Merge remote-tracking branch 'upstream/master' into hist_legend

Author: rhshadrach

.travis.yml

@@ -14,6 +14,8 @@ cache:
 
 env:
   global:
+    # Variable for test workers
+    - PYTEST_WORKERS="auto"
     # create a github personal access token
     # cd pandas-dev/pandas
     # travis encrypt 'PANDAS_GH_TOKEN=personal_access_token' -r pandas-dev/pandas
@@ -38,6 +40,10 @@ matrix:
     - env:
         - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network and not clipboard)"
 
+    - arch: arm64
+      env:
+        - JOB="3.7, arm64" PYTEST_WORKERS=8 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard)"
+
     - env:
         - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="((not slow and not network and not clipboard) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
       services:
@@ -59,15 +65,17 @@ matrix:
         - mysql
         - postgresql
   allow_failures:
-  - dist: bionic
-    python: 3.9-dev
-    env:
+    - arch: arm64
+      env:
+        - JOB="3.7, arm64" PYTEST_WORKERS=8 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard)"
+    - dist: bionic
+      python: 3.9-dev
+      env:
         - JOB="3.9-dev" PATTERN="(not slow and not network)"
 
 before_install:
   - echo "before_install"
-  # set non-blocking IO on travis
-  # https://github.com/travis-ci/travis-ci/issues/8920#issuecomment-352661024
+  # Use blocking IO on travis.  Ref:  https://github.com/travis-ci/travis-ci/issues/8920#issuecomment-352661024
   - python -c 'import os,sys,fcntl; flags = fcntl.fcntl(sys.stdout, fcntl.F_GETFL); fcntl.fcntl(sys.stdout, fcntl.F_SETFL, flags&~os.O_NONBLOCK);'
   - source ci/travis_process_gbq_encryption.sh
   - export PATH="$HOME/miniconda3/bin:$PATH"

README.md

@@ -16,6 +16,7 @@
 [![Downloads](https://anaconda.org/conda-forge/pandas/badges/downloads.svg)](https://pandas.pydata.org)
 [![Gitter](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/pydata/pandas)
 [![Powered by NumFOCUS](https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https://numfocus.org)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
 ## What is it?
 

azure-pipelines.yml

@@ -5,6 +5,9 @@ trigger:
 pr:
 - master
 
+variables:
+  PYTEST_WORKERS: auto
+
 jobs:
 # Mac and Linux use the same template
 - template: ci/azure/posix.yml

ci/deps/azure-37-numpydev.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pip:
     - cython==0.29.16 # GH#34014
     - "git+git://github.com/dateutil/dateutil.git"
-    - "-f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com"
+    - "--extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple"
     - "--pre"
     - "numpy"
     - "scipy"

ci/deps/travis-37-arm64.yaml

@@ -0,0 +1,21 @@
+name: pandas-dev
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - python=3.7.*
+
+  # tools
+  - cython>=0.29.13
+  - pytest>=5.0.1
+  - pytest-xdist>=1.21
+  - hypothesis>=3.58.0
+
+  # pandas dependencies
+  - botocore>=1.11
+  - numpy
+  - python-dateutil
+  - pytz
+  - pip
+  - pip:
+    - moto

ci/run_tests.sh

@@ -20,7 +20,7 @@ if [[ $(uname) == "Linux" && -z $DISPLAY ]]; then
     XVFB="xvfb-run "
 fi
 
-PYTEST_CMD="${XVFB}pytest -m \"$PATTERN\" -n auto --dist=loadfile -s --strict --durations=10 --junitxml=test-data.xml $TEST_ARGS $COVERAGE pandas"
+PYTEST_CMD="${XVFB}pytest -m \"$PATTERN\" -n $PYTEST_WORKERS --dist=loadfile -s --strict --durations=30 --junitxml=test-data.xml $TEST_ARGS $COVERAGE pandas"
 
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"

ci/setup_env.sh

@@ -41,9 +41,17 @@ else
   exit 1
 fi
 
-wget -q "https://repo.continuum.io/miniconda/Miniconda3-latest-$CONDA_OS.sh" -O miniconda.sh
+if [ "${TRAVIS_CPU_ARCH}" == "arm64" ]; then
+  sudo apt-get -y install xvfb
+  CONDA_URL="https://github.com/conda-forge/miniforge/releases/download/4.8.2-1/Miniforge3-4.8.2-1-Linux-aarch64.sh"
+else
+  CONDA_URL="https://repo.continuum.io/miniconda/Miniconda3-latest-$CONDA_OS.sh"
+fi
+wget -q $CONDA_URL -O miniconda.sh
 chmod +x miniconda.sh
-./miniconda.sh -b
+
+# Installation path is required for ARM64 platform as miniforge script installs in path $HOME/miniforge3.
+./miniconda.sh -b -p $MINICONDA_DIR
 
 export PATH=$MINICONDA_DIR/bin:$PATH
 

doc/source/development/contributing.rst

@@ -110,7 +110,7 @@ version control to allow many people to work together on the project.
 Some great resources for learning Git:
 
