solve merge conflict

Author: tp

.gitignore

@@ -106,3 +106,4 @@ doc/build/html/index.html
 doc/tmp.sv
 doc/source/styled.xlsx
 doc/source/templates/
+env/

asv_bench/benchmarks/frame_ctor.py

@@ -2,8 +2,9 @@
 import pandas.util.testing as tm
 from pandas import DataFrame, Series, MultiIndex, Timestamp, date_range
 try:
-    from pandas.tseries import offsets
-except:
+    from pandas.tseries.offsets import Nano, Hour
+except ImportError:
+    # For compatability with older versions
     from pandas.core.datetools import * # noqa
 
 from .pandas_vb_common import setup # noqa
@@ -24,16 +25,16 @@ def setup(self):
         self.data2 = {i: {j: float(j) for j in range(100)}
                       for i in range(2000)}
 
-    def time_frame_ctor_list_of_dict(self):
+    def time_list_of_dict(self):
         DataFrame(self.dict_list)
 
-    def time_frame_ctor_nested_dict(self):
+    def time_nested_dict(self):
         DataFrame(self.data)
 
-    def time_series_ctor_from_dict(self):
+    def time_dict(self):
         Series(self.some_dict)
 
-    def time_frame_ctor_nested_dict_int64(self):
+    def time_nested_dict_int64(self):
         # nested dict, integer indexes, regression described in #621
         DataFrame(self.data2)
 
@@ -46,78 +47,24 @@ def setup(self):
         mi = MultiIndex.from_product([range(100), range(100)])
         self.s = Series(np.random.randn(10000), index=mi)
 
-    def time_frame_from_mi_series(self):
+    def time_mi_series(self):
         DataFrame(self.s)
 
-# ----------------------------------------------------------------------
-# From dict with DatetimeIndex with all offsets
 
-# dynamically generate benchmarks for every offset
-#
-# get_period_count & get_index_for_offset are there because blindly taking each
-# offset times 1000 can easily go out of Timestamp bounds and raise errors.
+class FromDictwithTimestamp(object):
 
+    goal_time = 0.2
+    params = [Nano(1), Hour(1)]
+    param_names = ['offset']
 
-def get_period_count(start_date, off):
-    ten_offsets_in_days = ((start_date + (off * 10)) - start_date).days
-    if (ten_offsets_in_days == 0):
-        return 1000
-    else:
-        periods = 9 * (Timestamp.max - start_date).days // ten_offsets_in_days
-        return min(periods, 1000)
-
-
-def get_index_for_offset(off):
-    start_date = Timestamp('1/1/1900')
-    return date_range(start_date,
-                      periods=get_period_count(start_date, off),
-                      freq=off)
-
-
-all_offsets = offsets.__all__
-# extra cases
-for off in ['FY5253', 'FY5253Quarter']:
-    all_offsets.pop(all_offsets.index(off))
-    all_offsets.extend([off + '_1', off + '_2'])
-
-
-class FromDictwithTimestampOffsets(object):
-
-    params = [all_offsets, [1, 2]]
-    param_names = ['offset', 'n_steps']
-
-    offset_kwargs = {'WeekOfMonth': {'weekday': 1, 'week': 1},
-                     'LastWeekOfMonth': {'weekday': 1, 'week': 1},
-                     'FY5253': {'startingMonth': 1, 'weekday': 1},
-                     'FY5253Quarter': {'qtr_with_extra_week': 1,
-                                       'startingMonth': 1,
-                                       'weekday': 1}}
-
-    offset_extra_cases = {'FY5253': {'variation': ['nearest', 'last']},
-                          'FY5253Quarter': {'variation': ['nearest', 'last']}}
-
-    def setup(self, offset, n_steps):
+    def setup(self, offset):
+        N = 10**3
         np.random.seed(1234)
-        extra = False
-        if offset.endswith("_", None, -1):
-            extra = int(offset[-1])
-            offset = offset[:-2]
-
-        kwargs = {}
-        if offset in self.offset_kwargs:
-            kwargs = self.offset_kwargs[offset]
-
-        if extra:
-            extras = self.offset_extra_cases[offset]
-            for extra_arg in extras:
-                kwargs[extra_arg] = extras[extra_arg][extra - 1]
-
-        offset = getattr(offsets, offset)
-        self.idx = get_index_for_offset(offset(n_steps, **kwargs))
-        self.df = DataFrame(np.random.randn(len(self.idx), 10), index=self.idx)
-        self.d = self.df.to_dict()
-
-    def time_frame_ctor(self, offset, n_steps):
+        idx = date_range(Timestamp('1/1/1900'), freq=offset, periods=N)
+        df = DataFrame(np.random.randn(N, 10), index=idx)
+        self.d = df.to_dict()
+
+    def time_dict_with_timestamp_offsets(self, offset):
         DataFrame(self.d)
 
