biocutils 0.3.0__tar.gz → 0.3.1.dev0__tar.gz

biocutils-0.3.1.dev0/.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

biocutils-0.3.1.dev0/.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 }}

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: biocutils
-Version: 0.3.0
+Version: 0.3.1.dev0
 Summary: Utilities to use across the biocpy packages.
 Home-page: https://github.com/biocpy/biocutils
 Author: Aaron Lun

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/__init__.py

@@ -15,13 +15,13 @@ except PackageNotFoundError:  # pragma: no cover
 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 .convert_to_dense import convert_to_dense
 
 from .get_height import get_height
 from .is_high_dimensional import is_high_dimensional
+
+from .bioc_object import BiocObject

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/_utils_combine.py

@@ -26,6 +26,8 @@ def _check_array_dimensions(x, active: int) -> bool:
                     + ")"
                 )
 
+    return True
+
 
 def _coerce_sparse_matrix(first, combined, module):
     if isinstance(first, module.csr_matrix):

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/assign.py

@@ -14,7 +14,8 @@ def assign(x: Any, indices: Sequence[int], replacement: Any) -> Any:
     :py:func:`~biocutils.assign_sequence.assign_sequence` instead.
 
     Args:
-        x: Object to be assignted.
+        x:
+            Object to be assignted.
 
     Returns:
         The object after assignment, typically the same type as ``x``.

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/assign_rows.py

@@ -31,15 +31,15 @@ def assign_rows(x: Any, indices: Sequence[int], replacement: Any) -> Any:
     tmp = [slice(None)] * len(x.shape)
     tmp[0] = indices
     output[(*tmp,)] = replacement
+
     return output
 
 
 @assign_rows.register
-def _assign_rows_numpy(
-    x: numpy.ndarray, indices: Sequence[int], replacement: Any
-) -> numpy.ndarray:
+def _assign_rows_numpy(x: numpy.ndarray, indices: Sequence[int], replacement: Any) -> numpy.ndarray:
     tmp = [slice(None)] * len(x.shape)
     tmp[0] = indices
     output = numpy.copy(x)
     output[(*tmp,)] = replacement
+
     return output

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/assign_sequence.py

@@ -41,18 +41,14 @@ def _assign_sequence_list(x: list, indices: Sequence[int], replacement: Any) ->
 
 
 @assign_sequence.register
-def _assign_sequence_numpy(
-    x: numpy.ndarray, indices: Sequence[int], replacement: Any
-) -> numpy.ndarray:
+def _assign_sequence_numpy(x: numpy.ndarray, indices: Sequence[int], replacement: Any) -> numpy.ndarray:
     output = numpy.copy(x)
     output[indices] = replacement
     return output
 
 
 @assign_sequence.register
-def _assign_sequence_range(
-    x: range, indices: Sequence[int], replacement: Any
-) -> Union[range, list]:
+def _assign_sequence_range(x: range, indices: Sequence[int], replacement: Any) -> Union[range, list]:
     if (
         isinstance(replacement, range)
         and isinstance(indices, range)

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/bioc_object.py

@@ -4,12 +4,7 @@ import copy
 from typing import Any, Dict, Optional, Union
 from warnings import warn
 
-try:
-    from typing import Self
-except ImportError:
-    Self = "BiocObject"
-
-from .NamedList import NamedList
+from .named_list import NamedList
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "jkanche"
@@ -40,22 +35,22 @@ class BiocObject:
     Provides a standardized `metadata` slot and copy-on-write semantics.
     """
 
-    def __init__(self, metadata: Optional[Union[Dict[str, Any], NamedList]] = None, validate: bool = True) -> None:
+    def __init__(self, metadata: Optional[Union[Dict[str, Any], NamedList]] = None, _validate: bool = True) -> None:
         """Initialize the BiocObject.
 
         Args:
             metadata:
                 Additional metadata. Defaults to an empty NamedList.
 
