Merge remote-tracking branch 'upstream/master' into io_csv_docstring_…

…fixed

* upstream/master: (46 commits)
  DEPS: bump xlrd min version to 1.0.0 (pandas-dev#23774)
  BUG: Don't warn if default conflicts with dialect (pandas-dev#23775)
  BUG: Fixing memory leaks in read_csv (pandas-dev#23072)
  TST: Extend datetime64 arith tests to array classes, fix several broken cases (pandas-dev#23771)
  STYLE: Specify bare exceptions in pandas/tests (pandas-dev#23370)
  ENH: between_time, at_time accept axis parameter (pandas-dev#21799)
  PERF: Use is_utc check to improve performance of dateutil UTC in DatetimeIndex methods (pandas-dev#23772)
  CLN: io/formats/html.py: refactor (pandas-dev#22726)
  API: Make Categorical.searchsorted returns a scalar when supplied a scalar (pandas-dev#23466)
  TST: Add test case for GH14080 for overflow exception (pandas-dev#23762)
  BUG: Don't extract header names if none specified (pandas-dev#23703)
  BUG: Index.str.partition not nan-safe (pandas-dev#23558) (pandas-dev#23618)
  DEPR: tz_convert in the Timestamp constructor (pandas-dev#23621)
  PERF: Datetime/Timestamp.normalize for timezone naive datetimes (pandas-dev#23634)
  TST: Use new arithmetic fixtures, parametrize many more tests (pandas-dev#23757)
  REF/TST: Add more pytest idiom to parsers tests (pandas-dev#23761)
  DOC: Add ignore-deprecate argument to validate_docstrings.py (pandas-dev#23650)
  ENH: update pandas-gbq to 0.8.0, adds credentials arg (pandas-dev#23662)
  DOC: Improve error message to show correct order (pandas-dev#23652)
  ENH: Improve error message for empty object array (pandas-dev#23718)
  ...

.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.

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

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

@@ -591,21 +591,14 @@ run this slightly modified command::
 
    git diff master --name-only -- "*.py" | grep "pandas/" | xargs flake8
 
-Note that on Windows, these commands are unfortunately not possible because
-commands like ``grep`` and ``xargs`` are not available natively. To imitate the
-behavior with the commands above, you should run::
+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::
 
-    git diff master --name-only -- "*.py"
+    for /f %i in ('git diff upstream/master --name-only ^| findstr pandas/') do flake8 %i
 
-This will list all of the Python files that have been modified. The only ones
-that matter during linting are any whose directory filepath begins with "pandas."
-For each filepath, copy and paste it after the ``flake8`` command as shown below:
-
-    flake8 <python-filepath>
-
-Alternatively, you can install the ``grep`` and ``xargs`` commands via the
-`MinGW <http://www.mingw.org/>`__ toolchain, and it will allow you to run the
-commands above.
+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.
 
 .. _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
@@ -286,7 +286,9 @@ Optional Dependencies
   `xsel <http://www.vergenet.net/~conrad/software/xsel/>`__, or
   `xclip <https://github.com/astrand/xclip/>`__: necessary to use
   :func:`~pandas.read_clipboard`. Most package managers on Linux distributions will have ``xclip`` and/or ``xsel`` immediately available for installation.
-* `pandas-gbq <https://pandas-gbq.readthedocs.io/en/latest/install.html#dependencies>`__: for Google BigQuery I/O.
+* `pandas-gbq
+  <https://pandas-gbq.readthedocs.io/en/latest/install.html#dependencies>`__:
+  for Google BigQuery I/O. (pandas-gbq >= 0.8.0)
 
 
 * `Backports.lzma <https://pypi.org/project/backports.lzma/>`__: Only for Python 2, for writing to and/or reading from an xz compressed DataFrame in CSV; Python 3 support is built into the standard library.