 

asv_bench/benchmarks/timedelta.py

@@ -1,5 +1,7 @@
-from .pandas_vb_common import *
-from pandas import to_timedelta, Timestamp
+import numpy as np
+import pandas as pd
+
+from pandas import to_timedelta, Timestamp, Timedelta
 
 
 class ToTimedelta(object):
@@ -67,8 +69,8 @@ class DatetimeAccessor(object):
     def setup(self):
         self.N = 100000
         self.series = pd.Series(
-            pd.timedelta_range('1 days', periods=self.N, freq='h')
-        )
+            pd.timedelta_range('1 days', periods=self.N, freq='h'))
+
     def time_dt_accessor(self):
         self.series.dt
 

asv_bench/benchmarks/timeseries.py

@@ -85,7 +85,7 @@ def time_dti_tz_factorize(self):
         self.dti_tz.factorize()
 
     def time_dti_time(self):
-        self.rng.time
+        self.dst_rng.time
 
     def time_timestamp_tzinfo_cons(self):
         self.rng5[0]

asv_bench/benchmarks/timestamp.py

@@ -1,15 +1,33 @@
-from pandas import to_timedelta, Timestamp
+from pandas import Timestamp
 import pytz
 import datetime
 
 
+class TimestampConstruction(object):
+    # TODO: classmethod constructors: fromordinal, fromtimestamp...
+
+    def time_parse_iso8601_no_tz(self):
+        Timestamp('2017-08-25 08:16:14')
+
+    def time_parse_iso8601_tz(self):
+        Timestamp('2017-08-25 08:16:14-0500')
+
+    def time_parse_dateutil(self):
+        Timestamp('2017/08/25 08:16:14 AM')
+
+    def time_parse_today(self):
+        Timestamp('today')
+
+    def time_parse_now(self):
+        Timestamp('now')
+
+
 class TimestampProperties(object):
     goal_time = 0.2
 
-    params = [(None, None),
-              (pytz.timezone('Europe/Amsterdam'), None),
-              (None, 'B'),
-              (pytz.timezone('Europe/Amsterdam'), 'B')]
+    _tzs = [None, pytz.timezone('Europe/Amsterdam')]
+    _freqs = [None, 'B']
+    params = [_tzs, _freqs]
     param_names = ['tz', 'freq']
 
     def setup(self, tz, freq):

ci/check_imports.py

@@ -9,7 +9,6 @@
     'ipython',
     'jinja2'
     'lxml',
-    'matplotlib',
     'numexpr',
     'openpyxl',
     'py',

ci/environment-dev.yaml

@@ -10,5 +10,5 @@ dependencies:
   - python-dateutil>=2.5.0
   - python=3
   - pytz
-  - setuptools
+  - setuptools>=3.3
   - sphinx

ci/lint.sh

@@ -23,6 +23,13 @@ if [ "$LINT" ]; then
     fi
     echo "Linting setup.py DONE"
 
