmd: activate pandas
+  - cmd: pip install moto
   - SET REQ=ci\requirements-%PYTHON_VERSION%_WIN.run
   - cmd: echo "installing requirements from %REQ%"
   - cmd: conda install -n pandas --file=%REQ%
   - cmd: conda list -n pandas
   - cmd: echo "installing requirements from %REQ% - done"
 
+  # add some pip only reqs to the env
+  - SET REQ=ci\requirements-%PYTHON_VERSION%_WIN.pip
+  - cmd: echo "installing requirements from %REQ%"
+  - cmd: pip install -Ur %REQ%
+
   # build em using the local source checkout in the correct windows env
   - cmd: '%CMD_IN_ENV% python setup.py build_ext --inplace'
 

asv_bench/benchmarks/categoricals.py

@@ -67,6 +67,9 @@ def time_value_counts_dropna(self):
     def time_rendering(self):
         str(self.sel)
 
+    def time_set_categories(self):
+        self.ts.cat.set_categories(self.ts.cat.categories[::2])
+
 
 class Categoricals3(object):
     goal_time = 0.2

asv_bench/benchmarks/period.py

@@ -78,6 +78,65 @@ def time_value_counts_pindex(self):
         self.i.value_counts()
 
 
+class Properties(object):
+    def setup(self):
+        self.per = Period('2017-09-06 08:28', freq='min')
+
+    def time_year(self):
+        self.per.year
+
+    def time_month(self):
+        self.per.month
+
+    def time_day(self):
+        self.per.day
+
+    def time_hour(self):
+        self.per.hour
+
+    def time_minute(self):
+        self.per.minute
+
+    def time_second(self):
+        self.per.second
+
+    def time_is_leap_year(self):
+        self.per.is_leap_year
+
+    def time_quarter(self):
+        self.per.quarter
+
+    def time_qyear(self):
+        self.per.qyear
+
+    def time_week(self):
+        self.per.week
+
+    def time_daysinmonth(self):
+        self.per.daysinmonth
+
+    def time_dayofweek(self):
+        self.per.dayofweek
+
+    def time_dayofyear(self):
+        self.per.dayofyear
+
+    def time_start_time(self):
+        self.per.start_time
+
+    def time_end_time(self):
+        self.per.end_time
+
+    def time_to_timestamp():
+        self.per.to_timestamp()
+
+    def time_now():
+        self.per.now()
+
+    def time_asfreq():
+        self.per.asfreq('A')
+
+
 class period_standard_indexing(object):
     goal_time = 0.2
 

ci/install_circle.sh

@@ -67,6 +67,7 @@ time conda create -n pandas -q --file=${REQ_BUILD} || exit 1
 time conda install -n pandas pytest>=3.1.0 || exit 1
 
 source activate pandas
+time pip install moto || exit 1
 
 # build but don't install
 echo "[build em]"

ci/install_travis.sh

@@ -104,7 +104,7 @@ if [ -e ${REQ} ]; then
 fi
 
 time conda install -n pandas pytest>=3.1.0
-time pip install pytest-xdist
+time pip install pytest-xdist moto
 
 if [ "$LINT" ]; then
    conda install flake8

ci/requirements-2.7_WIN.pip

@@ -5,3 +5,4 @@ cython
 pytest>=3.1.0
 pytest-cov
 flake8
+moto

ci/requirements-3.6_NUMPY_DEV.pip

@@ -625,7 +625,7 @@ Index Types
 We have discussed ``MultiIndex`` in the previous sections pretty extensively. ``DatetimeIndex`` and ``PeriodIndex``
 are shown :ref:`here <timeseries.overview>`. ``TimedeltaIndex`` are :ref:`here <timedeltas.timedeltas>`.
 
-In the following sub-sections we will highlite some other index types.
+In the following sub-sections we will highlight some other index types.
 
