Merge branch 'master' into pre-commit-ci-update-config

Author: jkanche

.github/workflows/pypi-publish.yml

@@ -12,12 +12,12 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.9
+          python-version: 3.11
 
       # build SQLite from source, because I need 3.35<=
       - name: Download SQLite3

.github/workflows/pypi-test.yml

@@ -11,13 +11,13 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: [ "3.9", "3.10", "3.11", "3.12" ]
 
     name: Python ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Setup Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
           cache: "pip"

.pre-commit-config.yaml

@@ -17,26 +17,27 @@ repos:
   - id: mixed-line-ending
     args: ['--fix=auto']  # replace 'auto' with 'lf' to enforce Linux/Mac line endings or 'crlf' for Windows
 
-- repo: https://github.com/PyCQA/docformatter
-  rev: v1.7.5
-  hooks:
-    - id: docformatter
-      additional_dependencies: [tomli]
-      args: [--in-place, --wrap-descriptions=120, --wrap-summaries=120]
-      # --config, ./pyproject.toml
+# - repo: https://github.com/PyCQA/docformatter
+#   rev: master
+#   hooks:
+#     - id: docformatter
+#       additional_dependencies: [tomli]
+#       args: [--in-place, --wrap-descriptions=120, --wrap-summaries=120]
+#       # --config, ./pyproject.toml
 
-- repo: https://github.com/psf/black
-  rev: 24.10.0
-  hooks:
-  - id: black
-    language_version: python3
+# - repo: https://github.com/psf/black
+#   rev: 24.8.0
+#   hooks:
+#   - id: black
+#     language_version: python3
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
   rev: v0.8.2
   hooks:
     - id: ruff
       args: [--fix, --exit-non-zero-on-fix]
+    - id: ruff-format
 
 ## If like to embrace black styles even in the docs:
 # - repo: https://github.com/asottile/blacken-docs

CHANGELOG.md

@@ -1,7 +1,10 @@
 # Changelog
 
-## Version 0.1 (development)
+## Version 0.2.0
 
-- Feature A added
-- FIX: nasty bug #1729 fixed
-- add your changes here!
+- chore: Remove Python 3.8 (EOL)
+- precommit: Replace docformatter with ruff's formatter
+
+## Version 0.1.0
+
+- Initial version of the package.

README.md

@@ -15,10 +15,10 @@
 # celldex - reference cell type datasets
 
 This package provides reference datasets with annotated cell types for convenient use by [BiocPy](https://github.com/biocpy) packages and workflows in Python.
-These references were sourced and uploaded by the [celldex R/Bioconductor](https://bioconductor.org/packages/devel/data/experiment/html/celldex.html) package.
-
-Each dataset is loaded as a [`SummarizedExperiment`](https://bioconductor.org/packages/SummarizedExperiment) that is ready for further analysis, and may be used for downstream analysis, e.g in the [SingleR Python implementation](https://github.com/BiocPy/singler).
+These references were sourced and uploaded by the [**celldex** R/Bioconductor](https://bioconductor.org/packages/celldex) package.
 
+Each dataset is loaded as a [`SummarizedExperiment`](https://bioconductor.org/packages/SummarizedExperiment) that is ready for further analysis, and may be used for downstream analysis,
+e.g in the [SingleR Python implementation](https://github.com/SingleR-inc/singler).
 
 ## Installation
 

docs/conf.py

@@ -72,6 +72,7 @@
     "sphinx.ext.ifconfig",
     "sphinx.ext.mathjax",
     "sphinx.ext.napoleon",
+    "sphinx_autodoc_typehints",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
@@ -166,6 +167,14 @@
 # If this is True, todo emits a warning for each TODO entries. The default is False.
 todo_emit_warnings = True
 
+autodoc_default_options = {
+      'special-members': True,
+      'undoc-members': False,
+      'exclude-members': '__weakref__, __dict__, __str__, __module__, __init__'
+  }
+
+autosummary_generate = True
+autosummary_imported_members = True
 
 # -- Options for HTML output -------------------------------------------------
 

setup.cfg

@@ -12,10 +12,10 @@ license = MIT
 license_files = LICENSE.txt
 long_description = file: README.md
 long_description_content_type = text/markdown; charset=UTF-8; variant=GFM
-url = https://github.com/biocpy/celldex
+url = https://github.com/SingleR-inc/celldex
 # Add here related links, for example:
 project_urls =
-    Documentation = https://github.com/biocpy/celldex
+    Documentation = https://github.com/SingleR-inc/celldex
 #    Source = https://github.com/pyscaffold/pyscaffold/
 #    Changelog = https://pyscaffold.org/en/latest/changelog.html
 #    Tracker = https://github.com/pyscaffold/pyscaffold/issues
@@ -41,7 +41,7 @@ package_dir =
     =src
 
 # Require a min/specific Python version (comma-separated conditions)
-python_requires = >=3.8
+python_requires = >=3.9
 
 # Add here dependencies of your project (line-separated), e.g. requests>=2.2,<3.0.
 # Version specifiers like >=2.2,<3.0 avoid problems due to API changes in

src/celldex/fetch_reference.py

@@ -81,12 +81,8 @@ def fetch_reference(
         or one of its subclasses.
     """
 
-    version_path = save_version(
-        package, name, version, cache_dir=cache_dir, overwrite=overwrite
-    )
-    obj_path = (
-        version_path if path is None else os.path.join(version_path, path.rstrip("/"))
-    )
+    version_path = save_version(package, name, version, cache_dir=cache_dir, overwrite=overwrite)
+    obj_path = version_path if path is None else os.path.join(version_path, path.rstrip("/"))
 
     old = alt_read_object_function(celldex_load_object)
 