+    echo "Linting asv_bench/benchmarks/"
+    flake8 asv_bench/benchmarks/  --exclude=asv_bench/benchmarks/[ghijoprs]*.py --ignore=F811
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
+    echo "Linting asv_bench/benchmarks/*.py DONE"
+
     echo "Linting *.pyx"
     flake8 pandas --filename=*.pyx --select=E501,E302,E203,E111,E114,E221,E303,E128,E231,E126,E265,E305,E301,E127,E261,E271,E129,W291,E222,E241,E123,F403
     if [ $? -ne "0" ]; then

ci/requirements_dev.txt

@@ -6,5 +6,5 @@ moto
 pytest>=3.1
 python-dateutil>=2.5.0
 pytz
-setuptools
-sphinx
+setuptools>=3.3
+sphinx

conda.recipe/meta.yaml

@@ -15,7 +15,7 @@ requirements:
     - python
     - cython
     - numpy x.x
-    - setuptools
+    - setuptools >=3.3
 
   run:
     - python

doc/source/api.rst

@@ -2373,6 +2373,17 @@ Style Export and Import
    Styler.use
    Styler.to_excel
 
+Plotting
+~~~~~~~~
+
+.. currentmodule:: pandas
+
+.. autosummary::
+   :toctree: generated/
+
+   plotting.register_matplotlib_converters
+   plotting.deregister_matplotlib_converters
+
 .. currentmodule:: pandas
 
 General utility functions

doc/source/computation.rst

@@ -253,12 +253,6 @@ accept the following arguments:
   result is NA)
 - ``center``: boolean, whether to set the labels at the center (default is False)
 
-.. warning::
-
-   The ``freq`` and ``how`` arguments were in the API prior to 0.18.0 changes. These are deprecated in the new API. You can simply resample the input prior to creating a window function.
-
-   For example, instead of ``s.rolling(window=5,freq='D').max()`` to get the max value on a rolling 5 Day window, one could use ``s.resample('D').max().rolling(window=5).max()``, which first resamples the data to daily data, then provides a rolling 5 day window.
-
 We can then call methods on these ``rolling`` objects. These return like-indexed objects:
 
 .. ipython:: python

doc/source/indexing.rst

@@ -1833,15 +1833,27 @@ that you've done this:
 
 Yikes!
 
+.. _indexing.evaluation_order:
+
 Evaluation order matters
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-Furthermore, in chained expressions, the order may determine whether a copy is returned or not.
-If an expression will set values on a copy of a slice, then a ``SettingWithCopy``
-warning will be issued.
+When you use chained indexing, the order and type of the indexing operation
+partially determine whether the result is a slice into the original object, or
+a copy of the slice.
+
+Pandas has the ``SettingWithCopyWarning`` because assigning to a copy of a
+slice is frequently not intentional, but a mistake caused by chained indexing
+returning a copy where a slice was expected.
+
+If you would like pandas to be more or less trusting about assignment to a
+chained indexing expression, you can set the :ref:`option <options>`
+``mode.chained_assignment`` to one of these values:
 
-You can control the action of a chained assignment via the option ``mode.chained_assignment``,
-which can take the values ``['raise','warn',None]``, where showing a warning is the default.
+* ``'warn'``, the default, means a ``SettingWithCopyWarning`` is printed.
+* ``'raise'`` means pandas will raise a ``SettingWithCopyException``
+  you have to deal with.
+* ``None`` will suppress the warnings entirely.
 
 .. ipython:: python
    :okwarning:

doc/source/install.rst

@@ -141,28 +141,24 @@ and can take a few minutes to complete.
 Installing using your Linux distribution's package manager.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-The commands in this table will install pandas for Python 2 from your distribution.
-To install pandas for Python 3 you may need to use the package ``python3-pandas``.
+The commands in this table will install pandas for Python 3 from your distribution.
+To install pandas for Python 2 you may need to use the package ``python-pandas``.
 
 .. csv-table::
     :header: "Distribution", "Status", "Download / Repository Link", "Install method"
     :widths: 10, 10, 20, 50
 