 .. _indexing.categoricalindex:
 
@@ -645,7 +645,7 @@ and allows efficient indexing and storage of an index with a large number of dup
    df.dtypes
    df.B.cat.categories
 
-Setting the index, will create create a ``CategoricalIndex``
+Setting the index, will create a ``CategoricalIndex``
 
 .. ipython:: python
 
@@ -681,7 +681,7 @@ Groupby operations on the index will preserve the index nature as well
 Reindexing operations, will return a resulting index based on the type of the passed
 indexer, meaning that passing a list will return a plain-old-``Index``; indexing with
 a ``Categorical`` will return a ``CategoricalIndex``, indexed according to the categories
-of the PASSED ``Categorical`` dtype. This allows one to arbitrarly index these even with
+of the PASSED ``Categorical`` dtype. This allows one to arbitrarily index these even with
 values NOT in the categories, similarly to how you can reindex ANY pandas index.
 
 .. ipython :: python
@@ -722,7 +722,7 @@ Int64Index and RangeIndex
 Prior to 0.18.0, the ``Int64Index`` would provide the default index for all ``NDFrame`` objects.
 
 ``RangeIndex`` is a sub-class of ``Int64Index`` added in version 0.18.0, now providing the default index for all ``NDFrame`` objects.
-``RangeIndex`` is an optimized version of ``Int64Index`` that can represent a monotonic ordered set. These are analagous to python `range types <https://docs.python.org/3/library/stdtypes.html#typesseq-range>`__.
+``RangeIndex`` is an optimized version of ``Int64Index`` that can represent a monotonic ordered set. These are analogous to python `range types <https://docs.python.org/3/library/stdtypes.html#typesseq-range>`__.
 
 .. _indexing.float64index:
 
@@ -963,7 +963,7 @@ index can be somewhat complicated. For example, the following does not work:
     s.loc['c':'e'+1]
 
 A very common use case is to limit a time series to start and end at two
-specific dates. To enable this, we made the design design to make label-based
+specific dates. To enable this, we made the design to make label-based
 slicing include both endpoints:
 
 .. ipython:: python

ci/requirements-3.6_WIN.pip

@@ -218,10 +218,19 @@ Top-level dealing with datetimelike
    to_timedelta
    date_range
    bdate_range
+   cdate_range
    period_range
    timedelta_range
    infer_freq
 
