Merge branch 'main' into backend-indexing

* main: (48 commits) Add test for #9155 (#9161) Remove mypy exclusions for a couple more libraries (#9160) Include numbagg in type checks (#9159) Improve zarr chunks docs (#9140) groupby: remove some internal use of IndexVariable (#9123) Improve `to_zarr` docs (#9139) Split out distributed writes in zarr docs (#9132) Update zendoo badge link (#9133) Support duplicate dimensions in `.chunk` (#9099) Bump the actions group with 2 updates (#9130) adjust repr tests to account for different platforms (#9127) (#9128) Grouper refactor (#9122) Update docstring in api.py for open_mfdataset(), clarifying "chunks" argument (#9121) Add test for rechunking to a size string (#9117) Move Sphinx directives out of `See also` (#8466) new whats-new section (#9115) release v2024.06.0 (#9113) release notes for 2024.06.0 (#9092) [skip-ci] Try fixing hypothesis CI trigger (#9112) Undo custom padding-top. (#9107) ...
pydata · Jun 24, 2024 · 46a902f · 46a902f
2 parents 8d64f60 + 872c1c5
commit 46a902f
Show file tree

Hide file tree

Showing 57 changed files with 1,543 additions and 1,027 deletions.
diff --git a/.github/workflows/ci-additional.yaml b/.github/workflows/ci-additional.yaml
@@ -8,13 +8,6 @@ on:
     branches:
       - "main"
       - "backend-indexing"
-    paths:
-      - 'ci/**'
-      - '.github/**'
-      - '/*'  # covers files such as `pyproject.toml`
-      - 'properties/**'
-      - 'xarray/**'
-
   workflow_dispatch: # allows you to trigger manually
 
 concurrency:
@@ -139,7 +132,7 @@ jobs:
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report xarray/
 
       - name: Upload mypy coverage to Codecov
-        uses: codecov/codecov-action@v4.4.0
+        uses: codecov/codecov-action@v4.5.0
         with:
           file: mypy_report/cobertura.xml
           flags: mypy
@@ -193,7 +186,7 @@ jobs:
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report xarray/
 
       - name: Upload mypy coverage to Codecov
-        uses: codecov/codecov-action@v4.4.0
+        uses: codecov/codecov-action@v4.5.0
         with:
           file: mypy_report/cobertura.xml
           flags: mypy39
@@ -254,7 +247,7 @@ jobs:
           python -m pyright xarray/
 
       - name: Upload pyright coverage to Codecov
-        uses: codecov/codecov-action@v4.4.0
+        uses: codecov/codecov-action@v4.5.0
         with:
           file: pyright_report/cobertura.xml
           flags: pyright
@@ -313,7 +306,7 @@ jobs:
           python -m pyright xarray/
 
       - name: Upload pyright coverage to Codecov
-        uses: codecov/codecov-action@v4.4.0
+        uses: codecov/codecov-action@v4.5.0
         with:
           file: pyright_report/cobertura.xml
           flags: pyright39

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
@@ -8,12 +8,6 @@ on:
     branches:
       - "main"
       - "backend-indexing"
-    paths:
-      - 'ci/**'
-      - '.github/**'
-      - '/*'  # covers files such as `pyproject.toml`
-      - 'properties/**'
-      - 'xarray/**'
   workflow_dispatch: # allows you to trigger manually
 
 concurrency:
@@ -167,7 +161,7 @@ jobs:
           path: pytest.xml
 
       - name: Upload code coverage to Codecov
-        uses: codecov/codecov-action@v4.4.0
+        uses: codecov/codecov-action@v4.5.0
         with:
           file: ./coverage.xml
           flags: unittests

