Merge remote-tracking branch 'upstream/master' into GH36360

Author: arw2019

.github/workflows/stale-pr.yml

@@ -2,7 +2,7 @@ name: "Stale PRs"
 on:
   schedule:
   # * is a special character in YAML so you have to quote this string
-  - cron: "0 */6 * * *"
+  - cron: "0 0 * * *"
 
 jobs:
   stale:
@@ -11,8 +11,8 @@ jobs:
     - uses: actions/stale@v3
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
-        stale-pr-message: "This pull request is stale because it has been open for thirty days with no activity."
-        skip-stale-pr-message: true
+        stale-pr-message: "This pull request is stale because it has been open for thirty days with no activity. Please update or respond to this comment if you're still interested in working on this."
+        skip-stale-pr-message: false
         stale-pr-label: "Stale"
         exempt-pr-labels: "Needs Review,Blocked,Needs Discussion"
         days-before-stale: 30

.pre-commit-config.yaml

@@ -43,3 +43,7 @@ repos:
         entry: python -m scripts.generate_pip_deps_from_conda
         files: ^(environment.yml|requirements-dev.txt)$
         pass_filenames: false
+-   repo: https://github.com/asottile/yesqa
+    rev: v1.2.2
+    hooks:
+    -   id: yesqa

.travis.yml

@@ -46,16 +46,16 @@ 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=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"
       services:
         - mysql
         - postgresql
 
+    - arch: arm64
+      env:
+        - 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:
         # Enabling Deprecations when running tests
         # PANDAS_TESTING_MODE="deprecate" causes DeprecationWarning messages to be displayed in the logs
@@ -65,6 +65,12 @@ matrix:
         - mysql
         - postgresql
 
+  allow_failures:
+    # Moved to allowed_failures 2020-09-29 due to timeouts https://github.com/pandas-dev/pandas/issues/36719
+    - arch: arm64
+      env:
+        - 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)"
+
 
 before_install:
   - echo "before_install"

asv_bench/benchmarks/indexing.py

@@ -191,7 +191,7 @@ def setup(self, index):
         }
         index = indexes[index]
         self.s = Series(np.random.rand(N), index=index)
-        self.indexer = [True, False, True, True, False] * 20000
+        self.indexer = np.random.randint(0, N, size=N)
 
     def time_take(self, index):
         self.s.take(self.indexer)

asv_bench/benchmarks/pandas_vb_common.py

@@ -15,7 +15,7 @@
 
 # Compatibility import for the testing module
 try:
-    import pandas._testing as tm  # noqa
+    import pandas._testing as tm
 except ImportError:
     import pandas.util.testing as tm  # noqa
 

asv_bench/benchmarks/tslibs/offsets.py

@@ -9,7 +9,7 @@
 from pandas import offsets
 
 try:
-    import pandas.tseries.holiday  # noqa
+    import pandas.tseries.holiday
 except ImportError:
     pass
 

ci/code_checks.sh

@@ -335,7 +335,7 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Doctests strings.py' ; echo $MSG
-    pytest -q --doctest-modules pandas/core/strings.py
+    pytest -q --doctest-modules pandas/core/strings/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     # Directories

codecov.yml

@@ -1,7 +1,7 @@
 codecov:
   branch: master
 
-comment: off
+comment: false
 
 coverage:
   status:
@@ -11,3 +11,6 @@ coverage:
     patch:
       default:
         target: '50'
+
+github_checks:
+    annotations: false

doc/source/conf.py

@@ -146,7 +146,7 @@
 # built documents.
 #
 # The short X.Y version.
-import pandas  # noqa: E402 isort:skip
+import pandas  # isort:skip
 
 # version = '%s r%s' % (pandas.__version__, svn_version())
 version = str(pandas.__version__)
@@ -441,14 +441,14 @@
 # Add custom Documenter to handle attributes/methods of an AccessorProperty
 # eg pandas.Series.str and pandas.Series.dt (see GH9322)
 
-import sphinx  # noqa: E402 isort:skip
-from sphinx.util import rpartition  # noqa: E402 isort:skip
-from sphinx.ext.autodoc import (  # noqa: E402 isort:skip
+import sphinx  # isort:skip
+from sphinx.util import rpartition  # isort:skip
+from sphinx.ext.autodoc import (  # isort:skip
     AttributeDocumenter,
     Documenter,
     MethodDocumenter,
 )
-from sphinx.ext.autosummary import Autosummary  # noqa: E402 isort:skip
+from sphinx.ext.autosummary import Autosummary  # isort:skip
 
 
 class AccessorDocumenter(MethodDocumenter):

doc/source/development/code_style.rst

@@ -9,7 +9,7 @@ pandas code style guide
 .. contents:: Table of contents:
    :local:
 
