Merge branch 'main' into enhancement/issue-742

.github/pull_request_template.md

@@ -4,10 +4,10 @@
 
 <!-- Please fill in the appropriate checklist below (delete whatever is not relevant). These are the most common things requested on pull requests (PRs). -->
 
--   [ ] This comment contains a description of changes (with reason)
--   [ ] Referenced issue is linked
--   [ ] If you've fixed a bug or added code that should be tested, add tests!
--   [ ] Documentation in `docs` is updated
+- [ ] This comment contains a description of changes (with reason)
+- [ ] Referenced issue is linked
+- [ ] If you've fixed a bug or added code that should be tested, add tests!
+- [ ] Documentation in `docs` is updated
 
 **Description of changes**
 

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.11.0 🌈"
-tag-template: 0.11.0
+name-template: "0.12.0 🌈"
+tag-template: 0.12.0
 exclude-labels:
     - "skip-changelog"
 

.github/workflows/run_notebooks.yml

@@ -1,7 +1,6 @@
 name: Run Notebooks
 
 on:
-    - push
     - pull_request
 
 jobs:

.pre-commit-config.yaml

@@ -6,12 +6,12 @@ default_stages:
     - pre-push
 minimum_pre_commit_version: 2.16.0
 repos:
-    - repo: https://github.com/pre-commit/mirrors-prettier
-      rev: v4.0.0-alpha.8
+    - repo: https://github.com/rbubley/mirrors-prettier
+      rev: v3.4.2
       hooks:
           - id: prettier
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.8.2
+      rev: v0.9.1
       hooks:
           - id: ruff
             args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
@@ -27,7 +27,7 @@ repos:
           - id: trailing-whitespace
           - id: check-case-conflict
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.13.0
+      rev: v1.14.1
       hooks:
           - id: mypy
             args: [--no-strict-optional, --ignore-missing-imports]

CODE_OF_CONDUCT.md

@@ -14,23 +14,23 @@ religion, or sexual identity and orientation.
 Examples of behavior that contributes to creating a positive environment
 include:
 
--   Using welcoming and inclusive language
--   Being respectful of differing viewpoints and experiences
--   Gracefully accepting constructive criticism
--   Focusing on what is best for the community
--   Showing empathy towards other community members
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
 
 Examples of unacceptable behavior by participants include:
 
--   The use of sexualized language or imagery and unwelcome sexual
-    attention or advances
--   Trolling, insulting/derogatory comments, and personal or political
-    attacks
--   Public or private harassment
--   Publishing others’ private information, such as a physical or
-    electronic address, without explicit permission
--   Other conduct which could reasonably be considered inappropriate in a
-    professional setting
+- The use of sexualized language or imagery and unwelcome sexual
+  attention or advances
+- Trolling, insulting/derogatory comments, and personal or political
+  attacks
+- Public or private harassment
+- Publishing others’ private information, such as a physical or
+  electronic address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
 
 ## Our Responsibilities
 

README.md

@@ -16,10 +16,10 @@
 
 ## Features
 
--   Exploratory and targeted analysis of Electronic Health Records
--   Quality control & preprocessing
--   Visualization & Exploration
--   Clustering & trajectory inference
+- Exploratory and targeted analysis of Electronic Health Records
+- Quality control & preprocessing
+- Visualization & Exploration
+- Clustering & trajectory inference
 
 ## Installation
 

docs/_ext/typed_returns.py

@@ -10,7 +10,7 @@ def _process_return(lines: Iterable[str]) -> Iterator[str]:
         m = re.fullmatch(r"(?P<param>\w+)\s+:\s+(?P<type>[\w.]+)", line)
         if m:
             # Once this is in scanpydoc, we can use the fancy hover stuff
-            yield f'**{m["param"]}** : :class:`~{m["type"]}`'
+            yield f"**{m['param']}** : :class:`~{m['type']}`"
         else:
             yield line
 

docs/contributing.md

@@ -126,11 +126,11 @@ in the cookiecutter-scverse template.
 
 Please write documentation for new or changed features and use-cases. This project uses [sphinx][] with the following features:
 
--   the [myst][] extension allows to write documentation in markdown/Markedly Structured Text
--   Google-style docstrings
--   Jupyter notebooks as tutorials through [myst-nb][] (See [Tutorials with myst-nb](#tutorials-with-myst-nb-and-jupyter-notebooks))
--   [Sphinx autodoc typehints][], to automatically reference annotated input and output types
--   Citations (like {cite:p}`Virshup_2023`) can be included with [sphinxcontrib-bibtex](https://sphinxcontrib-bibtex.readthedocs.io/)
+- the [myst][] extension allows to write documentation in markdown/Markedly Structured Text
+- Google-style docstrings
+- Jupyter notebooks as tutorials through [myst-nb][] (See [Tutorials with myst-nb](#tutorials-with-myst-nb-and-jupyter-notebooks))
+- [Sphinx autodoc typehints][], to automatically reference annotated input and output types
+- Citations (like {cite:p}`Virshup_2023`) can be included with [sphinxcontrib-bibtex](https://sphinxcontrib-bibtex.readthedocs.io/)
 
