bio2zarr 0.0.9__tar.gz → 0.1.0__tar.gz

bio2zarr-0.1.0/.github/workflows/cd.yml

@@ -0,0 +1,86 @@
+name: CD
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - '*'
+  release:
+    types: [published]
+
+jobs:
+  packaging:
+    if: github.repository_owner == 'sgkit-dev'
+    name: Packaging
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.9'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install build twine validate-pyproject[all]
+      - name: Check and install package
+        run: |
+          validate-pyproject pyproject.toml
+          python -m build
+          python -m twine check --strict dist/*
+          python -m pip install dist/*.whl
+      - name: Check vcf2zarr CLI
+        run: |
+          vcf2zarr --help
+          python -m bio2zarr vcf2zarr --help
+      - name: Check vcfpartition CLI
+        run: |
+          vcfpartition --help
+          python -m bio2zarr vcfpartition --help
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    if: github.repository_owner == 'sgkit-dev' && github.event_name == 'release'
+    needs:
+      - packaging
+    runs-on: ubuntu-latest
+
+    environment:
+      name: pypi
+      url: https://pypi.org/p/bio2zarr
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - uses: pypa/gh-action-pypi-publish@release/v1
+
+
+  publish-to-testpypi:
+    if: github.repository_owner == 'sgkit-dev' && github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags')
+    needs:
+      - packaging
+    runs-on: ubuntu-latest
+
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/bio2zarr
+
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        repository-url: https://test.pypi.org/legacy/

bio2zarr-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,107 @@
+name: CI
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+jobs:
+  pre-commit:
+    name: Lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - uses: pre-commit/action@v3.0.1
+  test:
+    name: Test
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        # Use macos-13 because pip binary packages for ARM aren't
+        # available for many dependencies
+        os: [macos-13, macos-14, ubuntu-latest]
+        python-version: ["3.9", "3.10", "3.11"]
+        exclude:
+          # Just run macos tests on one Python version
+          - os: macos-13
+            python-version: "3.10"
+          - os: macos-13
+            python-version: "3.11"
+          - os: macos-14
+            python-version: "3.9"
+          - os: macos-14
+            python-version: "3.10"
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install '.[dev]'
+      - name: Run basic vcf2zarr example
+        run: |
+          python -m bio2zarr vcf2zarr convert tests/data/vcf/sample.vcf.gz sample.vcz -f
+      - name: Run two-pass vcf2zarr example
+        run: |
+          python -m bio2zarr vcf2zarr explode tests/data/vcf/sample.vcf.gz sample.icf -f
+          python -m bio2zarr vcf2zarr encode sample.icf sample.vcz -f
+      - name: Run distributed explode example
+        run: |
+          python -m bio2zarr vcf2zarr dexplode-init tests/data/vcf/sample.vcf.gz sample.icf -fn 3
+          python -m bio2zarr vcf2zarr dexplode-partition sample.icf 0
+          python -m bio2zarr vcf2zarr dexplode-partition sample.icf 1
+          python -m bio2zarr vcf2zarr dexplode-partition sample.icf 2
+          python -m bio2zarr vcf2zarr dexplode-finalise sample.icf
+      - name: Run distributed encode example
+        run: |
+          python -m bio2zarr vcf2zarr dencode-init sample.icf sample.vcz -fn 3 --variants-chunk-size=3
+          python -m bio2zarr vcf2zarr dencode-partition sample.vcz 0
+          python -m bio2zarr vcf2zarr dencode-partition sample.vcz 1
+          python -m bio2zarr vcf2zarr dencode-partition sample.vcz 2
+          python -m bio2zarr vcf2zarr dencode-finalise sample.vcz
+      - name: Run tests
+        run: |
+          pytest --cov=bio2zarr
+      - name: Upload coverage to Coveralls
+        uses: coverallsapp/github-action@v2.3.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          # The first coveralls upload will succeed and others seem to fail now.
+          # This is a quick workaround for doing a proper "parallel" setup:
+          # https://github.com/coverallsapp/github-action
+          fail-on-error: false
+
+  packaging:
+    name: Packaging
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install build twine validate-pyproject[all]
+      - name: Check and install package
+        run: |
+          validate-pyproject pyproject.toml
+          python -m build
+          python -m twine check --strict dist/*
+          python -m pip install dist/*.whl
+      - name: Check vcf2zarr CLI
+        run: |
+          vcf2zarr --help
+          python -m bio2zarr vcf2zarr --help
+      - name: Check vcfpartition CLI
+        run: |
+          vcfpartition --help
+          python -m bio2zarr vcfpartition --help
+

