Merge remote-tracking branch 'upstream/master' into numpy-ea

Author: TomAugspurger

asv_bench/benchmarks/frame_methods.py

@@ -103,6 +103,7 @@ def setup(self):
         self.df2 = DataFrame(np.random.randn(N * 50, 10))
         self.df3 = DataFrame(np.random.randn(N, 5 * N),
                              columns=['C' + str(c) for c in range(N * 5)])
+        self.df4 = DataFrame(np.random.randn(N * 1000, 10))
 
     def time_iteritems(self):
         # (monitor no-copying behaviour)
@@ -119,10 +120,70 @@ def time_iteritems_indexing(self):
         for col in self.df3:
             self.df3[col]
 
+    def time_itertuples_start(self):
+        self.df4.itertuples()
+
+    def time_itertuples_read_first(self):
+        next(self.df4.itertuples())
+
     def time_itertuples(self):
-        for row in self.df2.itertuples():
+        for row in self.df4.itertuples():
+            pass
+
+    def time_itertuples_to_list(self):
+        list(self.df4.itertuples())
+
+    def mem_itertuples_start(self):
+        return self.df4.itertuples()
+
+    def peakmem_itertuples_start(self):
+        self.df4.itertuples()
+
+    def mem_itertuples_read_first(self):
+        return next(self.df4.itertuples())
+
+    def peakmem_itertuples(self):
+        for row in self.df4.itertuples():
+            pass
+
+    def mem_itertuples_to_list(self):
+        return list(self.df4.itertuples())
+
+    def peakmem_itertuples_to_list(self):
+        list(self.df4.itertuples())
+
+    def time_itertuples_raw_start(self):
+        self.df4.itertuples(index=False, name=None)
+
+    def time_itertuples_raw_read_first(self):
+        next(self.df4.itertuples(index=False, name=None))
+
+    def time_itertuples_raw_tuples(self):
+        for row in self.df4.itertuples(index=False, name=None):
             pass
 
+    def time_itertuples_raw_tuples_to_list(self):
+        list(self.df4.itertuples(index=False, name=None))
+
+    def mem_itertuples_raw_start(self):
+        return self.df4.itertuples(index=False, name=None)
+
+    def peakmem_itertuples_raw_start(self):
+        self.df4.itertuples(index=False, name=None)
+
+    def peakmem_itertuples_raw_read_first(self):
+        next(self.df4.itertuples(index=False, name=None))
+
+    def peakmem_itertuples_raw(self):
+        for row in self.df4.itertuples(index=False, name=None):
+            pass
+
+    def mem_itertuples_raw_to_list(self):
+        return list(self.df4.itertuples(index=False, name=None))
+
+    def peakmem_itertuples_raw_to_list(self):
+        list(self.df4.itertuples(index=False, name=None))
+
     def time_iterrows(self):
         for row in self.df.iterrows():
             pass

asv_bench/benchmarks/join_merge.py

@@ -50,7 +50,7 @@ def setup(self, axis):
         self.empty_right = [df, DataFrame()]
 
     def time_concat_series(self, axis):
-        concat(self.series, axis=axis)
+        concat(self.series, axis=axis, sort=False)
 
     def time_concat_small_frames(self, axis):
         concat(self.small_frames, axis=axis)

asv_bench/benchmarks/panel_ctor.py

@@ -1,7 +1,7 @@
 import warnings
 from datetime import datetime, timedelta
 
-from pandas import DataFrame, Panel, DatetimeIndex, date_range
+from pandas import DataFrame, Panel, date_range
 
 
 class DifferentIndexes(object):
@@ -23,9 +23,9 @@ def time_from_dict(self):
 class SameIndexes(object):
 
     def setup(self):
-        idx = DatetimeIndex(start=datetime(1990, 1, 1),
-                            end=datetime(2012, 1, 1),
-                            freq='D')
+        idx = date_range(start=datetime(1990, 1, 1),
+                         end=datetime(2012, 1, 1),
+                         freq='D')
         df = DataFrame({'a': 0, 'b': 1, 'c': 2}, index=idx)
         self.data_frames = dict(enumerate([df] * 100))
 