diff --git a/.github/workflows/hypothesis.yaml b/.github/workflows/hypothesis.yaml
@@ -39,9 +39,9 @@ jobs:
     if: |
         always()
         && (
-            (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
-            || needs.detect-ci-trigger.outputs.triggered == 'true'
-            || contains( github.event.pull_request.labels.*.name, 'run-slow-hypothesis')
+            needs.detect-ci-trigger.outputs.triggered == 'false'
+            && ( (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
+                || contains( github.event.pull_request.labels.*.name, 'run-slow-hypothesis'))
         )
     defaults:
       run:

diff --git a/.github/workflows/pypi-release.yaml b/.github/workflows/pypi-release.yaml
@@ -88,7 +88,7 @@ jobs:
           path: dist
       - name: Publish package to TestPyPI
         if: github.event_name == 'push'
-        uses: pypa/gh-action-pypi-publish@v1.8.14
+        uses: pypa/gh-action-pypi-publish@v1.9.0
         with:
           repository_url: https://test.pypi.org/legacy/
           verbose: true
@@ -111,6 +111,6 @@ jobs:
           name: releases
           path: dist
       - name: Publish package to PyPI
-        uses: pypa/gh-action-pypi-publish@v1.8.14
+        uses: pypa/gh-action-pypi-publish@v1.9.0
         with:
           verbose: true
diff --git a/.github/workflows/upstream-dev-ci.yaml b/.github/workflows/upstream-dev-ci.yaml
@@ -146,7 +146,7 @@ jobs:
         run: |
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report
       - name: Upload mypy coverage to Codecov
-        uses: codecov/codecov-action@v4.4.0
+        uses: codecov/codecov-action@v4.5.0
         with:
           file: mypy_report/cobertura.xml
           flags: mypy

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -13,7 +13,7 @@ repos:
       - id: mixed-line-ending
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: 'v0.4.3'
+    rev: 'v0.4.7'
     hooks:
       - id: ruff
         args: ["--fix", "--show-fixes"]

diff --git a/CITATION.cff b/CITATION.cff
@@ -11,6 +11,7 @@ authors:
   orcid: "https://orcid.org/0000-0001-7479-8439"
 - family-names: "Magin"
   given-names: "Justus"
+  orcid: "https://orcid.org/0000-0002-4254-8002"
 - family-names: "Cherian"
   given-names: "Deepak"
   orcid: "https://orcid.org/0000-0002-6861-8734"
@@ -75,6 +76,19 @@ authors:
 - family-names: "Wolfram"
   given-names: "Phillip J."
   orcid: "https://orcid.org/0000-0001-5971-4241"
+- family-names: "Henderson"
+  given-names: "Scott"
+  orcid: "https://orcid.org/0000-0003-0624-4965"
+- family-names: "Awowale"
+  given-names: "Eniola Olufunke"
+- family-names: "Scheick"
+  given-names: "Jessica"
+  orcid: "https://orcid.org/0000-0002-3421-4459"
+- family-names: "Savoie"
+  given-names: "Matthew"
+  orcid: "https://orcid.org/0000-0002-8881-2550"
+- family-names: "Littlejohns"
+  given-names: "Owen"
 title: "xarray"
 abstract: "N-D labeled arrays and datasets in Python."
 license: Apache-2.0

diff --git a/README.md b/README.md
@@ -7,7 +7,7 @@
 [![Available on pypi](https://img.shields.io/pypi/v/xarray.svg)](https://pypi.python.org/pypi/xarray/)
 [![Formatted with black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)
 [![Checked with mypy](http://www.mypy-lang.org/static/mypy_badge.svg)](http://mypy-lang.org/)
-[![Mirror on zendoo](https://zenodo.org/badge/DOI/10.5281/zenodo.598201.svg)](https://doi.org/10.5281/zenodo.598201)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11183201.svg)](https://doi.org/10.5281/zenodo.11183201)
 [![Examples on binder](https://img.shields.io/badge/launch-binder-579ACA.svg?logo=data:image/png;base64,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)](https://mybinder.org/v2/gh/pydata/xarray/main?urlpath=lab/tree/doc/examples/weather-data.ipynb)
 [![Twitter](https://img.shields.io/twitter/follow/xarray_dev?style=social)](https://twitter.com/xarray_dev)
 