{bio2zarr-0.0.9 → bio2zarr-0.1.0}/.github/workflows/docs.yml

@@ -1,15 +1,16 @@
-name: Build Docs
+name: Docs
 
 on:
   pull_request:
   push:
-    branches: [main, test]
+    branches:
+      - main
     tags:
       - '*'
 
 jobs:
   build-docs:
-    name: Docs
+    name: Build
     runs-on: ubuntu-latest
     steps:
       - name: Cancel Previous Runs
@@ -28,6 +29,15 @@ jobs:
         run: |
           pip install --upgrade pip wheel
           pip install -r docs/requirements.txt
+          python3 -m bash_kernel.install
+
+      - name: Install bcftools
+        run: |
+          sudo apt-get install bcftools jq
+
+      - name: Install package
+        run: |
+          python3 -m pip install .
 
       - name: Build Docs
         run: |

{bio2zarr-0.0.9 → bio2zarr-0.1.0}/CHANGELOG.md

@@ -1,3 +1,14 @@
+# 0.1.0 2024-06-10
+
+- Initial production-ready version.
+- Add -Q/--no-progress flag to CLI
+- Change num-partitions argument in dexplode-init and dencode-init
+  to a named option.
+
+# 0.0.10 2024-05-15
+- Change output format of dexplode-init and dencode-init
+- Bugfix for mac progress, and change of multiprocessing startup strategy.
+
 # 0.0.9 2024-05-02
 
 - Change on-disk format for explode and schema

{bio2zarr-0.0.9 → bio2zarr-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bio2zarr
-Version: 0.0.9
+Version: 0.1.0
 Summary: Convert bioinformatics data to Zarr
 Author-email: sgkit Developers <project@sgkit.dev>
 License:                                  Apache License
@@ -206,10 +206,13 @@ License:                                  Apache License
            limitations under the License.
         
 Project-URL: repository, https://github.com/sgkit-dev/bio2zarr
-Project-URL: documentation, https://sgkit-dev.github.io/bio2zarr/intro.html
-Classifier: Development Status :: 3 - Alpha
+Project-URL: documentation, https://sgkit-dev.github.io/bio2zarr/
+Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Intended Audience :: Science/Research
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
@@ -238,126 +241,10 @@ Requires-Dist: sgkit>=0.8.0; extra == "dev"
 Requires-Dist: tqdm; extra == "dev"
 
 [![CI](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml)
+[![Coverage Status](https://coveralls.io/repos/github/sgkit-dev/bio2zarr/badge.svg)](https://coveralls.io/github/sgkit-dev/bio2zarr)
+
 
