Merge branch 'master' of github.com:pandas-dev/pandas

Author: dcreekp

.pep8speaks.yml

@@ -13,7 +13,6 @@ pycodestyle:
         - W503,  # line break before binary operator
         - W504,  # line break after binary operator
         - E402,  # module level import not at top of file
-        - E722,  # do not use bare except
         - E731,  # do not assign a lambda expression, use a def
         - C406,  # Unnecessary list literal - rewrite as a dict literal.
         - C408,  # Unnecessary dict call - rewrite as a literal.

Makefile

@@ -13,7 +13,7 @@ build: clean_pyc
 	python setup.py build_ext --inplace
 
 lint-diff:
-	git diff master --name-only -- "*.py" | grep -E "pandas|scripts" | xargs flake8
+	git diff upstream/master --name-only -- "*.py" | xargs flake8
 
 develop: build
 	-python setup.py develop

asv_bench/benchmarks/timeseries.py

@@ -1,5 +1,6 @@
 from datetime import timedelta
 
+import dateutil
 import numpy as np
 from pandas import to_datetime, date_range, Series, DataFrame, period_range
 from pandas.tseries.frequencies import infer_freq
@@ -57,7 +58,10 @@ def time_to_pydatetime(self, index_type):
 
 class TzLocalize(object):
 
-    def setup(self):
+    params = [None, 'US/Eastern', 'UTC', dateutil.tz.tzutc()]
+    param_names = 'tz'
+
+    def setup(self, tz):
         dst_rng = date_range(start='10/29/2000 1:00:00',
                              end='10/29/2000 1:59:59', freq='S')
         self.index = date_range(start='10/29/2000',
@@ -68,8 +72,8 @@ def setup(self):
                                                   end='10/29/2000 3:00:00',
                                                   freq='S'))
 
-    def time_infer_dst(self):
-        self.index.tz_localize('US/Eastern', ambiguous='infer')
+    def time_infer_dst(self, tz):
+        self.index.tz_localize(tz, ambiguous='infer')
 
 
 class ResetIndex(object):
@@ -377,15 +381,35 @@ def time_dup_string_tzoffset_dates(self, cache):
 
 class DatetimeAccessor(object):
 
-    def setup(self):
+    params = [None, 'US/Eastern', 'UTC', dateutil.tz.tzutc()]
+    param_names = 'tz'
+
+    def setup(self, tz):
         N = 100000
-        self.series = Series(date_range(start='1/1/2000', periods=N, freq='T'))
+        self.series = Series(
+            date_range(start='1/1/2000', periods=N, freq='T', tz=tz)
+        )
 
-    def time_dt_accessor(self):
+    def time_dt_accessor(self, tz):
         self.series.dt
 
-    def time_dt_accessor_normalize(self):
+    def time_dt_accessor_normalize(self, tz):
         self.series.dt.normalize()
 
+    def time_dt_accessor_month_name(self, tz):
+        self.series.dt.month_name()
+
+    def time_dt_accessor_day_name(self, tz):
+        self.series.dt.day_name()
+
+    def time_dt_accessor_time(self, tz):
+        self.series.dt.time
+
+    def time_dt_accessor_date(self, tz):
+        self.series.dt.date
+
+    def time_dt_accessor_year(self, tz):
+        self.series.dt.year
+
 
 from .pandas_vb_common import setup  # noqa: F401

asv_bench/benchmarks/timestamp.py

@@ -2,6 +2,7 @@
 
 from pandas import Timestamp
 import pytz
+import dateutil
 
 
 class TimestampConstruction(object):
@@ -29,7 +30,8 @@ def time_fromtimestamp(self):
 
 
 class TimestampProperties(object):
-    _tzs = [None, pytz.timezone('Europe/Amsterdam')]
+    _tzs = [None, pytz.timezone('Europe/Amsterdam'), pytz.UTC,
+            dateutil.tz.tzutc()]
     _freqs = [None, 'B']
     params = [_tzs, _freqs]
     param_names = ['tz', 'freq']
@@ -87,7 +89,8 @@ def time_microsecond(self, tz, freq):
 
 
 class TimestampOps(object):
-    params = [None, 'US/Eastern']
+    params = [None, 'US/Eastern', pytz.UTC,
+              dateutil.tz.tzutc()]
     param_names = ['tz']
 
     def setup(self, tz):
@@ -102,6 +105,17 @@ def time_replace_None(self, tz):
     def time_to_pydatetime(self, tz):
         self.ts.to_pydatetime()
 
