Merge branch 'main' into refactor-group-abundance

.conda/meta.yaml

@@ -40,6 +40,7 @@ requirements:
     - adjusttext >=0.7
     - numba >=0.41.0
     - pooch >=1.7.0
+    - joblib >=1.3.1
 
 test:
   source_files:

.cruft.json

@@ -1,7 +1,7 @@
 {
   "template": "https://github.com/scverse/cookiecutter-scverse",
-  "commit": "605f95714130c960bce12eab98a4e023e8932249",
-  "checkout": "v0.2.22",
+  "commit": "8e96abb5c3e2d5078c44713958da672711cf2a48",
+  "checkout": "v0.3.0",
   "context": {
     "cookiecutter": {
       "project_name": "scirpy",
@@ -16,6 +16,11 @@
         ".github/workflows/**.yaml",
         "docs/_templates/autosummary/**.rst"
       ],
+      "_render_devdocs": false,
+      "_jinja2_env_vars": {
+        "lstrip_blocks": true,
+        "trim_blocks": true
+      },
       "_template": "https://github.com/scverse/cookiecutter-scverse"
     }
   },

.github/workflows/conda.yaml

@@ -41,13 +41,12 @@ jobs:
           python-version: ${{ matrix.python-version }}
 
       - name: install conda build
-        # TODO pinning conda-build version because it stopped working for no good reason in 3.25 or 3.26.
         run: |
-          mamba install -y conda-build=3.24.0 conda-verify
+          mamba install -y boa conda-verify
         shell: bash
 
       - name: build and test package
         run: |
           cd .conda
-          mamba build --no-anaconda-upload .
+          conda mambabuild --no-anaconda-upload .
         shell: bash

.github/workflows/release.yaml

@@ -1,30 +1,29 @@
 name: Release
 
 on:
-  push:
-    tags:
-      - "*.*.*"
+  release:
+    types: [published]
 
+# Use "trusted publishing", see https://docs.pypi.org/trusted-publishers/
 jobs:
   release:
-    name: Release
+    name: Upload release to PyPI
     runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/scirpy
+    permissions:
+      id-token: write # IMPORTANT: this permission is mandatory for trusted publishing
     steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
         with:
-          python-version: "3.10"
-
-      - name: Install hatch
-        run: pip install hatch
-
-      - name: Build project for distribution
-        run: hatch build
-
-      - name: Publish a Python distribution to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
+          filter: blob:none
+          fetch-depth: 0
+      - uses: actions/setup-python@v4
         with:
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          python-version: "3.x"
+          cache: "pip"
+      - run: pip install build
+      - run: python -m build
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/test.yaml

@@ -26,10 +26,13 @@ jobs:
           - os: ubuntu-latest
             python: "3.9"
           - os: ubuntu-latest
-            python: "3.10"
+            python: "3.11"
           - os: ubuntu-latest
-            python: "3.10"
+            python: "3.11"
             pip-flags: "--pre"
+            name: PRE-RELEASE DEPENDENCIES
+
+    name: ${{ matrix.name }} Python ${{ matrix.python }}
 
     env:
       OS: ${{ matrix.os }}
@@ -59,6 +62,9 @@ jobs:
           PLATFORM: ${{ matrix.os }}
           DISPLAY: :42
         run: |
-          pytest -v --cov --color=yes
+          coverage run -m pytest -v --color=yes
+      - name: Report coverage
+        run: |
+          coverage report
       - name: Upload coverage
         uses: codecov/codecov-action@v3

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ default_stages:
 minimum_pre_commit_version: 2.16.0
 repos:
   - repo: https://github.com/psf/black
-    rev: "23.10.1"
+    rev: "23.12.1"
     hooks:
       - id: black
   - repo: https://github.com/asottile/blacken-docs
@@ -26,7 +26,7 @@ repos:
         language_version: "17.9.1"
         exclude: '^\.conda'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.3
+    rev: v0.1.14
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