-            validate:
+            _validate:
                 Whether to validate the input. Defaults to True.
         """
-        if validate and metadata is not None:
+        if _validate and metadata is not None:
             _validate_metadata(metadata)
 
         self._metadata = sanitize_metadata(metadata)
 
-    def _define_output(self, in_place: bool = False) -> Self:
+    def _define_output(self, in_place: bool = False) -> BiocObject:
         """Internal utility to handle in-place vs copy-on-modify."""
         if in_place:
             return self
@@ -93,7 +88,7 @@ class BiocObject:
         """Alias for :py:attr:`~metadata` getter."""
         return self.metadata
 
-    def set_metadata(self, metadata: Optional[Union[Dict[str, Any], NamedList]], in_place: bool = False) -> Self:
+    def set_metadata(self, metadata: Optional[Union[Dict[str, Any], NamedList]], in_place: bool = False) -> BiocObject:
         """Set new metadata.
 
         Args:

biocutils-0.3.0/src/biocutils/BooleanList.py → biocutils-0.3.1.dev0/src/biocutils/boolean_list.py

@@ -1,7 +1,9 @@
+from __future__ import annotations
+
 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 +12,27 @@ 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])
 
 
@@ -27,7 +46,7 @@ class BooleanList(NamedList):
 
     def __init__(
         self,
-        data: Optional[Iterable] = None,
+        data: Optional[Sequence] = None,
         names: Optional[Names] = None,
         _validate: bool = True,
     ):
@@ -45,41 +64,34 @@ class BooleanList(NamedList):
             _validate:
                 Internal use only.
         """
-        if _validate:
-            if data is not None:
-                if isinstance(data, BooleanList):
+        if data is not None:
+            if isinstance(data, BooleanList):
+                data = data._data
+            else:
+                if isinstance(data, NamedList):
                     data = data._data
-                else:
-                    if isinstance(data, NamedList):
-                        data = data._data
-                    original = data
-                    data = list(_coerce_to_bool(item) for item in original)
+
+                original = data
+                data = list(_coerce_to_bool(item) for item in original)
+
         super().__init__(data, names, _validate=_validate)
 
-    def set_value(
-        self, index: Union[int, str], value: Any, in_place: bool = False
-    ) -> "BooleanList":
+    def set_value(self, index: Union[int, str], value: Any, in_place: bool = False) -> BooleanList:
         """Calls :py:meth:`~biocutils.NamedList.NamedList.set_value` after coercing ``value`` to a boolean."""
         return super().set_value(index, _coerce_to_bool(value), in_place=in_place)
 
-    def set_slice(
-        self, index: SubscriptTypes, value: Sequence, in_place: bool = False
-    ) -> "BooleanList":
+    def set_slice(self, index: SubscriptTypes, value: Sequence, in_place: bool = False) -> BooleanList:
         """Calls :py:meth:`~biocutils.NamedList.NamedList.set_slice` after coercing ``value`` to booleans."""
         return super().set_slice(index, _SubscriptCoercer(value), in_place=in_place)
 
-    def safe_insert(
-        self, index: Union[int, str], value: Any, in_place: bool = False
-    ) -> "BooleanList":
+    def safe_insert(self, index: Union[int, str], value: Any, in_place: bool = False) -> BooleanList:
         """Calls :py:meth:`~biocutils.NamedList.NamedList.safe_insert` after coercing ``value`` to a boolean."""
         return super().safe_insert(index, _coerce_to_bool(value), in_place=in_place)
 
-    def safe_append(self, value: Any, in_place: bool = False) -> "BooleanList":
+    def safe_append(self, value: Any, in_place: bool = False) -> BooleanList:
         """Calls :py:meth:`~biocutils.NamedList.NamedList.safe_append` after coercing ``value`` to a boolean."""
         return super().safe_append(_coerce_to_bool(value), in_place=in_place)
 