 * the `GitHub help pages <https://help.github.com/>`_.
-* the `NumPy's documentation <https://docs.scipy.org/doc/numpy/dev/index.html>`_.
+* the `NumPy's documentation <https://numpy.org/doc/stable/dev/index.html>`_.
 * Matthew Brett's `Pydagogue <https://matthew-brett.github.com/pydagogue/>`_.
 
 Getting started with Git
@@ -974,7 +974,7 @@ it is worth getting in the habit of writing tests ahead of time so this is never
 Like many packages, pandas uses `pytest
 <https://docs.pytest.org/en/latest/>`_ and the convenient
 extensions in `numpy.testing
-<https://docs.scipy.org/doc/numpy/reference/routines.testing.html>`_.
+<https://numpy.org/doc/stable/reference/routines.testing.html>`_.
 
 .. note::
 

doc/source/development/extending.rst

@@ -219,7 +219,7 @@ and re-boxes it if necessary.
 
 If applicable, we highly recommend that you implement ``__array_ufunc__`` in your
 extension array to avoid coercion to an ndarray. See
-`the numpy documentation <https://docs.scipy.org/doc/numpy/reference/generated/numpy.lib.mixins.NDArrayOperatorsMixin.html>`__
+`the numpy documentation <https://numpy.org/doc/stable/reference/generated/numpy.lib.mixins.NDArrayOperatorsMixin.html>`__
 for an example.
 
 As part of your implementation, we require that you defer to pandas when a pandas

doc/source/ecosystem.rst

@@ -30,7 +30,7 @@ substantial projects that you feel should be on this list, please let us know.
 Data cleaning and validation
 ----------------------------
 
-`pyjanitor <https://github.com/ericmjl/pyjanitor/>`__
+`Pyjanitor <https://github.com/ericmjl/pyjanitor/>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Pyjanitor provides a clean API for cleaning data, using method chaining.
@@ -115,7 +115,7 @@ It is very similar to the matplotlib plotting backend, but provides interactive
 web-based charts and maps.
 
 
-`seaborn <https://seaborn.pydata.org>`__
+`Seaborn <https://seaborn.pydata.org>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Seaborn is a Python visualization library based on
@@ -136,7 +136,7 @@ provides a powerful, declarative and extremely general way to generate bespoke p
 Various implementations to other languages are available.
 A good implementation for Python users is `has2k1/plotnine <https://github.com/has2k1/plotnine/>`__.
 
-`IPython Vega <https://github.com/vega/ipyvega>`__
+`IPython vega <https://github.com/vega/ipyvega>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 `IPython Vega <https://github.com/vega/ipyvega>`__ leverages `Vega
@@ -147,7 +147,7 @@ A good implementation for Python users is `has2k1/plotnine <https://github.com/h
 
 `Plotly’s <https://plot.ly/>`__ `Python API <https://plot.ly/python/>`__ enables interactive figures and web shareability. Maps, 2D, 3D, and live-streaming graphs are rendered with WebGL and `D3.js <https://d3js.org/>`__. The library supports plotting directly from a pandas DataFrame and cloud-based collaboration. Users of `matplotlib, ggplot for Python, and Seaborn <https://plot.ly/python/matplotlib-to-plotly-tutorial/>`__ can convert figures into interactive web-based plots. Plots can be drawn in `IPython Notebooks <https://plot.ly/ipython-notebooks/>`__ , edited with R or MATLAB, modified in a GUI, or embedded in apps and dashboards. Plotly is free for unlimited sharing, and has `cloud <https://plot.ly/product/plans/>`__, `offline <https://plot.ly/python/offline/>`__, or `on-premise <https://plot.ly/product/enterprise/>`__ accounts for private use.
 