+    def time_normalize(self, tz):
+        self.ts.normalize()
+
+    def time_tz_convert(self, tz):
+        if self.ts.tz is not None:
+            self.ts.tz_convert(tz)
+
+    def time_tz_localize(self, tz):
+        if self.ts.tz is None:
+            self.ts.tz_localize(tz)
+
 
 class TimestampAcrossDst(object):
     def setup(self):

ci/deps/azure-27-compat.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytz=2013b
   - scipy=0.18.1
   - sqlalchemy=0.7.8
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-27-locale.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytz=2013b
   - scipy
   - sqlalchemy=0.8.1
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-27.yaml

@@ -35,7 +35,7 @@ dependencies:
   - scipy
   - sqlalchemy=0.9.6
   - xarray=0.9.6
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-36-doc.yaml

@@ -2,7 +2,6 @@ name: pandas
 channels:
   - defaults
   - conda-forge
-  - r
 dependencies:
   - beautifulsoup4
   - bottleneck
@@ -31,14 +30,11 @@ dependencies:
   - python-snappy
   - python=3.6*
   - pytz
-  - r
-  - rpy2
   - scipy
   - seaborn
   - sphinx
   - sqlalchemy
   - statsmodels
-  - tzlocal
   - xarray
   - xlrd
   - xlsxwriter

doc/source/conf.py

@@ -586,7 +586,7 @@ def linkcode_resolve(domain, info):
     for part in fullname.split('.'):
         try:
             obj = getattr(obj, part)
-        except:
+        except AttributeError:
             return None
 
     try:
@@ -595,14 +595,14 @@ def linkcode_resolve(domain, info):
             fn = inspect.getsourcefile(inspect.unwrap(obj))
         else:
             fn = inspect.getsourcefile(obj)
-    except:
+    except TypeError:
         fn = None
     if not fn:
         return None
 
     try:
         source, lineno = inspect.getsourcelines(obj)
-    except:
+    except OSError:
         lineno = None
 
     if lineno:

doc/source/contributing.rst

@@ -575,7 +575,7 @@ the `flake8 <https://pypi.org/project/flake8>`_ tool
 and report any stylistic errors in your code. Therefore, it is helpful before
 submitting code to run the check yourself on the diff::
 
-   git diff master -u -- "*.py" | flake8 --diff
+   git diff upstream/master -u -- "*.py" | flake8 --diff
 
 This command will catch any stylistic errors in your changes specifically, but
 be beware it may not catch all of them. For example, if you delete the only
@@ -584,21 +584,21 @@ unused function. However, style-checking the diff will not catch this because
 the actual import is not part of the diff. Thus, for completeness, you should
 run this command, though it will take longer::
 
-   git diff master --name-only -- "*.py" | grep "pandas/" | xargs -r flake8
+   git diff upstream/master --name-only -- "*.py" | xargs -r flake8
 
 Note that on OSX, the ``-r`` flag is not available, so you have to omit it and
 run this slightly modified command::
 
-   git diff master --name-only -- "*.py" | grep "pandas/" | xargs flake8
+   git diff upstream/master --name-only -- "*.py" | xargs flake8
 
-Windows does not support the ``grep`` and ``xargs`` commands (unless installed
-for example via the `MinGW <http://www.mingw.org/>`__ toolchain), but one can
-imitate the behaviour as follows::
+Windows does not support the ``xargs`` command (unless installed for example
+via the `MinGW <http://www.mingw.org/>`__ toolchain), but one can imitate the
+behaviour as follows::
 
-    for /f %i in ('git diff upstream/master --name-only ^| findstr pandas/') do flake8 %i
+    for /f %i in ('git diff upstream/master --name-only -- "*.py"') do flake8 %i
 
-This will also get all the files being changed by the PR (and within the
-``pandas/`` folder), and run ``flake8`` on them one after the other.
+This will get all the files being changed by the PR (and ending with ``.py``),
+and run ``flake8`` on them, one after the other.
 