CHANGELOG.md

@@ -8,7 +8,32 @@ and this project adheres to [Semantic Versioning][].
 [keep a changelog]: https://keepachangelog.com/en/1.0.0/
 [semantic versioning]: https://semver.org/spec/v2.0.0.html
 
-## [Unreleased]
+## v0.15.0
+
+### Fixes
+
+-   Fix incompatibility with `scipy` 1.12 ([#484](https://github.com/scverse/scirpy/pull/484))
+-   Fix incompatibility with `adjustText` 1.0 ([#477](https://github.com/scverse/scirpy/pull/477))
+-   Reduce overall importtime by deferring the import of the `airr` package until it is actually used. ([#473](https://github.com/scverse/scirpy/pull/473))
+
+### New features
+
+-   Speed up alignment distances by pre-filtering. There are two filtering strategies: A (lossless) length-based filter
+    and a heuristic based on the expected penalty per mismatch. This is implemented in the `FastAlignmentDistanceCalculator`
+    class which supersedes the `AlignmentDistanceCalculator` class, which is now deprecated. Using the `"alignment"` metric
+    in `pp.ir_dist` now uses the `FastAlignmentDistanceCalculator` with only the lenght-based filter activated.
+    Using the `"fastalignment"` activates the heuristic, which is significantly faster, but results in some false-negatives. ([#456](https://github.com/scverse/scirpy/pull/456))
+-   Switch to [joblib/loky](https://joblib.readthedocs.io/en/latest/generated/joblib.Parallel.html) as a backend for parallel
+    processing in `pp.ir_dist`. Joblib enables to switch to alternative backends that support out-of-machine computing
+    (e.g. `dask`, `ray`) via the `parallel_config` context manager. Additionally, chunk sizes are now adjusted dynamically based on the problem size. ([#473](https://github.com/scverse/scirpy/pull/473))
+
+### Documentation
+
+-   The default values of the distance calculator classes in `ir_dist.metrics` was unclear. The default value is now
+    set in the classes. In `pp.ir_dist` and `ir_dist.sequence_dist`, no cutoff argument is passed to the metrics
+    objects, unless one is explicitly specified (previously `None` was passed by default).
+
+## v0.14.0
 
 ### Breaking changes
 
@@ -19,9 +44,15 @@ and this project adheres to [Semantic Versioning][].
     `lambda x: ~ak.is_none(x["junction_aa"], axis=-1)`. To learn more about native awkward array functions, please
     refer to the [awkward array documentation](https://awkward-array.org/doc/main/reference/index.html). ([#444](https://github.com/scverse/scirpy/pull/444))
 
+### Additions
+
+-   The `clonal_expansion` function now supports a `breakpoints` argument for more flexible "expansion categories".
+    The `breakpoints` argument supersedes the `clip_at` parameter, which is now deprecated. ([#439](https://github.com/scverse/scirpy/pull/439))
+
 ### Fixes
 
 -   Fix that `define_clonotype_clusters` could not retreive `within_group` columns from MuData ([#459](https://github.com/scverse/scirpy/pull/459))
+-   Fix that AIRR Rearrangment fields of integer types could not be written when their value was None ([#465](https://github.com/scverse/scirpy/pull/465))
 
 ## v0.13.1
 

README.md

@@ -23,7 +23,7 @@ Please consider making a tax-deductible [donation](https://numfocus.org/donate-t
   >
 </a>
 
-[badge-tests]: https://img.shields.io/github/actions/workflow/status/grst/scirpy/test.yaml?branch=main
+[badge-tests]: https://img.shields.io/github/actions/workflow/status/scverse/scirpy/test.yaml?branch=main
 [link-tests]: https://github.com/scverse/scirpy/actions/workflows/test.yml
 [badge-docs]: https://img.shields.io/readthedocs/scirpy
 [badge-pypi]: https://img.shields.io/pypi/v/scirpy?logo=PyPI
@@ -69,7 +69,7 @@ There are several alternative options to install scirpy:
 3. Install the latest development version:
 
     ```bash
-    pip install git+https://github.com/grst/scirpy.git@main
+    pip install git+https://github.com/scverse/scirpy.git@main
     ```
 
 4. Run it in a container using [Docker][] or [Podman][]:
@@ -123,7 +123,7 @@ You can cite the scverse publication as follows:
 > [10.1038/s41587-023-01733-8](https://doi.org/10.1038/s41587-023-01733-8).
 
