Resolved Merge Conflicts

Author: joybh98

.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
@@ -34,32 +34,23 @@ matrix:
  include:
  - dist: trusty
  env:
- - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="not slow and not network"
+ - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network)"
 
  - 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 or (single 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) or (single 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) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
 
  # In allow_failures
  - dist: trusty

.travis.yml

@@ -0,0 +1,54 @@
+Copyright 2017- Paul Ganssle <paul@ganssle.io>
+Copyright 2017- dateutil contributors (see AUTHORS file)
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+
+The above license applies to all contributions after 2017-12-01, as well as
+all contributions that have been re-licensed (see AUTHORS file for the list of
+contributors who have re-licensed their code).
+--------------------------------------------------------------------------------
+dateutil - Extensions to the standard Python datetime module.
+
+Copyright (c) 2003-2011 - Gustavo Niemeyer <gustavo@niemeyer.net>
+Copyright (c) 2012-2014 - Tomi Pieviläinen <tomi.pievilainen@iki.fi>
+Copyright (c) 2014-2016 - Yaron de Leeuw <me@jarondl.net>
+Copyright (c) 2015- - Paul Ganssle <paul@ganssle.io>
+Copyright (c) 2015- - dateutil contributors (see AUTHORS file)
+
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+ * Redistributions of source code must retain the above copyright notice,
+ this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above copyright notice,
+ this list of conditions and the following disclaimer in the documentation
+ and/or other materials provided with the distribution.
+ * Neither the name of the copyright holder nor the names of its
+ contributors may be used to endorse or promote products derived from
+ this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+The above BSD License Applies to all code, even that also covered by Apache 2.0.

LICENSES/DATEUTIL_LICENSE

@@ -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

@@ -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

@@ -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

@@ -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: |

azure-pipelines.yml

@@ -20,21 +20,36 @@ jobs:
  CONDA_PY: "27"
  PATTERN: "not slow and not network"
 
- py37_locale:
- ENV_FILE: ci/deps/azure-37-locale.yaml
- CONDA_PY: "37"
- PATTERN: "not slow and not network"
+ py27_locale_slow_old_np:
+ ENV_FILE: ci/deps/azure-27-locale.yaml
+ CONDA_PY: "27"
+ PATTERN: "slow"
  LOCALE_OVERRIDE: "zh_CN.UTF-8"
+ EXTRA_APT: "language-pack-zh-hans"
 
  py36_locale_slow:
  ENV_FILE: ci/deps/azure-36-locale_slow.yaml
  CONDA_PY: "36"
  PATTERN: "not slow and not network"
  LOCALE_OVERRIDE: "it_IT.UTF-8"
 
+ py37_locale:
+ ENV_FILE: ci/deps/azure-37-locale.yaml
+ CONDA_PY: "37"
+ PATTERN: "not slow and not network"
+ LOCALE_OVERRIDE: "zh_CN.UTF-8"
+
+ py37_np_dev:
+ ENV_FILE: ci/deps/azure-37-numpydev.yaml
+ CONDA_PY: "37"
+ PATTERN: "not slow and not network"
+ TEST_ARGS: "-W error"
+ PANDAS_TESTING_MODE: "deprecate"
+ EXTRA_APT: "xsel"
+
  steps:
  - script: |
- if [ "$(uname)" == "Linux" ]; then sudo apt-get install -y libc6-dev-i386; fi
+ if [ "$(uname)" == "Linux" ]; then sudo apt-get install -y libc6-dev-i386 $EXTRA_APT; fi
  echo "Installing Miniconda"
  ci/incremental/install_miniconda.sh
  export PATH=$HOME/miniconda3/bin:$PATH