-`QtPandas <https://github.com/draperjames/qtpandas>`__
+`Qtpandas <https://github.com/draperjames/qtpandas>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Spun off from the main pandas library, the `qtpandas <https://github.com/draperjames/qtpandas>`__
@@ -187,7 +187,7 @@ See :ref:`Options and Settings <options>` and
 :ref:`Available Options <options.available>`
 for pandas ``display.`` settings.
 
-`quantopian/qgrid <https://github.com/quantopian/qgrid>`__
+`Quantopian/qgrid <https://github.com/quantopian/qgrid>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 qgrid is "an interactive grid for sorting and filtering
@@ -249,12 +249,12 @@ The following data feeds are available:
  * Stooq Index Data
  * MOEX Data
 
-`quandl/Python <https://github.com/quandl/Python>`__
+`Quandl/Python <https://github.com/quandl/Python>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Quandl API for Python wraps the Quandl REST API to return
 Pandas DataFrames with timeseries indexes.
 
-`pydatastream <https://github.com/vfilimonov/pydatastream>`__
+`Pydatastream <https://github.com/vfilimonov/pydatastream>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 PyDatastream is a Python interface to the
 `Refinitiv Datastream (DWS) <https://www.refinitiv.com/en/products/datastream-macroeconomic-analysis>`__
@@ -384,7 +384,7 @@ Pandas provides an interface for defining
 system. The following libraries implement that interface to provide types not
 found in NumPy or pandas, which work well with pandas' data containers.
 