 See the [scanpy developer docs](https://scanpy.readthedocs.io/en/latest/dev/documentation.html) for more information
 on how to write documentation.
@@ -144,10 +144,10 @@ These notebooks come from [pert-tutorials](https://github.com/theislab/ehrapy-tu
 
 #### Hints
 
--   If you refer to objects from other packages, please add an entry to `intersphinx_mapping` in `docs/conf.py`. Only
-    if you do so can sphinx automatically create a link to the external documentation.
--   If building the documentation fails because of a missing link that is outside your control, you can add an entry to
-    the `nitpick_ignore` list in `docs/conf.py`
+- If you refer to objects from other packages, please add an entry to `intersphinx_mapping` in `docs/conf.py`. Only
+  if you do so can sphinx automatically create a link to the external documentation.
+- If building the documentation fails because of a missing link that is outside your control, you can add an entry to
+  the `nitpick_ignore` list in `docs/conf.py`
 
 #### Building the docs locally
 

docs/index.md

@@ -61,8 +61,8 @@ medRxiv 2023.12.11.23299816; doi: https://doi.org/10.1101/2023.12.11.23299816 ](
 
 # Indices and tables
 
--   {ref}`genindex`
--   {ref}`modindex`
--   {ref}`search`
+- {ref}`genindex`
+- {ref}`modindex`
+- {ref}`search`
 
 [scanpy genome biology (2018)]: https://doi.org/10.1186/s13059-017-1382-0

docs/installation.md

@@ -51,10 +51,10 @@ pip install ehrapy[medcat]
 
 Available language models are
 
--   en_core_web_md (python -m spacy download en_core_web_md)
--   en-core-sci-sm (pip install <https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_sm-0.4.0.tar.gz>)
--   en-core-sci-md (pip install <https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_md-0.4.0.tar.gz>)
--   en-core-sci-lg (pip install <https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_lg-0.4.0.tar.gz>)
+- en_core_web_md (python -m spacy download en_core_web_md)
+- en-core-sci-sm (pip install <https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_sm-0.4.0.tar.gz>)
+- en-core-sci-md (pip install <https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_md-0.4.0.tar.gz>)
+- en-core-sci-lg (pip install <https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_lg-0.4.0.tar.gz>)
 
 [github repo]: https://github.com/theislab/ehrapy
 [pip]: https://pip.pypa.io

ehrapy/__init__.py

@@ -2,7 +2,12 @@
 
 __author__ = "Lukas Heumos"
 __email__ = "[email protected]"
-__version__ = "0.9.0"
+__version__ = "0.12.0"
+
+import os
+
+# https://docs.scipy.org/doc/scipy/dev/api-dev/array_api.html
+os.environ["SCIPY_ARRAY_API"] = "1"
 
 from ehrapy._settings import EhrapyConfig, ehrapy_settings
 

ehrapy/_compat.py

@@ -1,7 +1,6 @@
 # Since we might check whether an object is an instance of dask.array.Array
 # without requiring dask installed in the environment.
-# This would become obsolete should dask become a requirement for ehrapy
-
+from collections.abc import Callable
 
 try:
     import dask.array as da
@@ -11,6 +10,12 @@
     DASK_AVAILABLE = False
 
 
+def _raise_array_type_not_implemented(func: Callable, type_: type) -> NotImplementedError:
+    raise NotImplementedError(
+        f"{func.__name__} does not support array type {type_}. Must be of type {func.registry.keys()}."  # type: ignore
+    )
+
+
 def is_dask_array(array):
     if DASK_AVAILABLE:
         return isinstance(array, da.Array)

ehrapy/_settings.py

@@ -144,7 +144,7 @@ def file_format_data(self, file_format: str):
         _type_check(file_format, "file_format_data", str)
         file_format_options = {"csv", "h5ad"}
         if file_format not in file_format_options:
-            raise ValueError(f"Cannot set file_format_data to {file_format}. " f"Must be one of {file_format_options}")
+            raise ValueError(f"Cannot set file_format_data to {file_format}. Must be one of {file_format_options}")
         self._file_format_data = file_format
 
     @property
@@ -237,7 +237,7 @@ def cache_compression(self) -> str | None:
     @cache_compression.setter
     def cache_compression(self, cache_compression: str | None):
         if cache_compression not in {"lzf", "gzip", None}:
-            raise ValueError(f"`cache_compression` ({cache_compression}) " "must be in {'lzf', 'gzip', None}")
+            raise ValueError(f"`cache_compression` ({cache_compression}) must be in {{'lzf', 'gzip', None}}")
         self._cache_compression = cache_compression
 
