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

Author: simonjayhawkins

.pre-commit-config.yaml

@@ -30,3 +30,30 @@ repos:
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
+-   repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.6.0
+    hooks:
+      - id: rst-backticks
+        # these exclusions should be removed and the files fixed
+        exclude: (?x)(
+          categorical\.rst|
+          contributing\.rst|
+          contributing_docstring\.rst|
+          extending\.rst|
+          ecosystem\.rst|
+          comparison_with_sql\.rst|
+          install\.rst|
+          calculate_statistics\.rst|
+          combine_dataframes\.rst|
+          v0\.|
+          v1\.0\.|
+          v1\.1\.[012])
+-   repo: local
+    hooks:
+    -   id: pip_to_conda
+        name: Generate pip dependency from conda
+        description: This hook checks if the conda environment.yml and requirements-dev.txt are equal
+        language: system
+        entry: python -m scripts.generate_pip_deps_from_conda
+        files: ^(environment.yml|requirements-dev.txt)$
+        pass_filenames: false

.travis.yml

@@ -1,6 +1,15 @@
 language: python
 python: 3.7
 
+addons:
+  apt:
+    update: true
+    packages:
+      - xvfb
+
+services:
+  - xvfb
+
 # To turn off cached cython files and compiler cache
 # set NOCACHE-true
 # To delete caches go to https://travis-ci.org/OWNER/REPOSITORY/caches or run
@@ -10,30 +19,27 @@ cache:
   ccache: true
   directories:
     - $HOME/.cache # cython cache
-    - $HOME/.ccache # compiler 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
     - secure: "EkWLZhbrp/mXJOx38CHjs7BnjXafsqHtwxPQrqWy457VDFWhIY1DMnIR/lOWG+a20Qv52sCsFtiZEmMfUjf0pLGXOqurdxbYBGJ7/ikFLk9yV2rDwiArUlVM9bWFnFxHvdz9zewBH55WurrY4ShZWyV+x2dWjjceWG5VpWeI6sA="
 
 git:
-  # for cloning
   depth: false
 
 matrix:
   fast_finish: true
 
   include:
-    # In allowed failures
     - dist: bionic
       python: 3.9-dev
       env:
         - JOB="3.9-dev" PATTERN="(not slow and not network and not clipboard)"
+
     - env:
         - JOB="3.8" ENV_FILE="ci/deps/travis-38.yaml" PATTERN="(not slow and not network and not clipboard)"
 
@@ -42,7 +48,7 @@ matrix:
 
     - 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 and not arm_slow)"
+        - JOB="3.7, arm64" PYTEST_WORKERS=1 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard and not arm_slow)"
 
     - env:
         - JOB="3.7, locale" ENV_FILE="ci/deps/travis-37-locale.yaml" PATTERN="((not slow and not network and not clipboard) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
@@ -71,12 +77,6 @@ before_install:
   - uname -a
   - git --version
   - ./ci/check_git_tags.sh
-  # Because travis runs on Google Cloud and has a /etc/boto.cfg,
-  # it breaks moto import, see:
-  # https://github.com/spulec/moto/issues/1771
-  # https://github.com/boto/boto/issues/3741
-  # This overrides travis and tells it to look nowhere.
-  - export BOTO_CONFIG=/dev/null
 
 install:
   - echo "install start"

ci/build39.sh

@@ -1,7 +1,6 @@
 #!/bin/bash -e
 # Special build for python3.9 until numpy puts its own wheels up
 
-sudo apt-get install build-essential gcc xvfb
 pip install --no-deps -U pip wheel setuptools
 pip install cython numpy python-dateutil pytz pytest pytest-xdist hypothesis
 

ci/setup_env.sh

@@ -42,9 +42,7 @@ else
 fi
 
 if [ "${TRAVIS_CPU_ARCH}" == "arm64" ]; then
-  sudo apt-get update
-  sudo apt-get -y install xvfb
-  CONDA_URL="https://github.com/conda-forge/miniforge/releases/download/4.8.5-0/Miniforge3-4.8.5-0-Linux-aarch64.sh"
+  CONDA_URL="https://github.com/conda-forge/miniforge/releases/download/4.8.5-1/Miniforge3-4.8.5-1-Linux-aarch64.sh"
 else
   CONDA_URL="https://repo.continuum.io/miniconda/Miniconda3-latest-$CONDA_OS.sh"
 fi
@@ -100,8 +98,6 @@ echo "conda list (root environment)"
 conda list
 