@@ -40,10 +40,10 @@ def setup(self):
         start = datetime(1990, 1, 1)
         end = datetime(2012, 1, 1)
         df1 = DataFrame({'a': 0, 'b': 1, 'c': 2},
-                        index=DatetimeIndex(start=start, end=end, freq='D'))
+                        index=date_range(start=start, end=end, freq='D'))
         end += timedelta(days=1)
         df2 = DataFrame({'a': 0, 'b': 1, 'c': 2},
-                        index=DatetimeIndex(start=start, end=end, freq='D'))
+                        index=date_range(start=start, end=end, freq='D'))
         dfs = [df1] * 50 + [df2] * 50
         self.data_frames = dict(enumerate(dfs))
 

asv_bench/benchmarks/reindex.py

@@ -1,14 +1,14 @@
 import numpy as np
 import pandas.util.testing as tm
-from pandas import (DataFrame, Series, DatetimeIndex, MultiIndex, Index,
+from pandas import (DataFrame, Series, MultiIndex, Index,
                     date_range)
 from .pandas_vb_common import lib
 
 
 class Reindex(object):
 
     def setup(self):
-        rng = DatetimeIndex(start='1/1/1970', periods=10000, freq='1min')
+        rng = date_range(start='1/1/1970', periods=10000, freq='1min')
         self.df = DataFrame(np.random.rand(10000, 10), index=rng,
                             columns=range(10))
         self.df['foo'] = 'bar'

asv_bench/benchmarks/timedelta.py

@@ -1,8 +1,9 @@
 import datetime
 
 import numpy as np
-from pandas import Series, timedelta_range, to_timedelta, Timestamp, \
-    Timedelta, TimedeltaIndex, DataFrame
+
+from pandas import (
+    DataFrame, Series, Timedelta, Timestamp, timedelta_range, to_timedelta)
 
 
 class TimedeltaConstructor(object):
@@ -122,8 +123,8 @@ def time_timedelta_nanoseconds(self, series):
 class TimedeltaIndexing(object):
 
     def setup(self):
-        self.index = TimedeltaIndex(start='1985', periods=1000, freq='D')
-        self.index2 = TimedeltaIndex(start='1986', periods=1000, freq='D')
+        self.index = timedelta_range(start='1985', periods=1000, freq='D')
+        self.index2 = timedelta_range(start='1986', periods=1000, freq='D')
         self.series = Series(range(1000), index=self.index)
         self.timedelta = self.index[500]
 

asv_bench/benchmarks/timestamp.py

@@ -1,8 +1,9 @@
 import datetime
 
-from pandas import Timestamp
-import pytz
 import dateutil
+import pytz
+
+from pandas import Timestamp
 
 
 class TimestampConstruction(object):
@@ -46,7 +47,7 @@ def time_dayofweek(self, tz, freq):
         self.ts.dayofweek
 
     def time_weekday_name(self, tz, freq):
-        self.ts.weekday_name
+        self.ts.day_name
 
     def time_dayofyear(self, tz, freq):
         self.ts.dayofyear

azure-pipelines.yml

@@ -43,6 +43,7 @@ jobs:
       ci/incremental/install_miniconda.sh
       ci/incremental/setup_conda_environment.sh
     displayName: 'Set up environment'
+    condition: true
 
   # Do not require pandas
   - script: |

ci/code_checks.sh

@@ -145,7 +145,7 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check that the deprecated `assert_raises_regex` is not used (`pytest.raises(match=pattern)` should be used instead)' ; echo $MSG
-    invgrep -R --exclude=*.pyc --exclude=testing.py --exclude=test_testing.py assert_raises_regex pandas
+    invgrep -R --exclude=*.pyc --exclude=testing.py --exclude=test_util.py assert_raises_regex pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     # Check that we use pytest.raises only as a context manager
@@ -158,7 +158,12 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     # RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check that no file in the repo contains tailing whitespaces' ; echo $MSG
-    invgrep --exclude="*.svg" -RI "\s$" *
+    set -o pipefail
+    if [[ "$AZURE" == "true" ]]; then
+        ! grep -n --exclude="*.svg" -RI "\s$" * | awk -F ":" '{print "##vso[task.logissue type=error;sourcepath=" $1 ";linenumber=" $2 ";] Tailing whitespaces found: " $3}'
+    else
+        ! grep -n --exclude="*.svg" -RI "\s$" * | awk -F ":" '{print $1 ":" $2 ":Tailing whitespaces found: " $3}'
+    fi
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 fi
 

doc/source/basics.rst

@@ -397,9 +397,7 @@ To evaluate single-element pandas objects in a boolean context, use the method
 
