Merge remote-tracking branch 'upstream/master' into testing-cln

Author: arw2019

.pre-commit-config.yaml

@@ -30,3 +30,38 @@ 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)(
+          text\.rst|
+          timeseries\.rst|
+          visualization\.rst|
+          missing_data\.rst|
+          options\.rst|
+          reshaping\.rst|
+          scale\.rst|
+          merging\.rst|
+          cookbook\.rst|
+          enhancingperf\.rst|
+          groupby\.rst|
+          io\.rst|
+          overview\.rst|
+          panel\.rst|
+          plotting\.rst|
+          10min\.rst|
+          basics\.rst|
+          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])

.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/user_guide/timeseries.rst

@@ -579,7 +579,12 @@ This type of slicing will work on a ``DataFrame`` with a ``DatetimeIndex`` as we
 partial string selection is a form of label slicing, the endpoints **will be** included. This
 would include matching times on an included date:
 
+.. warning::
+
+   Indexing ``DataFrame`` rows with strings is deprecated in pandas 1.2.0 and will be removed in a future version.  Use ``frame.loc[dtstring]`` instead.
+
 .. ipython:: python
+   :okwarning:
 
    dft = pd.DataFrame(np.random.randn(100000, 1), columns=['A'],
                       index=pd.date_range('20130101', periods=100000, freq='T'))
@@ -590,24 +595,28 @@ This starts on the very first time in the month, and includes the last date and
 time for the month:
 
 .. ipython:: python
+   :okwarning:
 
    dft['2013-1':'2013-2']
 
 This specifies a stop time **that includes all of the times on the last day**:
 
 .. ipython:: python
+   :okwarning:
 
    dft['2013-1':'2013-2-28']
 
 This specifies an **exact** stop time (and is not the same as the above):
 
 .. ipython:: python
+   :okwarning:
 
    dft['2013-1':'2013-2-28 00:00:00']
 
 We are stopping on the included end-point as it is part of the index:
 
 .. ipython:: python
+   :okwarning:
 
    dft['2013-1-15':'2013-1-15 12:30:00']
 
@@ -631,6 +640,7 @@ We are stopping on the included end-point as it is part of the index:
 Slicing with string indexing also honors UTC offset.
 
 .. ipython:: python
+   :okwarning:
 
     df = pd.DataFrame([0], index=pd.DatetimeIndex(['2019-01-01'], tz='US/Pacific'))
     df
@@ -681,6 +691,7 @@ If index resolution is second, then the minute-accurate timestamp gives a
 If the timestamp string is treated as a slice, it can be used to index ``DataFrame`` with ``[]`` as well.
 
 .. ipython:: python
+    :okwarning:
 
     dft_minute = pd.DataFrame({'a': [1, 2, 3], 'b': [4, 5, 6]},
                               index=series_minute.index)
@@ -2027,6 +2038,7 @@ You can pass in dates and strings to ``Series`` and ``DataFrame`` with ``PeriodI
 Passing a string representing a lower frequency than ``PeriodIndex`` returns partial sliced data.
 
 .. ipython:: python
+   :okwarning:
 
    ps['2011']
 

doc/source/whatsnew/v0.11.0.rst

@@ -367,6 +367,7 @@ Enhancements
   - You can now select with a string from a DataFrame with a datelike index, in a similar way to a Series (:issue:`3070`)
 
     .. ipython:: python
+       :okwarning:
 
         idx = pd.date_range("2001-10-1", periods=5, freq='M')
         ts = pd.Series(np.random.rand(len(idx)), index=idx)

doc/source/whatsnew/v1.1.3.rst

@@ -35,6 +35,7 @@ Fixed regressions
 - Fixed regression in :meth:`Series.__getitem__` incorrectly raising when the input was a frozenset (:issue:`35747`)
 - Fixed regression in :meth:`read_excel` with ``engine="odf"`` caused ``UnboundLocalError`` in some cases where cells had nested child nodes (:issue:`36122`, :issue:`35802`)
 - Fixed regression in :class:`DataFrame` and :class:`Series` comparisons between numeric arrays and strings (:issue:`35700`, :issue:`36377`)
+- Fixed regression in :meth:`DataFrame.apply` with ``raw=True`` and user-function returning string (:issue:`35940`)
 - Fixed regression when setting empty :class:`DataFrame` column to a :class:`Series` in preserving name of index in frame (:issue:`36527`)
 - Fixed regression in :class:`Period` incorrect value for ordinal over the maximum timestamp (:issue:`36430`)
 
@@ -51,6 +52,7 @@ Bug fixes
 - Bug in :meth:`DataFrame.stack` raising a ``ValueError`` when stacking :class:`MultiIndex` columns based on position when the levels had duplicate names (:issue:`36353`)
 - Bug in :meth:`Series.astype` showing too much precision when casting from ``np.float32`` to string dtype (:issue:`36451`)
 - Bug in :meth:`Series.isin` and :meth:`DataFrame.isin` when using ``NaN`` and a row length above 1,000,000 (:issue:`22205`)
+- Bug in :func:`cut` raising a ``ValueError`` when passed a :class:`Series` of labels with ``ordered=False`` (:issue:`36603`)
 