 # bio2zarr
 Convert bioinformatics file formats to Zarr
 
-Initially supports converting VCF to the
-[sgkit vcf-zarr specification](https://github.com/pystatgen/vcf-zarr-spec/)
-
-**This is early alpha-status code: everything is subject to change,
-and it has not been thoroughly tested**
-
-## Install
-
-```
-$ python3 -m pip install bio2zarr
-```
-
-This will install the programs ``vcf2zarr``, ``plink2zarr`` and ``vcf_partition``
-into your local Python path. You may need to update your $PATH to call the 
-executables directly.
-
-Alternatively, calling 
-```
-$ python3 -m bio2zarr vcf2zarr <args>
-```
-is equivalent to 
-
-```
-$ vcf2zarr <args>
-```
-and will always work.
-
-
-## vcf2zarr
-
-
-Convert a VCF to zarr format:
-
-```
-$ vcf2zarr convert <VCF1> <VCF2> <zarr>
-```
-
-Converts the VCF to zarr format.
-
-**Do not use this for anything but the smallest files**
-
-The recommended approach is to use a multi-stage conversion
-
-First, convert the VCF into the intermediate format:
-
-```
-vcf2zarr explode tests/data/vcf/sample.vcf.gz tmp/sample.exploded
-```
-
-Then, (optionally) inspect this representation to get a feel for your dataset
-```
-vcf2zarr inspect tmp/sample.exploded
-```
-
-Then, (optionally) generate a conversion schema to describe the corresponding
-Zarr arrays:
-
-```
-vcf2zarr mkschema tmp/sample.exploded > sample.schema.json
-```
-
-View and edit the schema, deleting any columns you don't want, or tweaking 
-dtypes and compression settings to your taste.
-
-Finally, encode to Zarr:
-```
-vcf2zarr encode tmp/sample.exploded tmp/sample.zarr -s sample.schema.json
-```
-
-Use the ``-p, --worker-processes`` argument to control the number of workers used
-in the ``explode`` and ``encode`` phases.
-
-### Shell completion
-
-To enable shell completion for a particular session in Bash do:
-
-```
-eval "$(_VCF2ZARR_COMPLETE=bash_source vcf2zarr)" 
-```
-
-If you add this to your ``.bashrc`` vcf2zarr shell completion should available
-in all new shell sessions.
-
-See the [Click documentation](https://click.palletsprojects.com/en/8.1.x/shell-completion/#enabling-completion)
-for instructions on how to enable completion in other shells.
-a
-
-## plink2zarr
-
-Convert a plink ``.bed`` file to zarr format. **This is incomplete**
-
-## vcf_partition
-
-Partition a given VCF file into (approximately) a give number of regions:
-
-```
-vcf_partition 20201028_CCDG_14151_B01_GRM_WGS_2020-08-05_chr20.recalibrated_variants.vcf.gz -n 10
-```
-gives
-```
-chr20:1-6799360
-chr20:6799361-14319616
-chr20:14319617-21790720
-chr20:21790721-28770304
-chr20:28770305-31096832
-chr20:31096833-38043648
-chr20:38043649-45580288
-chr20:45580289-52117504
-chr20:52117505-58834944
-chr20:58834945-
-```
-
-These reqion strings can then be used to split computation of the VCF 
-into chunks for parallelisation.
-
-**TODO give a nice example here using xargs**
-
-**WARNING that this does not take into account that indels may overlap 
-partitions and you may count variants twice or more if they do**
+See the [documentation](https://sgkit-dev.github.io/bio2zarr/) for details.

bio2zarr-0.1.0/README.md

@@ -0,0 +1,8 @@
+[![CI](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/sgkit-dev/bio2zarr/actions/workflows/ci.yml)
+[![Coverage Status](https://coveralls.io/repos/github/sgkit-dev/bio2zarr/badge.svg)](https://coveralls.io/github/sgkit-dev/bio2zarr)
+
+
+# bio2zarr
+Convert bioinformatics file formats to Zarr
+
+See the [documentation](https://sgkit-dev.github.io/bio2zarr/) for details.

{bio2zarr-0.0.9 → bio2zarr-0.1.0}/bio2zarr/__main__.py

@@ -14,9 +14,9 @@ def bio2zarr():
 # install individual commands as console scripts. However, this
 # is handy for development and for those whose PATHs aren't set
 # up in the right way.
-bio2zarr.add_command(cli.vcf2zarr)
+bio2zarr.add_command(cli.vcf2zarr_main)
 bio2zarr.add_command(cli.plink2zarr)
-bio2zarr.add_command(cli.vcf_partition)
+bio2zarr.add_command(cli.vcfpartition)
 
 if __name__ == "__main__":
     bio2zarr()

{bio2zarr-0.0.9 → bio2zarr-0.1.0}/bio2zarr/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.9'
-__version_tuple__ = version_tuple = (0, 0, 9)
+__version__ = version = '0.1.0'
+__version_tuple__ = version_tuple = (0, 1, 0)