Merge remote-tracking branch 'origin/master' into fix-flake8-v017

Author: aqurilla

.circleci/config.yml

@@ -101,6 +101,7 @@ asv_bench/pandas/
 # Documentation generated files #
 #################################
 doc/source/generated
+doc/source/api/generated
 doc/source/_static
 doc/source/vbench
 doc/source/vbench.rst

.gitignore

@@ -23,7 +23,7 @@ env:
 
 git:
     # for cloning
-    depth: 1500
+    depth: 2000
 
 matrix:
     fast_finish: true
@@ -38,28 +38,19 @@ matrix:
 
     - dist: trusty
       env:
-        - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/deps/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" PATTERN="slow"
-      addons:
-        apt:
-          packages:
-          - language-pack-zh-hans
-    - dist: trusty
-      env:
-        - JOB="2.7" ENV_FILE="ci/deps/travis-27.yaml" PATTERN="not slow"
+        - JOB="2.7" ENV_FILE="ci/deps/travis-27.yaml" PATTERN="not slow and db"
       addons:
         apt:
           packages:
           - python-gtk2
+
     - dist: trusty
       env:
-        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36.yaml" PATTERN="not slow and not network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
+        - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="not slow and not network and db" LOCALE_OVERRIDE="zh_CN.UTF-8"
+
     - dist: trusty
       env:
-        - JOB="3.7, NumPy dev" ENV_FILE="ci/deps/travis-37-numpydev.yaml" PATTERN="not slow and not network" TEST_ARGS="-W error" PANDAS_TESTING_MODE="deprecate"
-      addons:
-        apt:
-          packages:
-          - xsel
+        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36.yaml" PATTERN="not slow and not network and db" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
 
     # In allow_failures
     - dist: trusty

.travis.yml

@@ -45,14 +45,6 @@
     </a>
   </td>
 </tr>
-<tr>
-  <td></td>
-  <td>
-    <a href="https://circleci.com/gh/pandas-dev/pandas">
-    <img src="https://circleci.com/gh/circleci/mongofinil/tree/master.svg?style=shield&circle-token=223d8cafa7b02902c3e150242520af8944e34671" alt="circleci build status" />
-    </a>
-  </td>
-</tr>
 <tr>
   <td></td>
   <td>

README.md

@@ -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/frame_methods.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/join_merge.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/panel_ctor.py

@@ -1,5 +1,6 @@
-from pandas import (DataFrame, Series, Period, PeriodIndex, date_range,
-                    period_range)
+from pandas import (
+    DataFrame, Period, PeriodIndex, Series, date_range, period_range)
+from pandas.tseries.frequencies import to_offset
 
 
 class PeriodProperties(object):
@@ -35,25 +36,48 @@ def time_asfreq(self, freq):
         self.per.asfreq('A')
 
 
+class PeriodConstructor(object):
+    params = [['D'], [True, False]]
+    param_names = ['freq', 'is_offset']
+
+    def setup(self, freq, is_offset):
+        if is_offset:
+            self.freq = to_offset(freq)
+        else:
+            self.freq = freq
+
+    def time_period_constructor(self, freq, is_offset):
+        Period('2012-06-01', freq=freq)
+
+
 class PeriodIndexConstructor(object):
 
-    params = ['D']
-    param_names = ['freq']
+    params = [['D'], [True, False]]
+    param_names = ['freq', 'is_offset']
 
-    def setup(self, freq):
+    def setup(self, freq, is_offset):
         self.rng = date_range('1985', periods=1000)
         self.rng2 = date_range('1985', periods=1000).to_pydatetime()
         self.ints = list(range(2000, 3000))
-
-    def time_from_date_range(self, freq):
+        self.daily_ints = date_range('1/1/2000', periods=1000,
+                                     freq=freq).strftime('%Y%m%d').map(int)
+        if is_offset:
+            self.freq = to_offset(freq)
+        else:
+            self.freq = freq
+
+    def time_from_date_range(self, freq, is_offset):
         PeriodIndex(self.rng, freq=freq)
 
-    def time_from_pydatetime(self, freq):
+    def time_from_pydatetime(self, freq, is_offset):
         PeriodIndex(self.rng2, freq=freq)
 
-    def time_from_ints(self, freq):
+    def time_from_ints(self, freq, is_offset):
         PeriodIndex(self.ints, freq=freq)
 
+    def time_from_ints_daily(self, freq, is_offset):
+        PeriodIndex(self.daily_ints, freq=freq)
+
 
 class DataFramePeriodColumn(object):
 
@@ -94,7 +118,7 @@ def time_value_counts(self, typ):
 class Indexing(object):
 
     def setup(self):
-        self.index = PeriodIndex(start='1985', periods=1000, freq='D')
+        self.index = period_range(start='1985', periods=1000, freq='D')
         self.series = Series(range(1000), index=self.index)
         self.period = self.index[500]
 

asv_bench/benchmarks/period.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/reindex.py

@@ -106,6 +106,7 @@ def setup(self, method, use_bottleneck):
             from pandas.core import nanops
             nanops._USE_BOTTLENECK = use_bottleneck
         self.df = pd.DataFrame(np.random.randn(1000, 30))
+        self.df2 = pd.DataFrame(np.random.randn(1000, 30))
         self.s = pd.Series(np.random.randn(1000))
         self.s2 = pd.Series(np.random.randn(1000))
 
@@ -115,6 +116,12 @@ def time_corr(self, method, use_bottleneck):
     def time_corr_series(self, method, use_bottleneck):
         self.s.corr(self.s2, method=method)
 
+    def time_corrwith_cols(self, method, use_bottleneck):
+        self.df.corrwith(self.df2, method=method)
+
+    def time_corrwith_rows(self, method, use_bottleneck):
+        self.df.corrwith(self.df2, axis=1, method=method)
+
 
 class Covariance(object):
 

asv_bench/benchmarks/stat_ops.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/timedelta.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

asv_bench/benchmarks/timestamp.py

@@ -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: |