@@ -46,15 +46,15 @@ provide a powerful and concise interface. For example:
 
 - Apply operations over dimensions by name: `x.sum('time')`.
 - Select values by label instead of integer location:
-    `x.loc['2014-01-01']` or `x.sel(time='2014-01-01')`.
+  `x.loc['2014-01-01']` or `x.sel(time='2014-01-01')`.
 - Mathematical operations (e.g., `x - y`) vectorize across multiple
-    dimensions (array broadcasting) based on dimension names, not shape.
+  dimensions (array broadcasting) based on dimension names, not shape.
 - Flexible split-apply-combine operations with groupby:
-    `x.groupby('time.dayofyear').mean()`.
+  `x.groupby('time.dayofyear').mean()`.
 - Database like alignment based on coordinate labels that smoothly
-    handles missing values: `x, y = xr.align(x, y, join='outer')`.
+  handles missing values: `x, y = xr.align(x, y, join='outer')`.
 - Keep track of arbitrary metadata in the form of a Python dictionary:
-    `x.attrs`.
+  `x.attrs`.
 
 ## Documentation
 
@@ -73,12 +73,12 @@ page](https://docs.xarray.dev/en/stable/contributing.html).
 ## Get in touch
 
 - Ask usage questions ("How do I?") on
-    [GitHub Discussions](https://github.com/pydata/xarray/discussions).
+  [GitHub Discussions](https://github.com/pydata/xarray/discussions).
 - Report bugs, suggest features or view the source code [on
-    GitHub](https://github.com/pydata/xarray).
+  GitHub](https://github.com/pydata/xarray).
 - For less well defined questions or ideas, or to announce other
-    projects of interest to xarray users, use the [mailing
-    list](https://groups.google.com/forum/#!forum/xarray).
+  projects of interest to xarray users, use the [mailing
+  list](https://groups.google.com/forum/#!forum/xarray).
 
 ## NumFOCUS
 
@@ -114,7 +114,7 @@ Licensed under the Apache License, Version 2.0 (the "License"); you
 may not use this file except in compliance with the License. You may
 obtain a copy of the License at
 
- <https://www.apache.org/licenses/LICENSE-2.0>
+<https://www.apache.org/licenses/LICENSE-2.0>
 
 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,

diff --git a/asv_bench/benchmarks/dataarray_missing.py b/asv_bench/benchmarks/dataarray_missing.py
@@ -66,7 +66,7 @@ def time_ffill(self, shape, chunks, limit):
         ),
     )
     def time_bfill(self, shape, chunks, limit):
-        actual = self.da.ffill(dim="time", limit=limit)
+        actual = self.da.bfill(dim="time", limit=limit)
 
         if chunks is not None:
             actual = actual.compute()
diff --git a/ci/install-upstream-wheels.sh b/ci/install-upstream-wheels.sh
@@ -1,13 +1,21 @@
 #!/usr/bin/env bash
 
+if which micromamba >/dev/null; then
+    conda=micromamba
+elif which mamba >/dev/null; then
+    conda=mamba
+else
+    conda=conda
+fi
+
 # temporarily (?) remove numbagg and numba
-micromamba remove -y numba numbagg sparse
+$conda remove -y numba numbagg sparse
 # temporarily remove numexpr
-micromamba remove -y numexpr
+$conda remove -y numexpr
 # temporarily remove backends
-micromamba remove -y cf_units hdf5 h5py netcdf4 pydap
+$conda remove -y cf_units hdf5 h5py netcdf4 pydap
 # forcibly remove packages to avoid artifacts
-micromamba remove -y --force \
+$conda remove -y --force \
     numpy \
     scipy \
     pandas \
@@ -19,6 +27,7 @@ micromamba remove -y --force \
     bottleneck \
     flox
     # pint
+
 # to limit the runtime of Upstream CI
 python -m pip install \
     -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple \
@@ -39,13 +48,15 @@ python -m pip install \
     --pre \
     --upgrade \
     pyarrow
+# manually install `pint` to pull in new dependencies
+python -m pip install --upgrade pint
 python -m pip install \
     --no-deps \
     --upgrade \
     git+https://github.com/dask/dask \
     git+https://github.com/dask/dask-expr \
     git+https://github.com/dask/distributed \
-    git+https://github.com/zarr-developers/zarr \
+    git+https://github.com/zarr-developers/zarr.git@main \
     git+https://github.com/Unidata/cftime \
     git+https://github.com/pypa/packaging \
     git+https://github.com/hgrecco/pint \

