Improvements to package workflow and documentation

.github/workflows/publish-pypi.yml

@@ -0,0 +1,52 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags: "*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      repository-projects: write
+      contents: write
+      pages: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox
+
+      - name: Test with tox
+        run: |
+          tox
+
+      - name: Build Project and Publish
+        run: |
+          python -m tox -e clean,build
+
+      # This uses the trusted publisher workflow so no token is required.
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Build docs
+        run: |
+          tox -e docs
+
+      - run: touch ./docs/_build/html/.nojekyll
+
+      - name: GH Pages Deployment
+        uses: JamesIves/github-pages-deploy-action@v4
+        with:
+          branch: gh-pages # The branch the action should deploy to.
+          folder: ./docs/_build/html
+          clean: true # Automatically remove deleted files from the deploy branch

.github/workflows/run-tests.yml

@@ -0,0 +1,73 @@
+name: Test the library
+
+on:
+  push:
+    branches:
+      - master # for legacy repos
+      - main
+  pull_request:
+    branches:
+      - master # for legacy repos
+      - main
+  workflow_dispatch: # Allow manually triggering the workflow
+  schedule:
+    # Run roughly every 15 days at 00:00 UTC
+    # (useful to check if updates on dependencies break the package)
+    - cron: "0 0 1,16 * *"
+
+permissions:
+  contents: read
+
+concurrency:
+  group: >-
+    ${{ github.workflow }}-${{ github.ref_type }}-
+    ${{ github.event.pull_request.number || github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    strategy:
+      matrix:
+        python: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+        platform:
+          - ubuntu-latest
+          - macos-latest
+          - windows-latest
+    runs-on: ${{ matrix.platform }}
+    name: Python ${{ matrix.python }}, ${{ matrix.platform }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        id: setup-python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox coverage
+
+      - name: Run tests
+        run: >-
+          pipx run --python '${{ steps.setup-python.outputs.python-path }}'
+          tox
+          -- -rFEx --durations 10 --color yes --cov --cov-branch --cov-report=xml  # pytest args
+
+      - name: Check for codecov token availability
+        id: codecov-check
+        shell: bash
+        run: |
+          if [ ${{ secrets.CODECOV_TOKEN }} != '' ]; then
+            echo "codecov=true" >> $GITHUB_OUTPUT;
+          else
+            echo "codecov=false" >> $GITHUB_OUTPUT;
+          fi
+
+      - name: Upload coverage reports to Codecov with GitHub Action
+        uses: codecov/codecov-action@v5
+        if: ${{ steps.codecov-check.outputs.codecov == 'true' }}
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+          slug: ${{ github.repository }}
+          flags: ${{ matrix.platform }} - py${{ matrix.python }}

src/biocutils/__init__.py

@@ -15,13 +15,13 @@
 finally:
     del version, PackageNotFoundError
 
-from .Factor import Factor
-from .StringList import StringList
-from .IntegerList import IntegerList
-from .FloatList import FloatList
-from .BooleanList import BooleanList
-from .Names import Names
-from .NamedList import NamedList
+from .factor import Factor
+from .string_list import StringList
+from .integer_list import IntegerList
+from .float_list import FloatList
+from .boolean_list import BooleanList
+from .names import Names
+from .named_list import NamedList
 
 from .factorize import factorize
 from .intersect import intersect
@@ -60,3 +60,5 @@
 
 from .get_height import get_height
 from .is_high_dimensional import is_high_dimensional
+
+from .bioc_object import BiocObject

src/biocutils/bioc_object.py

@@ -9,7 +9,7 @@
 except ImportError:
     Self = "BiocObject"
 
-from .NamedList import NamedList
+from .named_list import NamedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "jkanche"

src/biocutils/BooleanList.py → src/biocutils/boolean_list.py

@@ -1,7 +1,7 @@
 from typing import Any, Iterable, Optional, Sequence, Union
 
-from .NamedList import NamedList
-from .Names import Names
+from .named_list import NamedList
+from .names import Names
 from .normalize_subscript import SubscriptTypes
 
 
@@ -10,10 +10,25 @@ def _coerce_to_bool(x: Any):
 
 
 class _SubscriptCoercer:
-    def __init__(self, data):
+    """Coercer for subscript operations on BooleanList."""
+
+    def __init__(self, data: Sequence) -> None:
+        """Initialize the coercer.
+
+        Args:
+            data: Sequence of values to coerce.
+        """
         self._data = data
 
-    def __getitem__(self, index):
+    def __getitem__(self, index: int) -> Optional[bool]:
+        """Get an item and coerce it to boolean.
+
+        Args:
+            index: Index of the item.
+
+        Returns:
+            Coerced boolean value.
+        """
         return _coerce_to_bool(self._data[index])
 
 

src/biocutils/combine_rows.py

@@ -77,7 +77,7 @@ def _combine_rows_sparse_arrays(*x):
         _check_array_dimensions(x, 0)
         if is_list_of_type(x, sp.sparray):
             combined = sp.vstack(x)
-            return _coerce_sparse_array(first, combined, sp)
+            return _coerce_sparse_array(x[0], combined, sp)
 
         warn("not all elements are SciPy sparse arrays")
         x = [convert_to_dense(y) for y in x]

src/biocutils/extract_column_names.py

@@ -15,7 +15,7 @@ def extract_column_names(x: Any) -> numpy.ndarray:
     """Access column names from 2-dimensional representations.
 
     Args:
-        x: Any object.
+        x: Any object with column names.
 
     Returns:
         Array of strings containing column names.

src/biocutils/extract_row_names.py

@@ -15,7 +15,7 @@ def extract_row_names(x: Any) -> numpy.ndarray:
     """Access row names from 2-dimensional representations.
 
     Args:
-        x: Any object.
+        x: Any object with row names.
 
     Returns:
         Array of strings containing row names.

src/biocutils/Factor.py → src/biocutils/factor.py

@@ -10,14 +10,14 @@
 from .is_list_of_type import is_list_of_type
 from .is_missing_scalar import is_missing_scalar
 from .match import match
-from .Names import Names, _combine_names, _name_to_position, _sanitize_names
+from .names import Names, _combine_names, _name_to_position, _sanitize_names
 from .normalize_subscript import (
     NormalizedSubscript,
     SubscriptTypes,
     normalize_subscript,
 )
 from .print_truncated import print_truncated_list
-from .StringList import StringList
+from .string_list import StringList
 from .subset_sequence import subset_sequence
 
 

src/biocutils/FloatList.py → src/biocutils/float_list.py

@@ -1,7 +1,7 @@
 from typing import Any, Iterable, Optional, Sequence, Union
 
-from .NamedList import NamedList
-from .Names import Names
+from .named_list import NamedList
+from .names import Names
 from .normalize_subscript import SubscriptTypes
 
 
@@ -15,10 +15,25 @@ def _coerce_to_float(x: Any):
 
 
 class _SubscriptCoercer:
-    def __init__(self, data):
+    """Coercer for subscript operations on FloatList."""
+
+    def __init__(self, data: Sequence) -> None:
+        """Initialize the coercer.
+
+        Args:
+            data: Sequence of values to coerce.
+        """
         self._data = data
 
-    def __getitem__(self, index):
+    def __getitem__(self, index: int) -> Optional[float]:
+        """Get an item and coerce it to float.
+
+        Args:
+            index: Index of the item.
+
+        Returns:
+            Coerced float value.
+        """
         return _coerce_to_float(self._data[index])