-*pandas* follows the `PEP8 <https://www.python.org/dev/peps/pep-0008/>`_
+pandas follows the `PEP8 <https://www.python.org/dev/peps/pep-0008/>`_
 standard and uses `Black <https://black.readthedocs.io/en/stable/>`_
 and `Flake8 <https://flake8.pycqa.org/en/latest/>`_ to ensure a
 consistent code format throughout the project. For details see the

doc/source/development/contributing.rst

@@ -155,7 +155,7 @@ Using a Docker container
 
 Instead of manually setting up a development environment, you can use `Docker
 <https://docs.docker.com/get-docker/>`_ to automatically create the environment with just several
-commands. Pandas provides a ``DockerFile`` in the root directory to build a Docker image
+commands. pandas provides a ``DockerFile`` in the root directory to build a Docker image
 with a full pandas development environment.
 
 **Docker Commands**
@@ -190,7 +190,7 @@ Note that you might need to rebuild the C extensions if/when you merge with upst
 Installing a C compiler
 ~~~~~~~~~~~~~~~~~~~~~~~
 
-Pandas uses C extensions (mostly written using Cython) to speed up certain
+pandas uses C extensions (mostly written using Cython) to speed up certain
 operations. To install pandas from source, you need to compile these C
 extensions, which means you need a C compiler. This process depends on which
 platform you're using.
@@ -1219,7 +1219,7 @@ This test shows off several useful features of Hypothesis, as well as
 demonstrating a good use-case: checking properties that should hold over
 a large or complicated domain of inputs.
 
-To keep the Pandas test suite running quickly, parametrized tests are
+To keep the pandas test suite running quickly, parametrized tests are
 preferred if the inputs or logic are simple, with Hypothesis tests reserved
 for cases with complex logic or where there are too many combinations of
 options or subtle interactions to test (or think of!) all of them.

doc/source/development/extending.rst

@@ -34,7 +34,7 @@ decorate a class, providing the name of attribute to add. The class's
        @staticmethod
        def _validate(obj):
            # verify there is a column latitude and a column longitude
-           if 'latitude' not in obj.columns or 'longitude' not in obj.columns:
+           if "latitude" not in obj.columns or "longitude" not in obj.columns:
                raise AttributeError("Must have 'latitude' and 'longitude'.")
 
        @property
@@ -50,8 +50,9 @@ decorate a class, providing the name of attribute to add. The class's
 
 Now users can access your methods using the ``geo`` namespace:
 
-      >>> ds = pd.DataFrame({'longitude': np.linspace(0, 10),
-      ...                    'latitude': np.linspace(0, 20)})
+      >>> ds = pd.Dataframe(
+      ...     {"longitude": np.linspace(0, 10), "latitude": np.linspace(0, 20)}
+      ... )
       >>> ds.geo.center
       (5.0, 10.0)
       >>> ds.geo.plot()
@@ -176,6 +177,7 @@ your ``MyExtensionArray`` class, as follows:
 
     from pandas.api.extensions import ExtensionArray, ExtensionScalarOpsMixin
 
+
     class MyExtensionArray(ExtensionArray, ExtensionScalarOpsMixin):
         pass
 
@@ -271,6 +273,7 @@ included as a column in a pandas DataFrame):
         def __arrow_array__(self, type=None):
             # convert the underlying array values to a pyarrow Array
             import pyarrow
+
             return pyarrow.array(..., type=type)
 
 The ``ExtensionDtype.__from_arrow__`` method then controls the conversion
@@ -347,7 +350,6 @@ Below example shows how to define ``SubclassedSeries`` and ``SubclassedDataFrame
 .. code-block:: python
 
    class SubclassedSeries(pd.Series):
-
        @property
        def _constructor(self):
            return SubclassedSeries
@@ -358,7 +360,6 @@ Below example shows how to define ``SubclassedSeries`` and ``SubclassedDataFrame
 
 
    class SubclassedDataFrame(pd.DataFrame):
-
        @property
        def _constructor(self):
            return SubclassedDataFrame
@@ -377,7 +378,7 @@ Below example shows how to define ``SubclassedSeries`` and ``SubclassedDataFrame
    >>> type(to_framed)
    <class '__main__.SubclassedDataFrame'>
 
-   >>> df = SubclassedDataFrame({'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]})
+   >>> df = SubclassedDataFrame({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
    >>> df
       A  B  C
    0  1  4  7
@@ -387,7 +388,7 @@ Below example shows how to define ``SubclassedSeries`` and ``SubclassedDataFrame
    >>> type(df)
    <class '__main__.SubclassedDataFrame'>
 
-   >>> sliced1 = df[['A', 'B']]
+   >>> sliced1 = df[["A", "B"]]
    >>> sliced1
       A  B
    0  1  4
@@ -397,7 +398,7 @@ Below example shows how to define ``SubclassedSeries`` and ``SubclassedDataFrame