diff --git a/doc/_static/style.css b/doc/_static/style.css
@@ -7,9 +7,8 @@ table.docutils td {
     word-wrap: break-word;
 }
 
-div.bd-header-announcement {
-  background-color: unset;
-  color: #000;
+.bd-header-announcement {
+  background-color: var(--pst-color-info-bg);
 }
 
 /* Reduce left and right margins */
@@ -222,8 +221,6 @@ main *:target::before {
 }
 
 body {
-  /* Add padding to body to avoid overlap with navbar. */
-  padding-top: var(--navbar-height);
   width: 100%;
 }
 

diff --git a/doc/conf.py b/doc/conf.py
@@ -242,7 +242,7 @@
     Theme by the <a href="https://ebp.jupyterbook.org">Executable Book Project</a></p>""",
     twitter_url="https://twitter.com/xarray_dev",
     icon_links=[],  # workaround for pydata/pydata-sphinx-theme#1220
-    announcement="🍾 <a href='https://github.com/pydata/xarray/discussions/8462'>Xarray is now 10 years old!</a> 🎉",
+    announcement="<a href='https://forms.gle/KEq7WviCdz9xTaJX6'>Xarray's 2024 User Survey is live now. Please take ~5 minutes to fill it out and help us improve Xarray.</a>",
 )
 
 

diff --git a/doc/ecosystem.rst b/doc/ecosystem.rst
@@ -74,6 +74,7 @@ Extend xarray capabilities
 - `Collocate <https://github.com/cistools/collocate>`_: Collocate xarray trajectories in arbitrary physical dimensions
 - `eofs <https://ajdawson.github.io/eofs/>`_: EOF analysis in Python.
 - `hypothesis-gufunc <https://hypothesis-gufunc.readthedocs.io/en/latest/>`_: Extension to hypothesis. Makes it easy to write unit tests with xarray objects as input.
+- `ntv-pandas <https://github.com/loco-philippe/ntv-pandas>`_ : A tabular analyzer and a semantic, compact and reversible converter for multidimensional and tabular data
 - `nxarray <https://github.com/nxarray/nxarray>`_: NeXus input/output capability for xarray.
 - `xarray-compare <https://github.com/astropenguin/xarray-compare>`_: xarray extension for data comparison.
 - `xarray-dataclasses <https://github.com/astropenguin/xarray-dataclasses>`_: xarray extension for typed DataArray and Dataset creation.

diff --git a/doc/examples/multidimensional-coords.ipynb b/doc/examples/multidimensional-coords.ipynb
@@ -190,13 +190,6 @@
     "\n",
     "**Note**: This group-by-latitude approach does not take into account the finite-size geometry of grid cells. It simply bins each value according to the coordinates at the cell center. Xarray has no understanding of grid cells and their geometry. More precise geographic regridding for xarray data is available via the [xesmf](https://xesmf.readthedocs.io) package."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

diff --git a/doc/user-guide/computation.rst b/doc/user-guide/computation.rst
@@ -50,7 +50,7 @@ Use :py:func:`~xarray.where` to conditionally switch between values:
 
     xr.where(arr > 0, "positive", "negative")
 
-Use `@` to perform matrix multiplication:
+Use `@` to compute the :py:func:`~xarray.dot` product:
 
 .. ipython:: python