@@ -147,9 +143,7 @@ def fetch_metadata(
         Dictionary containing metadata for the specified dataset.
     """
     remote_path = "_bioconductor.json" if path is None else f"{path}/_bioconductor.json"
-    local_path = save_file(
-        package, name, version, remote_path, cache_dir=cache_dir, overwrite=overwrite
-    )
+    local_path = save_file(package, name, version, remote_path, cache_dir=cache_dir, overwrite=overwrite)
 
     with open(local_path, "r") as f:
         metadata = json.load(f)

src/celldex/list_references.py

@@ -14,9 +14,7 @@
 
 
 @lru_cache
-def list_references(
-    cache_dir: str = cache_directory(), overwrite: bool = False, latest: bool = True
-) -> pd.DataFrame:
+def list_references(cache_dir: str = cache_directory(), overwrite: bool = False, latest: bool = True) -> pd.DataFrame:
     """List all available reference datasets.
 
     Example:
@@ -83,9 +81,7 @@ def _format_query_results(results: list, key_names: list):
 
 
 def _sanitize_query_to_output(results: list, latest: bool, meta_name: str = "meta"):
-    _all_paths = [
-        None if "/" not in p else p.rsplit("/", 1)[0] for p in results["path"]
-    ]
+    _all_paths = [None if "/" not in p else p.rsplit("/", 1)[0] for p in results["path"]]
 
     df = pd.DataFrame(
         {
@@ -105,33 +101,22 @@ def _sanitize_query_to_output(results: list, latest: bool, meta_name: str = "met
     )
     df["title"] = _extract_atomic_from_json(_all_metas, lambda x: x.get("title"))
     df["description"] = _extract_atomic_from_json(_all_metas, lambda x: x.get("title"))
-    df["taxonomy_id"] = _extract_charlist_from_json(
-        _all_metas, lambda x: x.get("taxonomy_id")
-    )
+    df["taxonomy_id"] = _extract_charlist_from_json(_all_metas, lambda x: x.get("taxonomy_id"))
     df["genome"] = _extract_charlist_from_json(_all_metas, lambda x: x.get("genome"))
 
     df["rows"] = _extract_atomic_from_json(
         _all_metas,
-        lambda x: x.get("applications", {})
-        .get("takane", {})
-        .get("summarized_experiment", {})
-        .get("rows"),
+        lambda x: x.get("applications", {}).get("takane", {}).get("summarized_experiment", {}).get("rows"),
     )
 
     df["columns"] = _extract_atomic_from_json(
         _all_metas,
-        lambda x: x.get("applications", {})
-        .get("takane", {})
-        .get("summarized_experiment", {})
-        .get("columns"),
+        lambda x: x.get("applications", {}).get("takane", {}).get("summarized_experiment", {}).get("columns"),
     )
 
     df["assays"] = _extract_charlist_from_json(
         _all_metas,
-        lambda x: x.get("applications", {})
-        .get("takane", {})
-        .get("summarized_experiment", {})
-        .get("assays"),
+        lambda x: x.get("applications", {}).get("takane", {}).get("summarized_experiment", {}).get("assays"),
     )
     df["column_annotations"] = _extract_charlist_from_json(
         _all_metas,
@@ -155,15 +140,9 @@ def _sanitize_query_to_output(results: list, latest: bool, meta_name: str = "met
         .get("alternative_experiments"),
     )
 
-    df["bioconductor_version"] = _extract_atomic_from_json(
-        _all_metas, lambda x: x.get("bioconductor_version")
-    )
-    df["maintainer_name"] = _extract_atomic_from_json(
-        _all_metas, lambda x: x.get("maintainer_name")
-    )
-    df["maintainer_email"] = _extract_atomic_from_json(
-        _all_metas, lambda x: x.get("maintainer_email")
-    )
+    df["bioconductor_version"] = _extract_atomic_from_json(_all_metas, lambda x: x.get("bioconductor_version"))
+    df["maintainer_name"] = _extract_atomic_from_json(_all_metas, lambda x: x.get("maintainer_name"))
+    df["maintainer_email"] = _extract_atomic_from_json(_all_metas, lambda x: x.get("maintainer_email"))
 
     sources = []
     for meta in _all_metas:
@@ -186,9 +165,7 @@ def _sanitize_query_to_output(results: list, latest: bool, meta_name: str = "met
 
 
 def _extract_atomic_from_json(metadata, extract):
-    return [
-        extract(_meta) if extract(_meta) is not None else None for _meta in metadata
-    ]
+    return [extract(_meta) if extract(_meta) is not None else None for _meta in metadata]
 
 
 def _extract_charlist_from_json(metadata, extract):

src/celldex/save_reference.py

@@ -91,9 +91,7 @@ def save_reference(x: Any, labels: List[str], path: str, metadata: dict):
             # Save the reference
             celldex.save_reference(sce, cache_dir, meta)
     """
-    raise NotImplementedError(
-        f"'save_dataset' is not supported for objects of class: {type(x)}"
-    )
+    raise NotImplementedError(f"'save_dataset' is not supported for objects of class: {type(x)}")
 
 
 def _save_se(x: SummarizedExperiment, path, metadata):
@@ -112,9 +110,7 @@ def _save_se(x: SummarizedExperiment, path, metadata):
     for _cn in _cols.get_column_names():
         _data = _cols.get_column(_cn)
         if not all(isinstance(y, str) for y in _data):
-            raise ValueError(
-                f"All labels in 'column_data' must be a list of strings; column {_cn} does not."
-            )
+            raise ValueError(f"All labels in 'column_data' must be a list of strings; column {_cn} does not.")
 
     if "logcounts" not in list(x.get_assay_names()):
         raise ValueError("Assay 'logcounts' does not exist.")