 # Clean up any left-over from a previous build
-# (note workaround for https://github.com/conda/conda/issues/2679:
-#  `conda env remove` issue)
 conda remove --all -q -y -n pandas-dev
 
 echo
@@ -142,12 +138,6 @@ conda list pandas
 echo "[Build extensions]"
 python setup.py build_ext -q -i -j2
 
-# TODO: Some of our environments end up with old versions of pip (10.x)
-# Adding a new enough version of pip to the requirements explodes the
-# solve time. Just using pip to update itself.
-# - py35_macos
-# - py35_compat
-# - py36_32bit
 echo "[Updating pip]"
 python -m pip install --no-deps -U pip wheel setuptools
 

doc/source/development/policies.rst

@@ -16,7 +16,7 @@ deprecations, API compatibility, and version numbering.
 
 A pandas release number is made up of ``MAJOR.MINOR.PATCH``.
 
-API breaking changes should only occur in **major** releases. Theses changes
+API breaking changes should only occur in **major** releases. These changes
 will be documented, with clear guidance on what is changing, why it's changing,
 and how to migrate existing code to the new behavior.
 

doc/source/getting_started/overview.rst

@@ -40,7 +40,7 @@ Here are just a few of the things that pandas does well:
     higher dimensional objects
   - Automatic and explicit **data alignment**: objects can be explicitly
     aligned to a set of labels, or the user can simply ignore the labels and
-    let `Series`, `DataFrame`, etc. automatically align the data for you in
+    let ``Series``, ``DataFrame``, etc. automatically align the data for you in
     computations
   - Powerful, flexible **group by** functionality to perform
     split-apply-combine operations on data sets, for both aggregating and

doc/source/reference/panel.rst

@@ -7,4 +7,4 @@ Panel
 =====
 .. currentmodule:: pandas
 
-`Panel` was removed in 0.25.0. For prior documentation, see the `0.24 documentation <https://pandas.pydata.org/pandas-docs/version/0.24/reference/panel.html>`_
+``Panel`` was removed in 0.25.0. For prior documentation, see the `0.24 documentation <https://pandas.pydata.org/pandas-docs/version/0.24/reference/panel.html>`_

doc/source/reference/plotting.rst

@@ -7,7 +7,7 @@ Plotting
 ========
 .. currentmodule:: pandas.plotting
 
-The following functions are contained in the `pandas.plotting` module.
+The following functions are contained in the ``pandas.plotting`` module.
 
 .. autosummary::
    :toctree: api/

doc/source/user_guide/10min.rst

@@ -431,9 +431,9 @@ See more at :ref:`Histogramming and Discretization <basics.discretization>`.
 String Methods
 ~~~~~~~~~~~~~~
 
-Series is equipped with a set of string processing methods in the `str`
+Series is equipped with a set of string processing methods in the ``str``
 attribute that make it easy to operate on each element of the array, as in the
-code snippet below. Note that pattern-matching in `str` generally uses `regular
+code snippet below. Note that pattern-matching in ``str`` generally uses `regular
 expressions <https://docs.python.org/3/library/re.html>`__ by default (and in
 some cases always uses them). See more at :ref:`Vectorized String Methods
 <text.string_methods>`.

doc/source/user_guide/basics.rst

@@ -1459,7 +1459,7 @@ for altering the ``Series.name`` attribute.
 .. versionadded:: 0.24.0
 
 The methods :meth:`DataFrame.rename_axis` and :meth:`Series.rename_axis`
-allow specific names of a `MultiIndex` to be changed (as opposed to the
+allow specific names of a ``MultiIndex`` to be changed (as opposed to the
 labels).
 
 .. ipython:: python
@@ -1592,7 +1592,7 @@ index value along with a Series containing the data in each row:
       row
 
    All values in ``row``, returned as a Series, are now upcasted
-   to floats, also the original integer value in column `x`:
+   to floats, also the original integer value in column ``x``:
 
    .. ipython:: python
 
@@ -1787,8 +1787,8 @@ used to sort a pandas object by its index levels.
 .. versionadded:: 1.1.0
 
 Sorting by index also supports a ``key`` parameter that takes a callable
-function to apply to the index being sorted. For `MultiIndex` objects,
-the key is applied per-level to the levels specified by `level`.
+function to apply to the index being sorted. For ``MultiIndex`` objects,
+the key is applied per-level to the levels specified by ``level``.
 
 .. ipython:: python
 
@@ -1812,8 +1812,8 @@ For information on key sorting by value, see :ref:`value sorting
 By values
 ~~~~~~~~~
 