-    def safe_extend(self, other: Iterable, in_place: bool = True) -> "BooleanList":
+    def safe_extend(self, other: Iterable, in_place: bool = False) -> BooleanList:
         """Calls :py:meth:`~biocutils.NamedList.NamedList.safe_extend` after coercing elements of ``other`` to booleans."""
-        return super().safe_extend(
-            (_coerce_to_bool(y) for y in other), in_place=in_place
-        )
+        return super().safe_extend((_coerce_to_bool(y) for y in other), in_place=in_place)

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/combine.py

@@ -5,7 +5,7 @@ from .combine_sequences import combine_sequences
 from .is_high_dimensional import is_high_dimensional
 
 
-def combine(*x: Any):
+def combine(*x: Any) -> Any:
     """
     Generic combine that checks if the objects are n-dimensional for n > 1
     (i.e. has a ``shape`` property of length greater than 1); if so, it calls
@@ -14,7 +14,8 @@ def combine(*x: Any):
     :py:func:`~biocutils.combine_sequences.combine_sequences` instead.
 
     Args:
-        x: Objects to combine.
+        x:
+            Objects to combine.
 
     Returns:
         A combined object, typically the same type as the first element in ``x``.
@@ -28,9 +29,8 @@ def combine(*x: Any):
             has_1d = True
 
     if has_nd and has_1d:
-        raise ValueError(
-            "cannot mix 1-dimensional and higher-dimensional objects in `combine`"
-        )
+        raise ValueError("cannot mix 1-dimensional and higher-dimensional objects in `combine`")
+
     if has_nd:
         return combine_rows(*x)
     else:

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/combine_columns.py

@@ -19,7 +19,7 @@ __license__ = "MIT"
 
 
 @singledispatch
-def combine_columns(*x: Any):
+def combine_columns(*x: Any) -> Any:
     """Combine n-dimensional objects along the second dimension.
 
     If all elements are :py:class:`~numpy.ndarray`,
@@ -40,11 +40,7 @@ def combine_columns(*x: Any):
     Returns:
         Combined object, typically the same type as the first entry of ``x``
     """
-    raise NotImplementedError(
-        "no `combine_columns` method implemented for '"
-        + type(x[0]).__name__
-        + "' objects"
-    )
+    raise NotImplementedError("no `combine_columns` method implemented for '" + type(x[0]).__name__ + "' objects")
 
 
 @combine_columns.register
@@ -57,7 +53,7 @@ def _combine_columns_dense_arrays(*x: numpy.ndarray):
     return numpy.concatenate(x, axis=1)
 
 
-if is_package_installed("scipy") is True:
+if is_package_installed("scipy"):
     import scipy.sparse as sp
 
     def _combine_columns_sparse_matrices(*x):
@@ -85,8 +81,13 @@ if is_package_installed("scipy") is True:
         x = [convert_to_dense(y) for y in x]
         return numpy.concatenate(x, axis=1)
 
+    try:
+        combine_columns.register(sp.sparray, _combine_columns_sparse_arrays)
+    except Exception:
+        pass
+
 
-if is_package_installed("pandas") is True:
+if is_package_installed("pandas"):
     from pandas import DataFrame, concat
 
     @combine_columns.register(DataFrame)

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/combine_rows.py

@@ -19,7 +19,7 @@ __license__ = "MIT"
 
 
 @singledispatch
-def combine_rows(*x: Any):
+def combine_rows(*x: Any) -> Any:
     """Combine n-dimensional objects along their first dimension.
 
     If all elements are :py:class:`~numpy.ndarray`, we combine them using
@@ -40,9 +40,7 @@ def combine_rows(*x: Any):
     Returns:
         Combined object, typically the same type as the first entry of ``x``.
     """
-    raise NotImplementedError(
-        "no `combine_rows` method implemented for '" + type(x[0]).__name__ + "' objects"
-    )
+    raise NotImplementedError("no `combine_rows` method implemented for '" + type(x[0]).__name__ + "' objects")
 
