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

Author: simonjayhawkins

.github/workflows/autoupdate-pre-commit-config.yml

@@ -23,7 +23,7 @@ jobs:
       - name: Update pre-commit config packages
         uses: technote-space/create-pr-action@v2
         with:
-          GITHUB_TOKEN: ${{ secrets.ACTION_TRIGGER_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           EXECUTE_COMMANDS: |
             pip install pre-commit
             pre-commit autoupdate || (exit 0);

.github/workflows/comment_bot.yml

@@ -0,0 +1,40 @@
+name: Comment-bot
+
+on:
+  issue_comment:
+    types:
+      - created
+      - edited
+
+jobs:
+  autotune:
+    name: "Fixup pre-commit formatting"
+    if: startsWith(github.event.comment.body, '@github-actions pre-commit')
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: r-lib/actions/pr-fetch@master
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - name: Cache multiple paths
+        uses: actions/cache@v2
+        with:
+          path: |
+            ~/.cache/pre-commit
+            ~/.cache/pip
+          key: pre-commit-dispatched-${{ runner.os }}-build
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      - name: Install-pre-commit
+        run: python -m pip install --upgrade pre-commit
+      - name: Run pre-commit
+        run: pre-commit run --all-files || (exit 0)
+      - name: Commit results
+        run: |
+          git config user.name "$(git log -1 --pretty=format:%an)"
+          git config user.email "$(git log -1 --pretty=format:%ae)"
+          git commit -a -m 'Fixes from pre-commit [automated commit]' || echo "No changes to commit"
+      - uses: r-lib/actions/pr-push@master
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.pre-commit-config.yaml

@@ -89,6 +89,9 @@ repos:
             # No direct imports from conftest
             conftest\ import|
             import\ conftest
+
+            # Check for use of pandas.testing instead of tm
+            pd\.testing\.
         types: [python]
         files: ^pandas/tests/
     -   id: incorrect-code-directives

asv_bench/benchmarks/algorithms.py

@@ -5,7 +5,6 @@
 from pandas._libs import lib
 
 import pandas as pd
-from pandas.core.algorithms import make_duplicates_of_left_unique_in_right
 
 from .pandas_vb_common import tm
 
@@ -175,15 +174,4 @@ def time_argsort(self, N):
         self.array.argsort()
 
 
-class RemoveDuplicates:
-    def setup(self):
-        N = 10 ** 5
-        na = np.arange(int(N / 2))
-        self.left = np.concatenate([na[: int(N / 4)], na[: int(N / 4)]])
-        self.right = np.concatenate([na, na])
-
-    def time_make_duplicates_of_left_unique_in_right(self):
-        make_duplicates_of_left_unique_in_right(self.left, self.right)
-
-
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

ci/deps/azure-38-locale.yaml

@@ -18,6 +18,7 @@ dependencies:
   - html5lib
   - ipython
   - jinja2
+  - jedi<0.18.0
   - lxml
   - matplotlib <3.3.0
   - moto

ci/deps/azure-38-slow.yaml

@@ -30,7 +30,7 @@ dependencies:
   - moto>=1.3.14
   - scipy
   - sqlalchemy
-  - xlrd<2.0
+  - xlrd>=2.0
   - xlsxwriter
   - xlwt
   - moto

ci/deps/azure-windows-37.yaml

@@ -33,7 +33,7 @@ dependencies:
   - s3fs>=0.4.2
   - scipy
   - sqlalchemy
-  - xlrd<2.0
+  - xlrd>=2.0
   - xlsxwriter
   - xlwt
   - pyreadstat

doc/source/conf.py

@@ -687,6 +687,30 @@ def process_class_docstrings(app, what, name, obj, options, lines):
         lines[:] = joined.split("\n")
 
 
+_BUSINED_ALIASES = [
+    "pandas.tseries.offsets." + name
+    for name in [
+        "BDay",
+        "CDay",
+        "BMonthEnd",
+        "BMonthBegin",
+        "CBMonthEnd",
+        "CBMonthBegin",
+    ]
+]
+
+
+def process_business_alias_docstrings(app, what, name, obj, options, lines):
+    """
+    Starting with sphinx 3.4, the "autodoc-process-docstring" event also
+    gets called for alias classes. This results in numpydoc adding the
+    methods/attributes to the docstring, which we don't want (+ this
+    causes warnings with sphinx).
+    """
+    if name in _BUSINED_ALIASES:
+        lines[:] = []
+
+
 suppress_warnings = [
     # We "overwrite" autosummary with our PandasAutosummary, but
     # still want the regular autosummary setup to run. So we just
@@ -716,6 +740,7 @@ def setup(app):
     app.connect("source-read", rstjinja)
     app.connect("autodoc-process-docstring", remove_flags_docstring)
     app.connect("autodoc-process-docstring", process_class_docstrings)
+    app.connect("autodoc-process-docstring", process_business_alias_docstrings)
     app.add_autodocumenter(AccessorDocumenter)
     app.add_autodocumenter(AccessorAttributeDocumenter)
     app.add_autodocumenter(AccessorMethodDocumenter)

doc/source/getting_started/overview.rst

@@ -147,7 +147,7 @@ pandas possible. Thanks to `all of our contributors <https://github.com/pandas-d
 
 If you're interested in contributing, please visit the :ref:`contributing guide <contributing>`.
 