     @property

ehrapy/anndata/_feature_specifications.py

@@ -113,7 +113,7 @@ def infer_feature_types(
 
     if verbose:
         logger.warning(
-            f"{'Features' if len(uncertain_features) >1 else 'Feature'} {str(uncertain_features)[1:-1]} {'were' if len(uncertain_features) >1 else 'was'} detected as categorical features stored numerically."
+            f"{'Features' if len(uncertain_features) > 1 else 'Feature'} {str(uncertain_features)[1:-1]} {'were' if len(uncertain_features) > 1 else 'was'} detected as categorical features stored numerically."
             f"Please verify and correct using `ep.ad.replace_feature_types` if necessary."
         )
 

ehrapy/core/meta_information.py

@@ -3,9 +3,7 @@
 import sys
 from datetime import datetime
 
-import session_info
 from rich import print
-from scanpy.logging import _versions_dependencies
 
 from ehrapy import __version__
 
@@ -17,56 +15,27 @@ def print_versions():  # pragma: no cover
         >>> import ehrapy as ep
         >>> ep.print_versions()
     """
-    try:
-        session_info.show(
-            dependencies=True,
-            html=False,
-            excludes=[
-                "builtins",
-                "stdlib_list",
-                "importlib_metadata",
-                "jupyter_core"
-                # Special module present if test coverage being calculated
-                # https://gitlab.com/joelostblom/session_info/-/issues/10
-                "$coverage",
-            ],
-        )
-    except AttributeError:
-        print("[bold yellow]Unable to fetch versions for one or more dependencies.")
-        pass
+    print_header()
 
 
 def print_version_and_date(*, file=None):  # pragma: no cover
     """Useful for starting a notebook so you see when you started working."""
     if file is None:
         file = sys.stdout
     print(
-        f"Running ehrapy {__version__}, " f"on {datetime.now():%Y-%m-%d %H:%M}.",
+        f"Running ehrapy {__version__}, on {datetime.now():%Y-%m-%d %H:%M}.",
         file=file,
     )
 
 
 def print_header(*, file=None):  # pragma: no cover
-    """Versions that might influence the numerical results.
+    """Versions that might influence the numerical results."""
+    from session_info2 import session_info
 
-    Matplotlib and Seaborn are excluded from this.
-    """
-    _DEPENDENCIES_NUMERICS = [
-        "scanpy",
-        "anndata",
-        "umap",
-        "numpy",
-        "scipy",
-        "pandas",
-        ("sklearn", "scikit-learn"),
-        "statsmodels",
-        ("igraph", "python-igraph"),
-        "leidenalg",
-        "pynndescent",
-    ]
+    sinfo = session_info(os=True, cpu=True, gpu=True, dependencies=True)
 
-    modules = ["ehrapy"] + _DEPENDENCIES_NUMERICS
-    print(
-        " ".join(f"{mod}=={ver}" for mod, ver in _versions_dependencies(modules)),
-        file=file or sys.stdout,
-    )
+    if file is not None:
+        print(sinfo, file=file)
+        return
+
+    return sinfo

ehrapy/plot/_scanpy_pl_api.py

@@ -1188,7 +1188,10 @@ def tsne(adata, **kwargs) -> Axes | list[Axes] | None:  # pragma: no cover
         .. image:: /_static/docstring_previews/tsne_1.png
 
         >>> ep.pl.tsne(
-        ...     adata, color=["day_icu_intime", "service_unit"], wspace=0.5, title=["Day of ICU admission", "Service unit"]
+        ...     adata,
+        ...     color=["day_icu_intime", "service_unit"],
+        ...     wspace=0.5,
+        ...     title=["Day of ICU admission", "Service unit"],
         ... )
 
         .. image:: /_static/docstring_previews/tsne_2.png
@@ -1233,7 +1236,10 @@ def umap(adata: AnnData, **kwargs) -> Axes | list[Axes] | None:  # pragma: no co
         .. image:: /_static/docstring_previews/umap_1.png
 
         >>> ep.pl.umap(
-        ...     adata, color=["day_icu_intime", "service_unit"], wspace=0.5, title=["Day of ICU admission", "Service unit"]
+        ...     adata,
+        ...     color=["day_icu_intime", "service_unit"],
+        ...     wspace=0.5,
+        ...     title=["Day of ICU admission", "Service unit"],
         ... )
 
         .. image:: /_static/docstring_previews/umap_2.png
@@ -1984,7 +1990,8 @@ def paga_compare(
         save=save,
         title_graph=title_graph,
         groups_graph=groups_graph,
-        pos=pos**paga_graph_params,
+        pos=pos,
+        **paga_graph_params,
     )