 
 @combine_rows.register(numpy.ndarray)
@@ -69,7 +67,7 @@ if is_package_installed("scipy"):
         return numpy.concatenate(x)
 
     try:
-        combine_rows.register(sp.sparray, _combine_rows_sparse_arrays)
+        combine_rows.register(sp.spmatrix, _combine_rows_sparse_matrices)
     except Exception:
         pass
 
@@ -77,14 +75,14 @@ if is_package_installed("scipy"):
         _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]
         return numpy.concatenate(x)
 
     try:
-        combine_rows.register(sp.spmatrix, _combine_rows_sparse_matrices)
+        combine_rows.register(sp.sparray, _combine_rows_sparse_arrays)
     except Exception:
         pass
 

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/combine_sequences.py

@@ -13,7 +13,7 @@ __license__ = "MIT"
 
 
 @singledispatch
-def combine_sequences(*x: Any):
+def combine_sequences(*x: Any) -> Any:
     """Combine vector-like objects (1-dimensional arrays).
 
     If all elements are :py:class:`~numpy.ndarray`,
@@ -34,11 +34,7 @@ def combine_sequences(*x: Any):
     Returns:
         A combined object, ideally of the same type as the first element in ``x``.
     """
-    raise NotImplementedError(
-        "no `combine_sequences` method implemented for '"
-        + type(x[0]).__name__
-        + "' objects"
-    )
+    raise NotImplementedError("no `combine_sequences` method implemented for '" + type(x[0]).__name__ + "' objects")
 
 
 @combine_sequences.register(list)
@@ -51,6 +47,7 @@ def _combine_sequences_dense_arrays(*x: numpy.ndarray):
     for y in x:
         if numpy.ma.is_masked(y):
             return numpy.ma.concatenate(x, axis=None)
+
     return numpy.concatenate(x, axis=None)
 
 
@@ -85,6 +82,7 @@ def _combine_sequences_ranges(*x: range):
 
     if not failed:
         return range(start, stop, step)
+
     return list(chain(*x))
 
 
@@ -101,4 +99,5 @@ if is_package_installed("pandas") is True:
                 else:
                     elems.append(elem)
             x = elems
+
         return concat(x)

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/convert_to_dense.py

@@ -15,7 +15,8 @@ def convert_to_dense(x: Any) -> numpy.ndarray:
     ``numpy.concatenate`` doesn't understand.
 
     Args:
-        x: Some array-like object to be stored as a NumPy array.
+        x:
+            Some array-like object to be stored as a NumPy array.
 
     Returns:
         A NumPy array.

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/extract_column_names.py

@@ -11,11 +11,12 @@ __license__ = "MIT"
 
 
 @singledispatch
-def extract_column_names(x: Any) -> numpy.ndarray:
+def extract_column_names(x: Any) -> Any:
     """Access column names from 2-dimensional representations.
 
     Args:
-        x: Any object.
+        x:
+            Any object with column names.
 
     Returns:
         Array of strings containing column names.
@@ -27,5 +28,5 @@ if is_package_installed("pandas") is True:
     from pandas import DataFrame
 
     @extract_column_names.register(DataFrame)
-    def _colnames_dataframe(x: DataFrame) -> list:
+    def _colnames_dataframe(x):
         return numpy.array(x.columns, dtype=str)

{biocutils-0.3.0 → biocutils-0.3.1.dev0}/src/biocutils/extract_row_names.py

@@ -11,11 +11,11 @@ __license__ = "MIT"
 
 
 @singledispatch
-def extract_row_names(x: Any) -> numpy.ndarray:
+def extract_row_names(x: Any) -> Any:
     """Access row names from 2-dimensional representations.
 
     Args:
-        x: Any object.
+        x: Any object with row names.
 
     Returns:
         Array of strings containing row names.
@@ -27,5 +27,5 @@ if is_package_installed("pandas") is True:
     from pandas import DataFrame
 
     @extract_row_names.register(DataFrame)
-    def _rownames_dataframe(x: DataFrame) -> list:
+    def _rownames_dataframe(x):
         return numpy.array(x.index, dtype=str)