+Top-level dealing with intervals
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autosummary::
+   :toctree: generated/
+
+   interval_range
+
 Top-level evaluation
 ~~~~~~~~~~~~~~~~~~~~
 
@@ -1282,7 +1291,7 @@ Index
 -----
 
 **Many of these methods or variants thereof are available on the objects
-that contain an index (Series/Dataframe) and those should most likely be
+that contain an index (Series/DataFrame) and those should most likely be
 used before calling these methods directly.**
 
 .. autosummary::
@@ -2062,6 +2071,7 @@ Style Application
 
    Styler.apply
    Styler.applymap
+   Styler.where
    Styler.format
    Styler.set_precision
    Styler.set_table_styles

ci/requirements_dev.txt

@@ -923,7 +923,7 @@ Passing a named function will yield that name for the row:
 Aggregating with a dict
 +++++++++++++++++++++++
 
-Passing a dictionary of column names to a scalar or a list of scalars, to ``DataFame.agg``
+Passing a dictionary of column names to a scalar or a list of scalars, to ``DataFrame.agg``
 allows you to customize which functions are applied to which columns. Note that the results
 are not in any particular order, you can use an ``OrderedDict`` instead to guarantee ordering.
 

doc/source/advanced.rst

@@ -654,7 +654,7 @@ aggregation with, outputting a DataFrame:
 
    r['A'].agg([np.sum, np.mean, np.std])
 
-On a widowed DataFrame, you can pass a list of functions to apply to each
+On a windowed DataFrame, you can pass a list of functions to apply to each
 column, which produces an aggregated result with a hierarchical index:
 
 .. ipython:: python

doc/source/api.rst

@@ -561,7 +561,7 @@ must be either implemented on GroupBy or available via :ref:`dispatching
 
 .. note::
 
-    If you pass a dict to ``aggregate``, the ordering of the output colums is
+    If you pass a dict to ``aggregate``, the ordering of the output columns is
     non-deterministic. If you want to be sure the output columns will be in a specific
     order, you can use an ``OrderedDict``.  Compare the output of the following two commands:
 
@@ -1211,7 +1211,7 @@ 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 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 gets selected for the groupby operation.
 

doc/source/basics.rst

@@ -714,7 +714,7 @@ Finally, one can also set a seed for ``sample``'s random number generator using
 Setting With Enlargement
 ------------------------
 
-The ``.loc/[]`` operations can perform enlargement when setting a non-existant key for that axis.
+The ``.loc/[]`` operations can perform enlargement when setting a non-existent key for that axis.
 
 In the ``Series`` case this is effectively an appending operation
 

doc/source/computation.rst

@@ -3077,7 +3077,7 @@ Compressed pickle files
 
 .. versionadded:: 0.20.0
 
-:func:`read_pickle`, :meth:`DataFame.to_pickle` and :meth:`Series.to_pickle` can read
+:func:`read_pickle`, :meth:`DataFrame.to_pickle` and :meth:`Series.to_pickle` can read
 and write compressed pickle files. The compression types of ``gzip``, ``bz2``, ``xz`` are supported for reading and writing.
 `zip`` file supports read only and must contain only one data file
 to be read in.
@@ -4515,8 +4515,7 @@ See the documentation for `pyarrow <http://arrow.apache.org/docs/python/>`__ and
                       'd': np.arange(4.0, 7.0, dtype='float64'),
                       'e': [True, False, True],
                       'f': pd.date_range('20130101', periods=3),
-                      'g': pd.date_range('20130101', periods=3, tz='US/Eastern'),
-                      'h': pd.date_range('20130101', periods=3, freq='ns')})
+                      'g': pd.date_range('20130101', periods=3, tz='US/Eastern')})
 
    df
    df.dtypes

doc/source/groupby.rst

@@ -1329,7 +1329,7 @@ By default we are taking the asof of the quotes.
                  on='time',
                  by='ticker')
 
-We only asof within ``2ms`` betwen the quote time and the trade time.
+We only asof within ``2ms`` between the quote time and the trade time.
 
 .. ipython:: python
 
@@ -1338,8 +1338,8 @@ We only asof within ``2ms`` betwen the quote time and the trade time.
                  by='ticker',
                  tolerance=pd.Timedelta('2ms'))
 
-We only asof within ``10ms`` betwen the quote time and the trade time and we exclude exact matches on time.
-Note that though we exclude the exact matches (of the quotes), prior quotes DO propogate to that point
+We only asof within ``10ms`` between the quote time and the trade time and we exclude exact matches on time.
+Note that though we exclude the exact matches (of the quotes), prior quotes DO propagate to that point
 in time.
 
 .. ipython:: python

doc/source/indexing.rst

@@ -320,7 +320,7 @@ Interpolation
 
   The ``limit_direction`` keyword argument was added.
 
-Both Series and Dataframe objects have an ``interpolate`` method that, by default,
+Both Series and DataFrame objects have an ``interpolate`` method that, by default,
 performs linear interpolation at missing datapoints.
 
 .. ipython:: python

doc/source/io.rst

@@ -313,9 +313,9 @@ display.large_repr                  truncate     For DataFrames exceeding max_ro
 display.latex.repr                  False        Whether to produce a latex DataFrame