 .. _contributing.import-formatting:
 

doc/source/install.rst

@@ -269,7 +269,7 @@ Optional Dependencies
 * `matplotlib <http://matplotlib.org/>`__: for plotting, Version 2.0.0 or higher.
 * For Excel I/O:
 
-    * `xlrd/xlwt <http://www.python-excel.org/>`__: Excel reading (xlrd) and writing (xlwt)
+    * `xlrd/xlwt <http://www.python-excel.org/>`__: Excel reading (xlrd), version 1.0.0 or higher required, and writing (xlwt)
     * `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`__: openpyxl version 2.4.0
       for writing .xlsx files (xlrd >= 0.9.0)
     * `XlsxWriter <https://pypi.org/project/XlsxWriter>`__: Alternative Excel writer

doc/source/r_interface.rst

@@ -33,21 +33,28 @@ See also the documentation of the `rpy2 <http://rpy2.bitbucket.org/>`__ project:
 
 In the remainder of this page, a few examples of explicit conversion is given. The pandas conversion of rpy2 needs first to be activated:
 
-.. ipython:: python
+.. code-block:: python
 
-   from rpy2.robjects import r, pandas2ri
-   pandas2ri.activate()
+    >>> from rpy2.robjects import pandas2ri  # doctest: +SKIP
+    >>> pandas2ri.activate()  # doctest: +SKIP
 
 Transferring R data sets into Python
 ------------------------------------
 
 Once the pandas conversion is activated (``pandas2ri.activate()``), many conversions
 of R to pandas objects will be done automatically. For example, to obtain the 'iris' dataset as a pandas DataFrame:
 
-.. ipython:: python
+.. code-block:: python
 
-    r.data('iris')
-    r['iris'].head()
+    >>> from rpy2.robjects import r  # doctest: +SKIP
+    >>> r.data('iris')  # doctest: +SKIP
+    >>> r['iris'].head()  # doctest: +SKIP
+        Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species
+    0           5.1          3.5           1.4          0.2  setosa
+    1           4.9          3.0           1.4          0.2  setosa
+    2           4.7          3.2           1.3          0.2  setosa
+    3           4.6          3.1           1.5          0.2  setosa
+    4           5.0          3.6           1.4          0.2  setosa
 
 If the pandas conversion was not activated, the above could also be accomplished
 by explicitly converting it with the ``pandas2ri.ri2py`` function
@@ -59,13 +66,19 @@ Converting DataFrames into R objects
 The ``pandas2ri.py2ri`` function support the reverse operation to convert
 DataFrames into the equivalent R object (that is, **data.frame**):
 
-.. ipython:: python
+.. code-block:: python
+
+   >>> df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]},
+   ...                   index=["one", "two", "three"])  # doctest: +SKIP
+   >>> r_dataframe = pandas2ri.py2ri(df)  # doctest: +SKIP
+   >>> print(type(r_dataframe))  # doctest: +SKIP
+   <class 'rpy2.robjects.vectors.DataFrame'>
+   >>> print(r_dataframe)  # doctest: +SKIP
+         A B C
+   one   1 4 7
+   two   2 5 8
+   three 3 6 9
 
-   df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6], 'C':[7,8,9]},
-                     index=["one", "two", "three"])
-   r_dataframe = pandas2ri.py2ri(df)
-   print(type(r_dataframe))
-   print(r_dataframe)
 
 The DataFrame's index is stored as the ``rownames`` attribute of the
 data.frame instance.