-`cyberpandas`_
+`Cyberpandas`_
 ~~~~~~~~~~~~~~
 
 Cyberpandas provides an extension type for storing arrays of IP Addresses. These
@@ -411,4 +411,4 @@ Library         Accessor   Classes                   Description
 .. _pdvega: https://altair-viz.github.io/pdvega/
 .. _Altair: https://altair-viz.github.io/
 .. _pandas_path: https://github.com/drivendataorg/pandas-path/
-.. _pathlib.Path: https://docs.python.org/3/library/pathlib.html
+.. _pathlib.Path: https://docs.python.org/3/library/pathlib.html

doc/source/getting_started/intro_tutorials/02_read_write.rst

@@ -23,7 +23,7 @@
                     <div class="card-body">
                         <p class="card-text">
 
-This tutorial uses the titanic data set, stored as CSV. The data
+This tutorial uses the Titanic data set, stored as CSV. The data
 consists of the following data columns:
 
 -  PassengerId: Id of every passenger.
@@ -61,7 +61,7 @@ How do I read and write tabular data?
     <ul class="task-bullet">
         <li>
 
-I want to analyse the titanic passenger data, available as a CSV file.
+I want to analyze the Titanic passenger data, available as a CSV file.
 
 .. ipython:: python
 
@@ -134,7 +134,7 @@ strings (``object``).
     <ul class="task-bullet">
         <li>
 
-My colleague requested the titanic data as a spreadsheet.
+My colleague requested the Titanic data as a spreadsheet.
 
 .. ipython:: python
 

doc/source/getting_started/intro_tutorials/03_subset_data.rst

@@ -330,7 +330,7 @@ When using the column names, row labels or a condition expression, use
 the ``loc`` operator in front of the selection brackets ``[]``. For both
 the part before and after the comma, you can use a single label, a list
 of labels, a slice of labels, a conditional expression or a colon. Using
-a colon specificies you want to select all rows or columns.
+a colon specifies you want to select all rows or columns.
 
 .. raw:: html
 

doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst

@@ -23,7 +23,7 @@
                     <div class="card-body">
                         <p class="card-text">
 
-This tutorial uses the titanic data set, stored as CSV. The data
+This tutorial uses the Titanic data set, stored as CSV. The data
 consists of the following data columns:
 
 -  PassengerId: Id of every passenger.
@@ -72,7 +72,7 @@ Aggregating statistics
     <ul class="task-bullet">
         <li>
 
-What is the average age of the titanic passengers?
+What is the average age of the Titanic passengers?
 
 .. ipython:: python
 
@@ -95,7 +95,7 @@ across rows by default.
     <ul class="task-bullet">
         <li>
 
-What is the median age and ticket fare price of the titanic passengers?
+What is the median age and ticket fare price of the Titanic passengers?
 
 .. ipython:: python
 
@@ -148,7 +148,7 @@ Aggregating statistics grouped by category
     <ul class="task-bullet">
         <li>
 
-What is the average age for male versus female titanic passengers?
+What is the average age for male versus female Titanic passengers?
 
 .. ipython:: python
 

doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst

@@ -23,7 +23,7 @@
                     <div class="card-body">
                         <p class="card-text">
 
-This tutorial uses the titanic data set, stored as CSV. The data
+This tutorial uses the Titanic data set, stored as CSV. The data
 consists of the following data columns:
 
 -  PassengerId: Id of every passenger.
@@ -122,7 +122,7 @@ Sort table rows
     <ul class="task-bullet">
         <li>
 
-I want to sort the titanic data according to the age of the passengers.
+I want to sort the Titanic data according to the age of the passengers.
 
 .. ipython:: python
 
@@ -138,7 +138,7 @@ I want to sort the titanic data according to the age of the passengers.
     <ul class="task-bullet">
         <li>
 
-I want to sort the titanic data according to the cabin class and age in descending order.
+I want to sort the Titanic data according to the cabin class and age in descending order.
 
 .. ipython:: python
 
@@ -282,7 +282,7 @@ For more information about :meth:`~DataFrame.pivot_table`, see the user guide se
    </div>
 
 .. note::
-    If case you are wondering, :meth:`~DataFrame.pivot_table` is indeed directly linked
+    In case you are wondering, :meth:`~DataFrame.pivot_table` is indeed directly linked
     to :meth:`~DataFrame.groupby`. The same result can be derived by grouping on both
     ``parameter`` and ``location``:
 
@@ -338,7 +338,7 @@ newly created column.
 
 The solution is the short version on how to apply :func:`pandas.melt`. The method
 will *melt* all columns NOT mentioned in ``id_vars`` together into two
-columns: A columns with the column header names and a column with the
+columns: A column with the column header names and a column with the
 values itself. The latter column gets by default the name ``value``.
 
 The :func:`pandas.melt` method can be defined in more detail:
@@ -357,8 +357,8 @@ The result in the same, but in more detail defined:
 
 -  ``value_vars`` defines explicitly which columns to *melt* together
 -  ``value_name`` provides a custom column name for the values column
-   instead of the default columns name ``value``
--  ``var_name`` provides a custom column name for the columns collecting
+   instead of the default column name ``value``
+-  ``var_name`` provides a custom column name for the column collecting
    the column header names. Otherwise it takes the index name or a
    default ``variable``
 
@@ -383,7 +383,7 @@ Conversion from wide to long format with :func:`pandas.melt` is explained in the
         <h4>REMEMBER</h4>
 
 -  Sorting by one or more columns is supported by ``sort_values``
--  The ``pivot`` function is purely restructering of the data,
+-  The ``pivot`` function is purely restructuring of the data,
    ``pivot_table`` supports aggregations
 -  The reverse of ``pivot`` (long to wide format) is ``melt`` (wide to
    long format)

doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst

@@ -305,7 +305,7 @@ More information on join/merge of tables is provided in the user guide section o
     <div class="shadow gs-callout gs-callout-remember">
         <h4>REMEMBER</h4>
 
--  Multiple tables can be concatenated both column as row wise using
+-  Multiple tables can be concatenated both column-wise and row-wise using
    the ``concat`` function.
 -  For database-like merging/joining of tables, use the ``merge``
    function.

doc/source/getting_started/intro_tutorials/09_timeseries.rst

@@ -78,7 +78,7 @@ provide any datetime operations (e.g. extract the year, day of the
 week,…). By applying the ``to_datetime`` function, pandas interprets the
 strings and convert these to datetime (i.e. ``datetime64[ns, UTC]``)
 objects. In pandas we call these datetime objects similar to
-``datetime.datetime`` from the standard library a :class:`pandas.Timestamp`.
+``datetime.datetime`` from the standard library as :class:`pandas.Timestamp`.
 
 .. raw:: html
 
@@ -99,7 +99,7 @@ objects. In pandas we call these datetime objects similar to
 Why are these :class:`pandas.Timestamp` objects useful? Let’s illustrate the added
 value with some example cases.
 
-   What is the start and end date of the time series data set working
+   What is the start and end date of the time series data set we are working
    with?
 
 .. ipython:: python
@@ -214,7 +214,7 @@ Plot the typical :math:`NO_2` pattern during the day of our time series of all s
 
 Similar to the previous case, we want to calculate a given statistic
 (e.g. mean :math:`NO_2`) **for each hour of the day** and we can use the
-split-apply-combine approach again. For this case, the datetime property ``hour``
+split-apply-combine approach again. For this case, we use the datetime property ``hour``
 of pandas ``Timestamp``, which is also accessible by the ``dt`` accessor.
 
 .. raw:: html