                                                  representation for jupyter frontends
                                                  that support it.
-display.latex.escape                True         Escapes special caracters in Dataframes, when
+display.latex.escape                True         Escapes special characters in DataFrames, when
                                                  using the to_latex method.
-display.latex.longtable             False        Specifies if the to_latex method of a Dataframe
+display.latex.longtable             False        Specifies if the to_latex method of a DataFrame
                                                  uses the longtable format.
 display.latex.multicolumn           True         Combines columns when using a MultiIndex
 display.latex.multicolumn_format    'l'          Alignment of multicolumn labels

doc/source/merging.rst

@@ -156,7 +156,7 @@ the level numbers:
    stacked.unstack('second')
 
 Notice that the ``stack`` and ``unstack`` methods implicitly sort the index
-levels involved. Hence a call to ``stack`` and then ``unstack``, or viceversa,
+levels involved. Hence a call to ``stack`` and then ``unstack``, or vice versa,
 will result in a **sorted** copy of the original DataFrame or Series:
 
 .. ipython:: python

doc/source/missing_data.rst

@@ -132,7 +132,7 @@ dtype, ``fill_value`` default changes:
    s.to_sparse()
 
 You can change the dtype using ``.astype()``, the result is also sparse. Note that
-``.astype()`` also affects to the ``fill_value`` to keep its dense represantation.
+``.astype()`` also affects to the ``fill_value`` to keep its dense representation.
 
 
 .. ipython:: python

doc/source/options.rst

@@ -169,7 +169,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Notice the similarity with the standard `df.applymap`, which operates on DataFrames elementwise. We want you to be able to resuse your existing knowledge of how to interact with DataFrames.\n",
+    "Notice the similarity with the standard `df.applymap`, which operates on DataFrames elementwise. We want you to be able to reuse your existing knowledge of how to interact with DataFrames.\n",
     "\n",
     "Notice also that our function returned a string containing the CSS attribute and value, separated by a colon just like in a `<style>` tag. This will be a common theme.\n",
     "\n",

doc/source/reshaping.rst

@@ -1054,7 +1054,7 @@ as ``BusinessHour`` except that it skips specified custom holidays.
     # Tuesday after MLK Day (Monday is skipped because it's a holiday)
     dt + bhour_us * 2
 
-You can use keyword arguments suported by either ``BusinessHour`` and ``CustomBusinessDay``.
+You can use keyword arguments supported by either ``BusinessHour`` and ``CustomBusinessDay``.
 
 .. ipython:: python
 
@@ -1088,7 +1088,7 @@ frequencies. We will refer to these aliases as *offset aliases*.
     "BMS", "business month start frequency"
     "CBMS", "custom business month start frequency"
     "Q", "quarter end frequency"
-    "BQ", "business quarter endfrequency"
+    "BQ", "business quarter end frequency"
     "QS", "quarter start frequency"
     "BQS", "business quarter start frequency"
     "A, Y", "year end frequency"
@@ -1132,13 +1132,13 @@ For some frequencies you can specify an anchoring suffix:
     :header: "Alias", "Description"
     :widths: 15, 100
 
-    "W\-SUN", "weekly frequency (sundays). Same as 'W'"
-    "W\-MON", "weekly frequency (mondays)"
-    "W\-TUE", "weekly frequency (tuesdays)"
-    "W\-WED", "weekly frequency (wednesdays)"
-    "W\-THU", "weekly frequency (thursdays)"
-    "W\-FRI", "weekly frequency (fridays)"
-    "W\-SAT", "weekly frequency (saturdays)"
+    "W\-SUN", "weekly frequency (Sundays). Same as 'W'"
+    "W\-MON", "weekly frequency (Mondays)"
+    "W\-TUE", "weekly frequency (Tuesdays)"
+    "W\-WED", "weekly frequency (Wednesdays)"
+    "W\-THU", "weekly frequency (Thursdays)"
+    "W\-FRI", "weekly frequency (Fridays)"
+    "W\-SAT", "weekly frequency (Saturdays)"
     "(B)Q(S)\-DEC", "quarterly frequency, year ends in December. Same as 'Q'"
     "(B)Q(S)\-JAN", "quarterly frequency, year ends in January"
     "(B)Q(S)\-FEB", "quarterly frequency, year ends in February"
@@ -1705,6 +1705,15 @@ has multiplied span.
 
    pd.PeriodIndex(start='2014-01', freq='3M', periods=4)
 
+If ``start`` or ``end`` are ``Period`` objects, they will be used as anchor
+endpoints for a ``PeriodIndex`` with frequency matching that of the
+``PeriodIndex`` constructor.
+
+.. ipython:: python
+
+   pd.PeriodIndex(start=pd.Period('2017Q1', freq='Q'),
+                  end=pd.Period('2017Q2', freq='Q'), freq='M')
+
 Just like ``DatetimeIndex``, a ``PeriodIndex`` can also be used to index pandas
 objects:
 

doc/source/sparse.rst

@@ -261,7 +261,7 @@ Histogram can be stacked by ``stacked=True``. Bin size can be changed by ``bins`
 
    plt.close('all')
 
-You can pass other keywords supported by matplotlib ``hist``. For example, horizontal and cumulative histgram can be drawn by ``orientation='horizontal'`` and ``cumulative='True'``.
+You can pass other keywords supported by matplotlib ``hist``. For example, horizontal and cumulative histogram can be drawn by ``orientation='horizontal'`` and ``cumulative=True``.
 
 .. ipython:: python