-pandas is a `NumFOCUS <https://www.numfocus.org/open-source-projects/>`__ sponsored project.
+pandas is a `NumFOCUS <https://numfocus.org/sponsored-projects>`__ sponsored project.
 This will help ensure the success of the development of pandas as a world-class open-source
 project and makes it possible to `donate <https://pandas.pydata.org/donate.html>`__ to the project.
 

doc/source/user_guide/10min.rst

@@ -163,7 +163,7 @@ Selection
 
 .. note::
 
-   While standard Python / Numpy expressions for selecting and setting are
+   While standard Python / NumPy expressions for selecting and setting are
    intuitive and come in handy for interactive work, for production code, we
    recommend the optimized pandas data access methods, ``.at``, ``.iat``,
    ``.loc`` and ``.iloc``.
@@ -239,7 +239,7 @@ Select via the position of the passed integers:
 
    df.iloc[3]
 
-By integer slices, acting similar to numpy/Python:
+By integer slices, acting similar to NumPy/Python:
 
 .. ipython:: python
 

doc/source/user_guide/cookbook.rst

@@ -15,7 +15,7 @@ Simplified, condensed, new-user friendly, in-line examples have been inserted wh
 augment the Stack-Overflow and GitHub links.  Many of the links contain expanded information,
 above what the in-line examples offer.
 
-pandas (pd) and Numpy (np) are the only two abbreviated imported modules. The rest are kept
+pandas (pd) and NumPy (np) are the only two abbreviated imported modules. The rest are kept
 explicitly imported for newer users.
 
 Idioms

doc/source/user_guide/io.rst

@@ -2834,15 +2834,40 @@ parse HTML tables in the top-level pandas io function ``read_html``.
 Excel files
 -----------
 
-The :func:`~pandas.read_excel` method can read Excel 2003 (``.xls``)
-files using the ``xlrd`` Python module.  Excel 2007+ (``.xlsx``) files
-can be read using either ``xlrd`` or ``openpyxl``. Binary Excel (``.xlsb``)
+The :func:`~pandas.read_excel` method can read Excel 2007+ (``.xlsx``) files
+using the ``openpyxl`` Python module. Excel 2003 (``.xls``) files
+can be read using ``xlrd``. Binary Excel (``.xlsb``)
 files can be read using ``pyxlsb``.
 The :meth:`~DataFrame.to_excel` instance method is used for
 saving a ``DataFrame`` to Excel.  Generally the semantics are
 similar to working with :ref:`csv<io.read_csv_table>` data.
 See the :ref:`cookbook<cookbook.excel>` for some advanced strategies.
 
+.. warning::
+
+   The `xlwt <https://xlwt.readthedocs.io/en/latest/>`__ package for writing old-style ``.xls``
+   excel files is no longer maintained.
+   The `xlrd <https://xlrd.readthedocs.io/en/latest/>`__ package is now only for reading
+   old-style ``.xls`` files.
+
+   Previously, the default argument ``engine=None`` to :func:`~pandas.read_excel`
+   would result in using the ``xlrd`` engine in many cases, including new
+   Excel 2007+ (``.xlsx``) files.
+   If `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`__  is installed,
+   many of these cases will now default to using the ``openpyxl`` engine.
+   See the :func:`read_excel` documentation for more details.
+
+   Thus, it is strongly encouraged to install ``openpyxl`` to read Excel 2007+
+   (``.xlsx``) files.
+   **Please do not report issues when using ``xlrd`` to read ``.xlsx`` files.**
+   This is no longer supported, switch to using ``openpyxl`` instead.
+
+   Attempting to use the the ``xlwt`` engine will raise a ``FutureWarning``
+   unless the option :attr:`io.excel.xls.writer` is set to ``"xlwt"``.
+   While this option is now deprecated and will also raise a ``FutureWarning``,
+   it can be globally set and the warning suppressed. Users are recommended to
+   write ``.xlsx`` files using the ``openpyxl`` engine instead.
+
 .. _io.excel_reader:
 
 Reading Excel files

doc/source/user_guide/timeseries.rst

@@ -1888,6 +1888,34 @@ Those two examples are equivalent for this time series:
 
 Note the use of ``'start'`` for ``origin`` on the last example. In that case, ``origin`` will be set to the first value of the timeseries.
 
+Backward resample
+~~~~~~~~~~~~~~~~~
+
+.. versionadded:: 1.3.0
+
+Instead of adjusting the beginning of bins, sometimes we need to fix the end of the bins to make a backward resample with a given ``freq``. The backward resample sets ``closed`` to ``'right'`` by default since the last value should be considered as the edge point for the last bin.
+
+We can set ``origin`` to ``'end'``. The value for a specific ``Timestamp`` index stands for the resample result from the current ``Timestamp`` minus ``freq`` to the current ``Timestamp`` with a right close.
+
+.. ipython:: python
+
+   ts.resample('17min', origin='end').sum()
+
+Besides, in contrast with the ``'start_day'`` option, ``end_day`` is supported. This will set the origin as the ceiling midnight of the largest ``Timestamp``.
+
+.. ipython:: python
+
+   ts.resample('17min', origin='end_day').sum()
+
+The above result uses ``2000-10-02 00:29:00`` as the last bin's right edge since the following computation.
+
+.. ipython:: python
+
+   ceil_mid = rng.max().ceil('D')
+   freq = pd.offsets.Minute(17)
+   bin_res = ceil_mid - freq * ((ceil_mid - rng.max()) // freq)
+   bin_res
+
 .. _timeseries.periods:
 
 Time span representation

doc/source/whatsnew/index.rst

@@ -24,6 +24,7 @@ Version 1.2
 .. toctree::
    :maxdepth: 2
 
+   v1.2.1
    v1.2.0
 
 Version 1.1