 
-    Debian, stable, `official Debian repository <http://packages.debian.org/search?keywords=pandas&searchon=names&suite=all&section=all>`__ , ``sudo apt-get install python-pandas``
-    Debian & Ubuntu, unstable (latest packages), `NeuroDebian <http://neuro.debian.net/index.html#how-to-use-this-repository>`__ , ``sudo apt-get install python-pandas``
-    Ubuntu, stable, `official Ubuntu repository <http://packages.ubuntu.com/search?keywords=pandas&searchon=names&suite=all&section=all>`__ , ``sudo apt-get install python-pandas``
-    Ubuntu, unstable (daily builds), `PythonXY PPA  <https://code.launchpad.net/~pythonxy/+archive/pythonxy-devel>`__; activate by: ``sudo add-apt-repository ppa:pythonxy/pythonxy-devel && sudo apt-get update``, ``sudo apt-get install python-pandas``
-    OpenSuse, stable, `OpenSuse Repository  <http://software.opensuse.org/package/python-pandas?search_term=pandas>`__ , ``zypper in  python-pandas``
-    Fedora, stable, `official Fedora repository  <https://admin.fedoraproject.org/pkgdb/package/rpms/python-pandas/>`__ , ``dnf install python-pandas``
-    Centos/RHEL, stable, `EPEL repository <https://admin.fedoraproject.org/pkgdb/package/rpms/python-pandas/>`__ , ``yum install python-pandas``
-
-
-
-
-
-
+    Debian, stable, `official Debian repository <http://packages.debian.org/search?keywords=pandas&searchon=names&suite=all&section=all>`__ , ``sudo apt-get install python3-pandas``
+    Debian & Ubuntu, unstable (latest packages), `NeuroDebian <http://neuro.debian.net/index.html#how-to-use-this-repository>`__ , ``sudo apt-get install python3-pandas``
+    Ubuntu, stable, `official Ubuntu repository <http://packages.ubuntu.com/search?keywords=pandas&searchon=names&suite=all&section=all>`__ , ``sudo apt-get install python3-pandas``
+    OpenSuse, stable, `OpenSuse Repository  <http://software.opensuse.org/package/python-pandas?search_term=pandas>`__ , ``zypper in  python3-pandas``
+    Fedora, stable, `official Fedora repository  <https://admin.fedoraproject.org/pkgdb/package/rpms/python-pandas/>`__ , ``dnf install python3-pandas``
+    Centos/RHEL, stable, `EPEL repository <https://admin.fedoraproject.org/pkgdb/package/rpms/python-pandas/>`__ , ``yum install python3-pandas``
 
+**However**, the packages in the linux package managers are often a few versions behind, so
+to get the newest version of pandas, it's recommended to install using the ``pip`` or ``conda``
+methods described above.
 
 
 Installing from source
@@ -198,7 +194,7 @@ installed), make sure you have `pytest
 Dependencies
 ------------
 
-* `setuptools <https://setuptools.readthedocs.io/en/latest/>`__
+* `setuptools <https://setuptools.readthedocs.io/en/latest/>`__: 3.3.0 or higher
 * `NumPy <http://www.numpy.org>`__: 1.9.0 or higher
 * `python-dateutil <//https://dateutil.readthedocs.io/en/stable/>`__: 2.5.0 or higher
 * `pytz <http://pytz.sourceforge.net/>`__

doc/source/io.rst

@@ -4522,6 +4522,7 @@ See the documentation for `pyarrow <http://arrow.apache.org/docs/python/>`__ and
 .. note::
 
    These engines are very similar and should read/write nearly identical parquet format files.
+   Currently ``pyarrow`` does not support timedelta data, and ``fastparquet`` does not support timezone aware datetimes (they are coerced to UTC).
    These libraries differ by having different underlying dependencies (``fastparquet`` by using ``numba``, while ``pyarrow`` uses a c-library).
 
 .. ipython:: python
@@ -4548,16 +4549,15 @@ Read from a parquet file.
 
 .. ipython:: python
 
-   result = pd.read_parquet('example_pa.parquet', engine='pyarrow')
    result = pd.read_parquet('example_fp.parquet', engine='fastparquet')
+   result = pd.read_parquet('example_pa.parquet', engine='pyarrow')
 
    result.dtypes
 
 Read only certain columns of a parquet file.
 
 .. ipython:: python
 
-   result = pd.read_parquet('example_pa.parquet', engine='pyarrow', columns=['a', 'b'])
    result = pd.read_parquet('example_fp.parquet', engine='fastparquet', columns=['a', 'b'])
 
    result.dtypes