 .. ---------------------------------------------------------------------------
 

doc/source/whatsnew/v1.2.0.rst

@@ -117,7 +117,7 @@ Other enhancements
 - :meth:`DataFrame.applymap` now supports ``na_action`` (:issue:`23803`)
 - :class:`Index` with object dtype supports division and multiplication (:issue:`34160`)
 - :meth:`DataFrame.explode` and :meth:`Series.explode` now support exploding of sets (:issue:`35614`)
-- `Styler` now allows direct CSS class name addition to individual data cells (:issue:`36159`)
+- ``Styler`` now allows direct CSS class name addition to individual data cells (:issue:`36159`)
 - :meth:`Rolling.mean()` and :meth:`Rolling.sum()` use Kahan summation to calculate the mean to avoid numerical problems (:issue:`10319`, :issue:`11645`, :issue:`13254`, :issue:`32761`, :issue:`36031`)
 - :meth:`DatetimeIndex.searchsorted`, :meth:`TimedeltaIndex.searchsorted`, :meth:`PeriodIndex.searchsorted`, and :meth:`Series.searchsorted` with datetimelike dtypes will now try to cast string arguments (listlike and scalar) to the matching datetimelike type (:issue:`36346`)
 
@@ -213,6 +213,7 @@ Deprecations
 - Date parser functions :func:`~pandas.io.date_converters.parse_date_time`, :func:`~pandas.io.date_converters.parse_date_fields`, :func:`~pandas.io.date_converters.parse_all_fields` and :func:`~pandas.io.date_converters.generic_parser` from ``pandas.io.date_converters`` are deprecated and will be removed in a future version; use :func:`to_datetime` instead (:issue:`35741`)
 - :meth:`DataFrame.lookup` is deprecated and will be removed in a future version, use :meth:`DataFrame.melt` and :meth:`DataFrame.loc` instead (:issue:`18682`)
 - The :meth:`Index.to_native_types` is deprecated. Use ``.astype(str)`` instead (:issue:`28867`)
+- Deprecated indexing :class:`DataFrame` rows with datetime-like strings ``df[string]``, use ``df.loc[string]`` instead (:issue:`36179`)
 
 .. ---------------------------------------------------------------------------
 
@@ -222,12 +223,12 @@ Deprecations
 Performance improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-- Performance improvements when creating DataFrame or Series with dtype `str` or :class:`StringDtype` from array with many string elements (:issue:`36304`, :issue:`36317`, :issue:`36325`, :issue:`36432`)
+- Performance improvements when creating DataFrame or Series with dtype ``str`` or :class:`StringDtype` from array with many string elements (:issue:`36304`, :issue:`36317`, :issue:`36325`, :issue:`36432`)
 - Performance improvement in :meth:`GroupBy.agg` with the ``numba`` engine (:issue:`35759`)
 - Performance improvements when creating :meth:`pd.Series.map` from a huge dictionary (:issue:`34717`)
 - Performance improvement in :meth:`GroupBy.transform` with the ``numba`` engine (:issue:`36240`)
 - ``Styler`` uuid method altered to compress data transmission over web whilst maintaining reasonably low table collision probability (:issue:`36345`)
-- Performance improvement in :meth:`pd.to_datetime` with non-`ns` time unit for `float` `dtype` columns (:issue:`20445`)
+- Performance improvement in :meth:`pd.to_datetime` with non-ns time unit for ``float`` ``dtype`` columns (:issue:`20445`)
 
 .. ---------------------------------------------------------------------------
 
@@ -262,7 +263,7 @@ Timedelta
 Timezones
 ^^^^^^^^^
 
-- Bug in :func:`date_range` was raising AmbiguousTimeError for valid input with `ambiguous=False` (:issue:`35297`)
+- Bug in :func:`date_range` was raising AmbiguousTimeError for valid input with ``ambiguous=False`` (:issue:`35297`)
 -
 
 
@@ -271,6 +272,7 @@ Numeric
 - Bug in :func:`to_numeric` where float precision was incorrect (:issue:`31364`)
 - Bug in :meth:`DataFrame.any` with ``axis=1`` and ``bool_only=True`` ignoring the ``bool_only`` keyword (:issue:`32432`)
 - Bug in :meth:`Series.equals` where a ``ValueError`` was raised when numpy arrays were compared to scalars (:issue:`35267`)
+- Bug in :class:`Series` where two :class:`Series` each have a :class:`DatetimeIndex` with different timezones having those indexes incorrectly changed when performing arithmetic operations (:issue:`33671`)
 -
 
 Conversion
@@ -303,29 +305,29 @@ Indexing
 Missing
 ^^^^^^^
 
-- Bug in :meth:`SeriesGroupBy.transform` now correctly handles missing values for `dropna=False` (:issue:`35014`)
+- Bug in :meth:`SeriesGroupBy.transform` now correctly handles missing values for ``dropna=False`` (:issue:`35014`)
 -
 