    >>> type(sliced1)
    <class '__main__.SubclassedDataFrame'>
 
-   >>> sliced2 = df['A']
+   >>> sliced2 = df["A"]
    >>> sliced2
    0    1
    1    2
@@ -422,39 +423,39 @@ Below is an example to define two original properties, "internal_cache" as a tem
    class SubclassedDataFrame2(pd.DataFrame):
 
        # temporary properties
-       _internal_names = pd.DataFrame._internal_names + ['internal_cache']
+       _internal_names = pd.DataFrame._internal_names + ["internal_cache"]
        _internal_names_set = set(_internal_names)
 
        # normal properties
-       _metadata = ['added_property']
+       _metadata = ["added_property"]
 
        @property
        def _constructor(self):
            return SubclassedDataFrame2
 
 .. code-block:: python
 
-   >>> df = SubclassedDataFrame2({'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]})
+   >>> df = SubclassedDataFrame2({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
    >>> df
       A  B  C
    0  1  4  7
    1  2  5  8
    2  3  6  9
 
-   >>> df.internal_cache = 'cached'
-   >>> df.added_property = 'property'
+   >>> df.internal_cache = "cached"
+   >>> df.added_property = "property"
 
    >>> df.internal_cache
    cached
    >>> df.added_property
    property
 
    # properties defined in _internal_names is reset after manipulation
-   >>> df[['A', 'B']].internal_cache
+   >>> df[["A", "B"]].internal_cache
    AttributeError: 'SubclassedDataFrame2' object has no attribute 'internal_cache'
 
    # properties defined in _metadata are retained
-   >>> df[['A', 'B']].added_property
+   >>> df[["A", "B"]].added_property
    property
 
 .. _extending.plotting-backends:
@@ -468,7 +469,7 @@ one based on Matplotlib. For example:
 
 .. code-block:: python
 
-    >>> pd.set_option('plotting.backend', 'backend.module')
+    >>> pd.set_option("plotting.backend", "backend.module")
     >>> pd.Series([1, 2, 3]).plot()
 
 This would be more or less equivalent to:
@@ -499,4 +500,4 @@ registers the default "matplotlib" backend as follows.
 
 
 More information on how to implement a third-party plotting backend can be found at
-https://github.com/pandas-dev/pandas/blob/master/pandas/plotting/__init__.py#L1.
+https://github.com/pandas-dev/pandas/blob/master/pandas/plotting/__init__.py#L1.

doc/source/development/maintaining.rst

@@ -207,7 +207,7 @@ Only core team members can merge pull requests. We have a few guidelines.
 1. You should typically not self-merge your own pull requests. Exceptions include
    things like small changes to fix CI (e.g. pinning a package version).
 2. You should not merge pull requests that have an active discussion, or pull
-   requests that has any ``-1`` votes from a core maintainer. Pandas operates
+   requests that has any ``-1`` votes from a core maintainer. pandas operates
    by consensus.
 3. For larger changes, it's good to have a +1 from at least two core team members.
 

doc/source/development/roadmap.rst

@@ -141,20 +141,6 @@ ways for users to apply their own Numba-jitted functions where pandas accepts us
 and in groupby and window contexts). This will improve the performance of
 user-defined-functions in these operations by staying within compiled code.
 
-
-Documentation improvements
---------------------------
-
-We'd like to improve the content, structure, and presentation of the pandas documentation.
-Some specific goals include
-
-* Overhaul the HTML theme with a modern, responsive design (:issue:`15556`)
-* Improve the "Getting Started" documentation, designing and writing learning paths
-  for users different backgrounds (e.g. brand new to programming, familiar with
-  other languages like R, already familiar with Python).
-* Improve the overall organization of the documentation and specific subsections
-  of the documentation to make navigation and finding content easier.
-
 Performance monitoring
 ----------------------
 
@@ -203,3 +189,20 @@ should be notified of the proposal.
 When there's agreement that an implementation
 would be welcome, the roadmap should be updated to include the summary and a
 link to the discussion issue.
+
+Completed items
+---------------
+
+This section records now completed items from the pandas roadmap.
+
+Documentation improvements
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+We improved the pandas documentation
+
+* The pandas community worked with others to build the `pydata-sphinx-theme`_,
+  which is now used for https://pandas.pydata.org/docs/ (:issue:`15556`).
+* :ref:`getting_started` contains a number of resources intended for new
+  pandas users coming from a variety of backgrounds (:issue:`26831`).
+
+.. _pydata-sphinx-theme: https://github.com/pandas-dev/pydata-sphinx-theme