 [scverse-discourse]: https://discourse.scverse.org/
-[issue-tracker]: https://github.com/grst/scirpy/issues
+[issue-tracker]: https://github.com/scverse/scirpy/issues
 [changelog]: https://scirpy.readthedocs.io/latest/changelog.html
 [link-docs]: https://scirpy.readthedocs.io
 [link-api]: https://scirpy.readthedocs.io/latest/api.html

docs/_static/css/custom.css

@@ -0,0 +1,4 @@
+/* Reduce the font size in data frames - See https://github.com/scverse/cookiecutter-scverse/issues/193 */
+div.cell_output table.dataframe {
+    font-size: 0.8em;
+}

docs/api.rst

@@ -301,3 +301,4 @@ distance metrics
    ir_dist.metrics.LevenshteinDistanceCalculator
    ir_dist.metrics.HammingDistanceCalculator
    ir_dist.metrics.AlignmentDistanceCalculator
+   ir_dist.metrics.FastAlignmentDistanceCalculator

docs/conf.py

@@ -115,6 +115,7 @@
     "mudata": ("https://mudata.readthedocs.io/en/latest/", None),
     "awkward": ("https://awkward-array.org/doc/main/", None),
     "pooch": ("https://www.fatiando.org/pooch/latest/", None),
+    "joblib": ("https://joblib.readthedocs.io/en/latest", None),
 }
 
 # List of patterns, relative to source directory, that match files and
@@ -132,6 +133,7 @@
 html_static_path = ["_static"]
 html_title = project_name
 html_logo = "img/scirpy_logo.png"
+html_css_files = ["css/custom.css"]
 
 
 html_theme_options = {
@@ -177,18 +179,3 @@
     ("py:meth", "mudata.MuData.update"),
     ("py:class", "awkward.highlevel.Array"),
 ]
-
-
-def setup(app):
-    """App setup hook."""
-    app.add_config_value(
-        "recommonmark_config",
-        {
-            "auto_toc_tree_section": "Contents",
-            "enable_auto_toc_tree": True,
-            "enable_math": True,
-            "enable_inline_math": False,
-            "enable_eval_rst": True,
-        },
-        True,
-    )

docs/contributing.md

@@ -1,6 +1,6 @@
 # Contributing guide
 
-Scanpy provides extensive [developer documentation][scanpy developer guide], most of which applies to this repo, too.
+Scanpy provides extensive [developer documentation][scanpy developer guide], most of which applies to this project, too.
 This document will not reproduce the entire content from there. Instead, it aims at summarizing the most important
 information to get you started on contributing.
 
@@ -19,8 +19,8 @@ pip install -e ".[dev,test,doc]"
 
 ## Code-style
 
-This template uses [pre-commit][] to enforce consistent code-styles. On every commit, pre-commit checks will either
-automatically fix issues with the code, or raise an error message.
+This package uses [pre-commit][] to enforce consistent code-styles.
+On every commit, pre-commit checks will either automatically fix issues with the code, or raise an error message.
 
 To enable pre-commit locally, simply run
 
@@ -42,10 +42,10 @@ git pull --rebase
 to integrate the changes into yours.
 While the [pre-commit.ci][] is useful, we strongly encourage installing and running pre-commit locally first to understand its usage.
 
-Finally, most editors have an _autoformat on save_ feature. Consider enabling this option for [black][black-editors]
+Finally, most editors have an _autoformat on save_ feature. Consider enabling this option for [ruff][ruff-editors]
 and [prettier][prettier-editors].
 