 MultiIndex
 ^^^^^^^^^^
 
-- Bug in :meth:`DataFrame.xs` when used with :class:`IndexSlice` raises ``TypeError`` with message `Expected label or tuple of labels` (:issue:`35301`)
+- Bug in :meth:`DataFrame.xs` when used with :class:`IndexSlice` raises ``TypeError`` with message ``"Expected label or tuple of labels"`` (:issue:`35301`)
 -
 
 I/O
 ^^^
 
 - :func:`read_sas` no longer leaks resources on failure (:issue:`35566`)
 - Bug in :meth:`to_csv` caused a ``ValueError`` when it was called with a filename in combination with ``mode`` containing a ``b`` (:issue:`35058`)
-- In :meth:`read_csv` `float_precision='round_trip'` now handles `decimal` and `thousands` parameters (:issue:`35365`)
+- In :meth:`read_csv` ``float_precision='round_trip'`` now handles ``decimal`` and ``thousands`` parameters (:issue:`35365`)
 - :meth:`to_pickle` and :meth:`read_pickle` were closing user-provided file objects (:issue:`35679`)
-- :meth:`to_csv` passes compression arguments for `'gzip'` always to `gzip.GzipFile` (:issue:`28103`)
+- :meth:`to_csv` passes compression arguments for ``'gzip'`` always to ``gzip.GzipFile`` (:issue:`28103`)
 - :meth:`to_csv` did not support zip compression for binary file object not having a filename (:issue:`35058`)
-- :meth:`to_csv` and :meth:`read_csv` did not honor `compression` and `encoding` for path-like objects that are internally converted to file-like objects (:issue:`35677`, :issue:`26124`, and :issue:`32392`)
+- :meth:`to_csv` and :meth:`read_csv` did not honor ``compression`` and ``encoding`` for path-like objects that are internally converted to file-like objects (:issue:`35677`, :issue:`26124`, and :issue:`32392`)
 - :meth:`to_picke` and :meth:`read_pickle` did not support compression for file-objects (:issue:`26237`, :issue:`29054`, and :issue:`29570`)
 - Bug in :func:`LongTableBuilder.middle_separator` was duplicating LaTeX longtable entires in the List of Tables of a LaTeX document (:issue:`34360`)
-- Bug in :meth:`read_csv` with `engine='python'` truncating data if multiple items present in first row and first element started with BOM (:issue:`36343`)
-- Removed ``private_key`` and ``verbose`` from :func:`read_gbq` as they are no longer supported in `pandas-gbq` (:issue:`34654` :issue:`30200`)
+- Bug in :meth:`read_csv` with ``engine='python'`` truncating data if multiple items present in first row and first element started with BOM (:issue:`36343`)
+- Removed ``private_key`` and ``verbose`` from :func:`read_gbq` as they are no longer supported in ``pandas-gbq`` (:issue:`34654`, :issue:`30200`)
 
 Plotting
 ^^^^^^^^

doc/sphinxext/README.rst

@@ -7,7 +7,7 @@ pandas documentation. These copies originate from other projects:
 - ``numpydoc`` - Numpy's Sphinx extensions: this can be found at its own
   repository: https://github.com/numpy/numpydoc
 - ``ipython_directive`` and ``ipython_console_highlighting`` in the folder
-  `ipython_sphinxext` - Sphinx extensions from IPython: these are included
+  ``ipython_sphinxext`` - Sphinx extensions from IPython: these are included
   in IPython: https://github.com/ipython/ipython/tree/master/IPython/sphinxext
 
 .. note::

pandas/core/aggregation.py

@@ -6,6 +6,7 @@
 from collections import defaultdict
 from functools import partial
 from typing import (
+    TYPE_CHECKING,
     Any,
     Callable,
     DefaultDict,
@@ -26,7 +27,9 @@
 from pandas.core.base import SpecificationError
 import pandas.core.common as com
 from pandas.core.indexes.api import Index
-from pandas.core.series import Series
+
+if TYPE_CHECKING:
+    from pandas.core.series import Series
 
 
 def reconstruct_func(
@@ -281,7 +284,7 @@ def relabel_result(
     func: Dict[str, List[Union[Callable, str]]],
     columns: Iterable[Label],
     order: Iterable[int],
-) -> Dict[Label, Series]:
+) -> Dict[Label, "Series"]:
     """
     Internal function to reorder result if relabelling is True for
     dataframe.agg, and return the reordered result in dict.
@@ -308,10 +311,10 @@ def relabel_result(
     reordered_indexes = [
         pair[0] for pair in sorted(zip(columns, order), key=lambda t: t[1])
     ]
-    reordered_result_in_dict: Dict[Label, Series] = {}
+    reordered_result_in_dict: Dict[Label, "Series"] = {}
     idx = 0
 
-    reorder_mask = not isinstance(result, Series) and len(result.columns) > 1
+    reorder_mask = not isinstance(result, ABCSeries) and len(result.columns) > 1
     for col, fun in func.items():
         s = result[col].dropna()