-The :meth:`Series.sort_values` method is used to sort a `Series` by its values. The
-:meth:`DataFrame.sort_values` method is used to sort a `DataFrame` by its column or row values.
+The :meth:`Series.sort_values` method is used to sort a ``Series`` by its values. The
+:meth:`DataFrame.sort_values` method is used to sort a ``DataFrame`` by its column or row values.
 The optional ``by`` parameter to :meth:`DataFrame.sort_values` may used to specify one or more columns
 to use to determine the sorted order.
 
@@ -1855,8 +1855,8 @@ to apply to the values being sorted.
    s1.sort_values()
    s1.sort_values(key=lambda x: x.str.lower())
 
-`key` will be given the :class:`Series` of values and should return a ``Series``
-or array of the same shape with the transformed values. For `DataFrame` objects,
+``key`` will be given the :class:`Series` of values and should return a ``Series``
+or array of the same shape with the transformed values. For ``DataFrame`` objects,
 the key is applied per column, so the key should still expect a Series and return
 a Series, e.g.
 

doc/source/user_guide/cookbook.rst

@@ -1270,7 +1270,7 @@ Often it's useful to obtain the lower (or upper) triangular form of a correlatio
 
     corr_mat.where(mask)
 
-The `method` argument within `DataFrame.corr` can accept a callable in addition to the named correlation types.  Here we compute the `distance correlation <https://en.wikipedia.org/wiki/Distance_correlation>`__ matrix for a `DataFrame` object.
+The ``method`` argument within ``DataFrame.corr`` can accept a callable in addition to the named correlation types.  Here we compute the ``distance correlation <https://en.wikipedia.org/wiki/Distance_correlation>``__ matrix for a ``DataFrame`` object.
 
 .. ipython:: python
 

doc/source/user_guide/enhancingperf.rst

@@ -488,9 +488,9 @@ These operations are supported by :func:`pandas.eval`:
 * Attribute access, e.g., ``df.a``
 * Subscript expressions, e.g., ``df[0]``
 * Simple variable evaluation, e.g., ``pd.eval('df')`` (this is not very useful)
-* Math functions: `sin`, `cos`, `exp`, `log`, `expm1`, `log1p`,
-  `sqrt`, `sinh`, `cosh`, `tanh`, `arcsin`, `arccos`, `arctan`, `arccosh`,
-  `arcsinh`, `arctanh`, `abs`, `arctan2` and `log10`.
+* Math functions: ``sin``, ``cos``, ``exp``, ``log``, ``expm1``, ``log1p``,
+  ``sqrt``, ``sinh``, ``cosh``, ``tanh``, ``arcsin``, ``arccos``, ``arctan``, ``arccosh``,
+  ``arcsinh``, ``arctanh``, ``abs``, ``arctan2`` and ``log10``.
 
 This Python syntax is **not** allowed:
 

doc/source/user_guide/groupby.rst

@@ -216,10 +216,10 @@ in case you want to include ``NA`` values in group keys, you could pass ``dropna
 
 .. ipython:: python
 
-    # Default `dropna` is set to True, which will exclude NaNs in keys
+    # Default ``dropna`` is set to True, which will exclude NaNs in keys
     df_dropna.groupby(by=["b"], dropna=True).sum()
 
-    # In order to allow NaN in keys, set `dropna` to False
+    # In order to allow NaN in keys, set ``dropna`` to False
     df_dropna.groupby(by=["b"], dropna=False).sum()
 
 The default setting of ``dropna`` argument is ``True`` which means ``NA`` are not included in group keys.