-[black-editors]: https://black.readthedocs.io/en/stable/integrations/editors.html
+[ruff-editors]: https://docs.astral.sh/ruff/integrations/
 [prettier-editors]: https://prettier.io/docs/en/editors.html
 
 ## Writing tests
@@ -64,74 +64,26 @@ command line by executing
 pytest
 ```
 
-in the root of the repository. Continuous integration will automatically run the tests on all pull requests.
+in the root of the repository.
 
-[scanpy-test-docs]: https://scanpy.readthedocs.io/en/latest/dev/testing.html#writing-tests
-
-## Publishing a release
-
-### Updating the version number
-
-Before making a release, you need to update the version number. Please adhere to [Semantic Versioning][semver], in brief
-
-> Given a version number MAJOR.MINOR.PATCH, increment the:
->
-> 1.  MAJOR version when you make incompatible API changes,
-> 2.  MINOR version when you add functionality in a backwards compatible manner, and
-> 3.  PATCH version when you make backwards compatible bug fixes.
->
-> Additional labels for pre-release and build metadata are available as extensions to the MAJOR.MINOR.PATCH format.
-
-We use [bump2version][] to automatically update the version number in all places and automatically create a git tag.
-Run one of the following commands in the root of the repository
-
-```bash
-bump2version patch
-bump2version minor
-bump2version major
-```
-
-Once you are done, run
-
-```
-git push --tags
-```
-
-to publish the created tag on GitHub.
+### Continuous integration
 
-[bump2version]: https://github.com/c4urself/bump2version
+Continuous integration will automatically run the tests on all pull requests and test
+against the minimum and maximum supported Python version.
 
-### Building and publishing the package on PyPI
+Additionally, there's a CI job that tests against pre-releases of all dependencies
+(if there are any). The purpose of this check is to detect incompatibilities
+of new package versions early on and gives you time to fix the issue or reach
+out to the developers of the dependency before the package is released to a wider audience.
 
-Python packages are not distributed as source code, but as _distributions_. The most common distribution format is the so-called _wheel_. To build a _wheel_, run
-
-```bash
-python -m build
-```
-
-This command creates a _source archive_ and a _wheel_, which are required for publishing your package to [PyPI][]. These files are created directly in the root of the repository.
-
-Before uploading them to [PyPI][] you can check that your _distribution_ is valid by running:
-
-```bash
-twine check dist/*
-```
-
-and finally publishing it with:
-
-```bash
-twine upload dist/*
-```
-
-Provide your username and password when requested and then go check out your package on [PyPI][]!
+[scanpy-test-docs]: https://scanpy.readthedocs.io/en/latest/dev/testing.html#writing-tests
 
-For more information, follow the [Python packaging tutorial][].
+## Publishing a release
 
-It is possible to automate this with GitHub actions, see also [this feature request][pypi-feature-request]
-in the cookiecutter-scverse template.
+### Updating the version number
 
-[python packaging tutorial]: https://packaging.python.org/en/latest/tutorials/packaging-projects/#generating-distribution-archives
-[pypi-feature-request]: https://github.com/scverse/cookiecutter-scverse/issues/88
+Scirpy uses [hatch-vcs](https://github.com/ofek/hatch-vcs) to automaticlly retrieve the version number
+from the git tag. To make a new release, navigate to the “Releases” page of this project on GitHub. Specify vX.X.X as a tag name and create a release. For more information, see [managing GitHub releases][]. This will automatically create a git tag and trigger a Github workflow that creates a release on PyPI.
 
 ## Writing documentation
 
@@ -195,3 +147,4 @@ open _build/html/index.html
 [numpydoc]: https://numpydoc.readthedocs.io/en/latest/format.html
 [sphinx autodoc typehints]: https://github.com/tox-dev/sphinx-autodoc-typehints
 [pypi]: https://pypi.org/
+[managing GitHub releases]: https://docs.github.com/en/repositories/releasing-projects-on-github/managing-releases-in-a-repository