       >>> df and df2
 
-   These will both raise errors, as you are trying to compare multiple values.
-
-   .. code-block:: python-traceback
+   These will both raise errors, as you are trying to compare multiple values.::
 
        ValueError: The truth value of an array is ambiguous. Use a.empty, a.any() or a.all().
 

doc/source/io.rst

@@ -1,5 +1,8 @@
 .. _io:
 
+.. currentmodule:: pandas
+
+
 {{ header }}
 
 .. ipython:: python

doc/source/tutorials.rst

@@ -88,12 +88,12 @@ Video Tutorials
   `GitHub repo <https://github.com/TomAugspurger/pydata-chi-h2t>`__
 * `Data analysis in Python with pandas <https://www.youtube.com/playlist?list=PL5-da3qGB5ICCsgW1MxlZ0Hq8LL5U3u9y>`_
   (2016-2018)
-  `GitHub repo <https://github.com/justmarkham/pandas-videos>`_ and
-  `Jupyter Notebook <http://nbviewer.jupyter.org/github/justmarkham/pandas-videos/blob/master/pandas.ipynb>`_
+  `GitHub repo <https://github.com/justmarkham/pandas-videos>`__ and
+  `Jupyter Notebook <http://nbviewer.jupyter.org/github/justmarkham/pandas-videos/blob/master/pandas.ipynb>`__
 * `Best practices with pandas <https://www.youtube.com/playlist?list=PL5-da3qGB5IBITZj_dYSFqnd_15JgqwA6>`_
   (2018)
-  `GitHub repo <https://github.com/justmarkham/pycon-2018-tutorial>`_ and
-  `Jupyter Notebook <http://nbviewer.jupyter.org/github/justmarkham/pycon-2018-tutorial/blob/master/tutorial.ipynb>`_
+  `GitHub repo <https://github.com/justmarkham/pycon-2018-tutorial>`__ and
+  `Jupyter Notebook <http://nbviewer.jupyter.org/github/justmarkham/pycon-2018-tutorial/blob/master/tutorial.ipynb>`__
 
 
 Various Tutorials

doc/source/whatsnew/v0.13.0.rst

@@ -690,7 +690,7 @@ Enhancements
 
   .. ipython:: python
 
-    ser = Series([1, 3, np.nan, np.nan, np.nan, 11])
+    ser = pd.Series([1, 3, np.nan, np.nan, np.nan, 11])
     ser.interpolate(limit=2)
 
 - Added ``wide_to_long`` panel data convenience function. See :ref:`the docs<reshaping.melt>`.
@@ -706,7 +706,7 @@ Enhancements
                       })
     df["id"] = df.index
     df
-    wide_to_long(df, ["A", "B"], i="id", j="year")
+    pd.wide_to_long(df, ["A", "B"], i="id", j="year")
 
 .. _scipy: http://www.scipy.org
 .. _documentation: http://docs.scipy.org/doc/scipy/reference/interpolate.html#univariate-interpolation

doc/source/whatsnew/v0.13.1.rst

@@ -88,7 +88,7 @@ Output Formatting Enhancements
 
   Previously output might look like:
 
-  ..   oode-block:: text
+  ..   code-block:: text
 
         age                 today               diff
       0 2001-01-01 00:00:00 2013-04-19 00:00:00 4491 days, 00:00:00

doc/source/whatsnew/v0.14.1.rst

@@ -122,6 +122,7 @@ Enhancements
   pytz timezones across pandas. (:issue:`4688`)
 
   .. ipython:: python
+
      rng = pd.date_range('3/6/2012 00:00', periods=10, freq='D',
                          tz='dateutil/Europe/London')
      rng.tz

doc/source/whatsnew/v0.15.0.rst

@@ -316,6 +316,7 @@ Timezone handling improvements
   previously this resulted in ``Exception`` or ``TypeError`` (:issue:`7812`)
 
   .. ipython:: python
+     :okwarning:
 
      ts = Timestamp('2014-08-01 09:00', tz='US/Eastern')
      ts

doc/source/whatsnew/v0.20.0.rst

@@ -189,6 +189,7 @@ URLs and paths are now inferred using their file extensions. Additionally,
 support for bz2 compression in the python 2 C-engine improved (:issue:`14874`).
 
 .. ipython:: python
+   :okwarning:
 
    url = ('https://github.com/{repo}/raw/{branch}/{path}'
           .format(repo='pandas-dev/pandas',